Daily Papers

Diffusion-based models have shown strong performance in video super-resolution (VSR) and video frame interpolation (VFI). However, their role in the coupled space-time video super-resolution (STVSR) setting remains limited. Existing diffusion-based STVSR approaches suffer from two issues: (1) low inference efficiency and (2) insufficient utilization of spatiotemporal information. These limitations impede deployment. To address these issues, we introduce DiffST, an efficient spatiotemporal-aware video diffusion framework for real-world STVSR. To improve efficiency, we adapt a pre-trained diffusion model for one-step sampling and process the entire video directly rather than operating on individual frames. Furthermore, to enhance spatiotemporal information utilization, we introduce cross-frame context aggregation (CFCA) and video representation guidance (VRG). The CFCA module aggregates information across multiple keyframes to produce intermediate frames. The VRG module extracts video-level global features to guide the diffusion process. Extensive experiments show that DiffST obtains leading results on real-world STVSR tasks. It also maintains high inference efficiency, running about 17times faster than previous diffusion-based STVSR methods. Code is available at: https://github.com/zhengchen1999/DiffST.

Video Large Language Models (VLLMs) demonstrate strong video understanding but suffer from inefficiency due to redundant visual tokens. Existing pruning primary targets intra-frame spatial redundancy or prunes inside the LLM with shallow-layer overhead, yielding suboptimal spatiotemporal reduction and underutilizing long-context compressibility. All of them often discard subtle yet informative context from merged or pruned tokens. In this paper, we propose a new perspective that elaborates token Anchors within intra-frame and inter-frame to comprehensively aggregate the informative contexts via local-global Optimal Transport (AOT). Specifically, we first establish local- and global-aware token anchors within each frame under the attention guidance, which then optimal transport aggregates the informative contexts from pruned tokens, constructing intra-frame token anchors. Then, building on the temporal frame clips, the first frame within each clip will be considered as the keyframe anchors to ensemble similar information from consecutive frames through optimal transport, while keeping distinct tokens to represent temporal dynamics, leading to efficient token reduction in a training-free manner. Extensive evaluations show that our proposed AOT obtains competitive performances across various short- and long-video benchmarks on leading video LLMs, obtaining substantial computational efficiency while preserving temporal and visual fidelity. Project webpage: https://tyroneli.github.io/AOT{AOT}.

In this paper, we re-examine the task of cross-modal clip-sentence retrieval, where the clip is part of a longer untrimmed video. When the clip is short or visually ambiguous, knowledge of its local temporal context (i.e. surrounding video segments) can be used to improve the retrieval performance. We propose Context Transformer (ConTra); an encoder architecture that models the interaction between a video clip and its local temporal context in order to enhance its embedded representations. Importantly, we supervise the context transformer using contrastive losses in the cross-modal embedding space. We explore context transformers for video and text modalities. Results consistently demonstrate improved performance on three datasets: YouCook2, EPIC-KITCHENS and a clip-sentence version of ActivityNet Captions. Exhaustive ablation studies and context analysis show the efficacy of the proposed method.

In this paper, we introduce the Context-Aware Video Instance Segmentation (CAVIS), a novel framework designed to enhance instance association by integrating contextual information adjacent to each object. To efficiently extract and leverage this information, we propose the Context-Aware Instance Tracker (CAIT), which merges contextual data surrounding the instances with the core instance features to improve tracking accuracy. Additionally, we design the Prototypical Cross-frame Contrastive (PCC) loss, which ensures consistency in object-level features across frames, thereby significantly enhancing matching accuracy. CAVIS demonstrates superior performance over state-of-the-art methods on all benchmark datasets in video instance segmentation (VIS) and video panoptic segmentation (VPS). Notably, our method excels on the OVIS dataset, known for its particularly challenging videos. Project page: https://seung-hun-lee.github.io/projects/CAVIS/

CLIP4Clip model transferred from the CLIP has been the de-factor standard to solve the video clip retrieval task from frame-level input, triggering the surge of CLIP4Clip-based models in the video-text retrieval domain. In this work, we rethink the inherent limitation of widely-used mean pooling operation in the frame features aggregation and investigate the adaptions of excitation and aggregation design for discriminative video representation generation. We present a novel excitationand-aggregation design, including (1) The excitation module is available for capturing non-mutuallyexclusive relationships among frame features and achieving frame-wise features recalibration, and (2) The aggregation module is applied to learn exclusiveness used for frame representations aggregation. Similarly, we employ the cascade of sequential module and aggregation design to generate discriminative video representation in the sequential type. Besides, we adopt the excitation design in the tight type to obtain representative frame features for multi-modal interaction. The proposed modules are evaluated on three benchmark datasets of MSR-VTT, ActivityNet and DiDeMo, achieving MSR-VTT (43.9 R@1), ActivityNet (44.1 R@1) and DiDeMo (31.0 R@1). They outperform the CLIP4Clip results by +1.2% (+0.5%), +4.5% (+1.9%) and +9.5% (+2.7%) relative (absolute) improvements, demonstrating the superiority of our proposed excitation and aggregation designs. We hope our work will serve as an alternative for frame representations aggregation and facilitate future research.

In text-video retrieval, the objective is to learn a cross-modal similarity function between a text and a video that ranks relevant text-video pairs higher than irrelevant pairs. However, videos inherently express a much wider gamut of information than texts. Instead, texts often capture sub-regions of entire videos and are most semantically similar to certain frames within videos. Therefore, for a given text, a retrieval model should focus on the text's most semantically similar video sub-regions to make a more relevant comparison. Yet, most existing works aggregate entire videos without directly considering text. Common text-agnostic aggregations schemes include mean-pooling or self-attention over the frames, but these are likely to encode misleading visual information not described in the given text. To address this, we propose a cross-modal attention model called X-Pool that reasons between a text and the frames of a video. Our core mechanism is a scaled dot product attention for a text to attend to its most semantically similar frames. We then generate an aggregated video representation conditioned on the text's attention weights over the frames. We evaluate our method on three benchmark datasets of MSR-VTT, MSVD and LSMDC, achieving new state-of-the-art results by up to 12% in relative improvement in Recall@1. Our findings thereby highlight the importance of joint text-video reasoning to extract important visual cues according to text. Full code and demo can be found at: https://layer6ai-labs.github.io/xpool/

Exploiting fine-grained correspondence and visual-semantic alignments has shown great potential in image-text matching. Generally, recent approaches first employ a cross-modal attention unit to capture latent region-word interactions, and then integrate all the alignments to obtain the final similarity. However, most of them adopt one-time forward association or aggregation strategies with complex architectures or additional information, while ignoring the regulation ability of network feedback. In this paper, we develop two simple but quite effective regulators which efficiently encode the message output to automatically contextualize and aggregate cross-modal representations. Specifically, we propose (i) a Recurrent Correspondence Regulator (RCR) which facilitates the cross-modal attention unit progressively with adaptive attention factors to capture more flexible correspondence, and (ii) a Recurrent Aggregation Regulator (RAR) which adjusts the aggregation weights repeatedly to increasingly emphasize important alignments and dilute unimportant ones. Besides, it is interesting that RCR and RAR are plug-and-play: both of them can be incorporated into many frameworks based on cross-modal interaction to obtain significant benefits, and their cooperation achieves further improvements. Extensive experiments on MSCOCO and Flickr30K datasets validate that they can bring an impressive and consistent R@1 gain on multiple models, confirming the general effectiveness and generalization ability of the proposed methods. Code and pre-trained models are available at: https://github.com/Paranioar/RCAR.

We present the content deformation field CoDeF as a new type of video representation, which consists of a canonical content field aggregating the static contents in the entire video and a temporal deformation field recording the transformations from the canonical image (i.e., rendered from the canonical content field) to each individual frame along the time axis.Given a target video, these two fields are jointly optimized to reconstruct it through a carefully tailored rendering pipeline.We advisedly introduce some regularizations into the optimization process, urging the canonical content field to inherit semantics (e.g., the object shape) from the video.With such a design, CoDeF naturally supports lifting image algorithms for video processing, in the sense that one can apply an image algorithm to the canonical image and effortlessly propagate the outcomes to the entire video with the aid of the temporal deformation field.We experimentally show that CoDeF is able to lift image-to-image translation to video-to-video translation and lift keypoint detection to keypoint tracking without any training.More importantly, thanks to our lifting strategy that deploys the algorithms on only one image, we achieve superior cross-frame consistency in processed videos compared to existing video-to-video translation approaches, and even manage to track non-rigid objects like water and smog.Project page can be found at https://qiuyu96.github.io/CoDeF/.

Our goal in this paper is the adaptation of image-text models for long video retrieval. Recent works have demonstrated state-of-the-art performance in video retrieval by adopting CLIP, effectively hitchhiking on the image-text representation for video tasks. However, there has been limited success in learning temporal aggregation that outperform mean-pooling the image-level representations extracted per frame by CLIP. We find that the simple yet effective baseline of weighted-mean of frame embeddings via query-scoring is a significant improvement above all prior temporal modelling attempts and mean-pooling. In doing so, we provide an improved baseline for others to compare to and demonstrate state-of-the-art performance of this simple baseline on a suite of long video retrieval benchmarks.

Motivated by the success of coarse-grained or fine-grained contrast in text-video retrieval, there emerge multi-grained contrastive learning methods which focus on the integration of contrasts with different granularity. However, due to the wider semantic range of videos, the text-agnostic video representations might encode misleading information not described in texts, thus impeding the model from capturing precise cross-modal semantic correspondence. To this end, we propose a Text-Conditioned Multi-Grained Contrast framework, dubbed TC-MGC. Specifically, our model employs a language-video attention block to generate aggregated frame and video representations conditioned on the word's and text's attention weights over frames. To filter unnecessary similarity interactions and decrease trainable parameters in the Interactive Similarity Aggregation (ISA) module, we design a Similarity Reorganization (SR) module to identify attentive similarities and reorganize cross-modal similarity vectors and matrices. Next, we argue that the imbalance problem among multigrained similarities may result in over- and under-representation issues. We thereby introduce an auxiliary Similarity Decorrelation Regularization (SDR) loss to facilitate cooperative relationship utilization by similarity variance minimization on matching text-video pairs. Finally, we present a Linear Softmax Aggregation (LSA) module to explicitly encourage the interactions between multiple similarities and promote the usage of multi-grained information. Empirically, TC-MGC achieves competitive results on multiple text-video retrieval benchmarks, outperforming X-CLIP model by +2.8% (+1.3%), +2.2% (+1.0%), +1.5% (+0.9%) relative (absolute) improvements in text-to-video retrieval R@1 on MSR-VTT, DiDeMo and VATEX, respectively. Our code is publicly available at https://github.com/JingXiaolun/TC-MGC.

In-context learning for vision data has been underexplored compared with that in natural language. Previous works studied image in-context learning, urging models to generate a single image guided by demonstrations. In this paper, we propose and study video in-context learning, where the model starts from an existing video clip and generates diverse potential future sequences, each semantically guided by the prompted video demonstrations. To achieve this, we provide a clear definition of the task, and train an autoregressive Transformer on video datasets. We thoroughly analyze the effect of different datasets and represent frames as discrete tokens, and then model them by next token predictions. We design various evaluation metrics, including both objective and subjective measures, to demonstrate the visual quality and semantic accuracy of generation results. Our model follows the scaling law and generates high-quality video clips that accurately align with the semantic guidance provided by in-context examples.

This paper introduces SuperGlue, a neural network that matches two sets of local features by jointly finding correspondences and rejecting non-matchable points. Assignments are estimated by solving a differentiable optimal transport problem, whose costs are predicted by a graph neural network. We introduce a flexible context aggregation mechanism based on attention, enabling SuperGlue to reason about the underlying 3D scene and feature assignments jointly. Compared to traditional, hand-designed heuristics, our technique learns priors over geometric transformations and regularities of the 3D world through end-to-end training from image pairs. SuperGlue outperforms other learned approaches and achieves state-of-the-art results on the task of pose estimation in challenging real-world indoor and outdoor environments. The proposed method performs matching in real-time on a modern GPU and can be readily integrated into modern SfM or SLAM systems. The code and trained weights are publicly available at https://github.com/magicleap/SuperGluePretrainedNetwork.

3D dense captioning is a task involving the localization of objects and the generation of descriptions for each object in a 3D scene. Recent approaches have attempted to incorporate contextual information by modeling relationships with object pairs or aggregating the nearest neighbor features of an object. However, the contextual information constructed in these scenarios is limited in two aspects: first, objects have multiple positional relationships that exist across the entire global scene, not only near the object itself. Second, it faces with contradicting objectives--where localization and attribute descriptions are generated better with tight localization, while descriptions involving global positional relations are generated better with contextualized features of the global scene. To overcome this challenge, we introduce BiCA, a transformer encoder-decoder pipeline that engages in 3D dense captioning for each object with Bi-directional Contextual Attention. Leveraging parallelly decoded instance queries for objects and context queries for non-object contexts, BiCA generates object-aware contexts, where the contexts relevant to each object is summarized, and context-aware objects, where the objects relevant to the summarized object-aware contexts are aggregated. This extension relieves previous methods from the contradicting objectives, enhancing both localization performance and enabling the aggregation of contextual features throughout the global scene; thus improving caption generation performance simultaneously. Extensive experiments on two of the most widely-used 3D dense captioning datasets demonstrate that our proposed method achieves a significant improvement over prior methods.

Online video understanding is essential for applications like public surveillance and AI glasses. However, applying Multimodal Large Language Models (MLLMs) to this domain is challenging due to the large number of video frames, resulting in high GPU memory usage and computational latency. To address these challenges, we propose token pruning as a means to reduce context length while retaining critical information. Specifically, we introduce a novel redundancy metric, Maximum Similarity to Spatially Adjacent Video Tokens (MSSAVT), which accounts for both token similarity and spatial position. To mitigate the bidirectional dependency between pruning and redundancy, we further design a masked pruning strategy that ensures only mutually unadjacent tokens are pruned. We also integrate an existing temporal redundancy-based pruning method to eliminate temporal redundancy of the video modality. Experimental results on multiple online and offline video understanding benchmarks demonstrate that our method significantly improves the accuracy (i.e., by 4\% at most) while incurring a negligible pruning latency (i.e., less than 1ms). Our full implementation will be made publicly available.

Conditional diffusion models have exhibited superior performance in high-fidelity text-guided visual generation and editing. Nevertheless, prevailing text-guided visual diffusion models primarily focus on incorporating text-visual relationships exclusively into the reverse process, often disregarding their relevance in the forward process. This inconsistency between forward and reverse processes may limit the precise conveyance of textual semantics in visual synthesis results. To address this issue, we propose a novel and general contextualized diffusion model (ContextDiff) by incorporating the cross-modal context encompassing interactions and alignments between text condition and visual sample into forward and reverse processes. We propagate this context to all timesteps in the two processes to adapt their trajectories, thereby facilitating cross-modal conditional modeling. We generalize our contextualized diffusion to both DDPMs and DDIMs with theoretical derivations, and demonstrate the effectiveness of our model in evaluations with two challenging tasks: text-to-image generation, and text-to-video editing. In each task, our ContextDiff achieves new state-of-the-art performance, significantly enhancing the semantic alignment between text condition and generated samples, as evidenced by quantitative and qualitative evaluations. Our code is available at https://github.com/YangLing0818/ContextDiff

Books are a rich source of both fine-grained information, how a character, an object or a scene looks like, as well as high-level semantics, what someone is thinking, feeling and how these states evolve through a story. This paper aims to align books to their movie releases in order to provide rich descriptive explanations for visual content that go semantically far beyond the captions available in current datasets. To align movies and books we exploit a neural sentence embedding that is trained in an unsupervised way from a large corpus of books, as well as a video-text neural embedding for computing similarities between movie clips and sentences in the book. We propose a context-aware CNN to combine information from multiple sources. We demonstrate good quantitative performance for movie/book alignment and show several qualitative examples that showcase the diversity of tasks our model can be used for.

In this paper, we address the semantic segmentation problem with a focus on the context aggregation strategy. Our motivation is that the label of a pixel is the category of the object that the pixel belongs to. We present a simple yet effective approach, object-contextual representations, characterizing a pixel by exploiting the representation of the corresponding object class. First, we learn object regions under the supervision of ground-truth segmentation. Second, we compute the object region representation by aggregating the representations of the pixels lying in the object region. Last, % the representation similarity we compute the relation between each pixel and each object region and augment the representation of each pixel with the object-contextual representation which is a weighted aggregation of all the object region representations according to their relations with the pixel. We empirically demonstrate that the proposed approach achieves competitive performance on various challenging semantic segmentation benchmarks: Cityscapes, ADE20K, LIP, PASCAL-Context, and COCO-Stuff. Cityscapes, ADE20K, LIP, PASCAL-Context, and COCO-Stuff. Our submission "HRNet + OCR + SegFix" achieves 1-st place on the Cityscapes leaderboard by the time of submission. Code is available at: https://git.io/openseg and https://git.io/HRNet.OCR. We rephrase the object-contextual representation scheme using the Transformer encoder-decoder framework. The details are presented in~Section3.3.

Omnimodal Large Language Models (Omni-LLMs) incur substantial computational overhead due to the large number of multimodal input tokens they process, making token reduction essential for real-world deployment. Existing Omni-LLM pruning methods typically reduce this cost by selecting tokens that are important for the current query or strongly aligned with cross-modal cues. However, such strategies can discard evidence that falls outside these criteria, even when needed for different questions or for understanding context beyond aligned audio-visual cues. To address this limitation, we reframe Omni-LLM token reduction as preserving broad audio-visual context while removing cross-modal redundancy. We propose ContextGuard, an inference-time token pruning framework built on this principle. ContextGuard predicts coarse visual semantics from audio and prunes video tokens whose coarse semantics are likely recoverable from audio, while retaining additional video tokens to preserve localized visual details that audio alone cannot specify. For further compression, our method merges temporally similar video tokens. The framework requires no downstream LLM fine-tuning and uses only an independently trained lightweight predictor. On Qwen2.5-Omni and Video-SALMONN2+ at 3B and 7B scales across six audio-visual benchmarks, ContextGuard outperforms prior inference-time pruning methods while pruning more tokens. Notably, on Qwen2.5-Omni 7B, ContextGuard achieves full-token-level performance on five of six benchmarks while pruning 55% of input tokens.

In Video Object Detection (VID), a common practice is to leverage the rich temporal contexts from the video to enhance the object representations in each frame. Existing methods treat the temporal contexts obtained from different objects indiscriminately and ignore their different identities. While intuitively, aggregating local views of the same object in different frames may facilitate a better understanding of the object. Thus, in this paper, we aim to enable the model to focus on the identity-consistent temporal contexts of each object to obtain more comprehensive object representations and handle the rapid object appearance variations such as occlusion, motion blur, etc. However, realizing this goal on top of existing VID models faces low-efficiency problems due to their redundant region proposals and nonparallel frame-wise prediction manner. To aid this, we propose ClipVID, a VID model equipped with Identity-Consistent Aggregation (ICA) layers specifically designed for mining fine-grained and identity-consistent temporal contexts. It effectively reduces the redundancies through the set prediction strategy, making the ICA layers very efficient and further allowing us to design an architecture that makes parallel clip-wise predictions for the whole video clip. Extensive experimental results demonstrate the superiority of our method: a state-of-the-art (SOTA) performance (84.7% mAP) on the ImageNet VID dataset while running at a speed about 7x faster (39.3 fps) than previous SOTAs.

We consider retrieving a specific temporal segment, or moment, from a video given a natural language text description. Methods designed to retrieve whole video clips with natural language determine what occurs in a video but not when. To address this issue, we propose the Moment Context Network (MCN) which effectively localizes natural language queries in videos by integrating local and global video features over time. A key obstacle to training our MCN model is that current video datasets do not include pairs of localized video segments and referring expressions, or text descriptions which uniquely identify a corresponding moment. Therefore, we collect the Distinct Describable Moments (DiDeMo) dataset which consists of over 10,000 unedited, personal videos in diverse visual settings with pairs of localized video segments and referring expressions. We demonstrate that MCN outperforms several baseline methods and believe that our initial results together with the release of DiDeMo will inspire further research on localizing video moments with natural language.

Vision-language models (VLMs) have advanced video understanding, but their performance is limited by the number of input frames they can process. Existing frame sampling strategies, such as uniform or fixed-budget selection, often fail to adapt to variations in information density or task complexity, resulting in inefficiency and information loss. To address this, we present FrameOracle, a lightweight and plug-and-play module that predicts both (1) which frames are most relevant to a given query and (2) how many frames are needed. FrameOracle is trained using a four-stage curriculum, with the first three stages relying on weak proxy signals such as cross-modal similarity. In the final stage, it leverages stronger supervision from a new dataset we introduce, FrameOracle-41K, the first large-scale VideoQA collection to provide keyframe annotations specifying the minimal set of frames required to answer each question. Extensive experiments across five VLMs and six benchmarks demonstrate that FrameOracle reduces 16-frame inputs to an average of 10.4 frames without any loss in accuracy. When starting from 64-frame candidates, it reduces the input to an average of 13.9 frames while improving accuracy by 1.4%, achieving state-of-the-art efficiency-accuracy trade-offs for scalable video understanding.

The alignment of representations from different modalities has recently been shown to provide insights on the structural similarities and downstream capabilities of different encoders across diverse data types. While significant progress has been made in aligning images with text, the temporal nature of video data remains largely unexplored in this context. In this work, we conduct the first comprehensive study of video-text representation alignment, probing the capabilities of modern video and language encoders. Our findings reveal several key insights. First, we demonstrate that cross-modal alignment highly depends on the richness of both visual (static images vs. multi-frame videos) and text (single caption vs. a collection) data provided at test time, especially when using state-of-the-art video encoders. We propose parametric test-time scaling laws that capture this behavior and show remarkable predictive power against empirical observations. Secondly, we investigate the correlation between semantic alignment and performance on both semantic and non-semantic downstream tasks, providing initial evidence that strong alignment against text encoders may be linked to general-purpose video representation and understanding. Finally, we correlate temporal reasoning with cross-modal alignment providing a challenging test-bed for vision and language models. Overall, our work introduces video-text alignment as an informative zero-shot way to probe the representation power of different encoders for spatio-temporal data. Project page can be found at https://video-prh.github.io/

Long-context autoregressive modeling has significantly advanced language generation, but video generation still struggles to fully utilize extended temporal contexts. To investigate long-context video modeling, we introduce Frame AutoRegressive (FAR), a strong baseline for video autoregressive modeling. Just as language models learn causal dependencies between tokens (i.e., Token AR), FAR models temporal causal dependencies between continuous frames, achieving better convergence than Token AR and video diffusion transformers. Building on FAR, we observe that long-context vision modeling faces challenges due to visual redundancy. Existing RoPE lacks effective temporal decay for remote context and fails to extrapolate well to long video sequences. Additionally, training on long videos is computationally expensive, as vision tokens grow much faster than language tokens. To tackle these issues, we propose balancing locality and long-range dependency. We introduce FlexRoPE, an test-time technique that adds flexible temporal decay to RoPE, enabling extrapolation to 16x longer vision contexts. Furthermore, we propose long short-term context modeling, where a high-resolution short-term context window ensures fine-grained temporal consistency, while an unlimited long-term context window encodes long-range information using fewer tokens. With this approach, we can train on long video sequences with a manageable token context length. We demonstrate that FAR achieves state-of-the-art performance in both short- and long-video generation, providing a simple yet effective baseline for video autoregressive modeling.

This paper presents a simple yet effective approach to modeling space-time correspondences in the context of video object segmentation. Unlike most existing approaches, we establish correspondences directly between frames without re-encoding the mask features for every object, leading to a highly efficient and robust framework. With the correspondences, every node in the current query frame is inferred by aggregating features from the past in an associative fashion. We cast the aggregation process as a voting problem and find that the existing inner-product affinity leads to poor use of memory with a small (fixed) subset of memory nodes dominating the votes, regardless of the query. In light of this phenomenon, we propose using the negative squared Euclidean distance instead to compute the affinities. We validated that every memory node now has a chance to contribute, and experimentally showed that such diversified voting is beneficial to both memory efficiency and inference accuracy. The synergy of correspondence networks and diversified voting works exceedingly well, achieves new state-of-the-art results on both DAVIS and YouTubeVOS datasets while running significantly faster at 20+ FPS for multiple objects without bells and whistles.

The canonical approach to video-text retrieval leverages a coarse-grained or fine-grained alignment between visual and textual information. However, retrieving the correct video according to the text query is often challenging as it requires the ability to reason about both high-level (scene) and low-level (object) visual clues and how they relate to the text query. To this end, we propose a Unified Coarse-to-fine Alignment model, dubbed UCoFiA. Specifically, our model captures the cross-modal similarity information at different granularity levels. To alleviate the effect of irrelevant visual clues, we also apply an Interactive Similarity Aggregation module (ISA) to consider the importance of different visual features while aggregating the cross-modal similarity to obtain a similarity score for each granularity. Finally, we apply the Sinkhorn-Knopp algorithm to normalize the similarities of each level before summing them, alleviating over- and under-representation issues at different levels. By jointly considering the crossmodal similarity of different granularity, UCoFiA allows the effective unification of multi-grained alignments. Empirically, UCoFiA outperforms previous state-of-the-art CLIP-based methods on multiple video-text retrieval benchmarks, achieving 2.4%, 1.4% and 1.3% improvements in text-to-video retrieval R@1 on MSR-VTT, Activity-Net, and DiDeMo, respectively. Our code is publicly available at https://github.com/Ziyang412/UCoFiA.

The exponential growth of Large Multimodal Models (LMMs) has driven advancements in cross-modal reasoning but at significant computational costs. In this work, we focus on visual language models. We highlight the redundancy and inefficiency in current vision encoders, and seek to construct an adaptive compression method for multimodal data. In this work, we characterize a panoply of visual token selection and merging approaches through both benchmarking and qualitative analysis. In particular, we demonstrate that simple cluster-level token aggregation outperforms prior state-of-the-art works in token selection and merging, including merging at the vision encoder level and attention-based approaches. We underline the redundancy in current vision encoders, and shed light on several puzzling trends regarding principles of visual token selection through cross-modal attention visualizations. This work is a first effort towards more effective encoding and processing of high-dimensional data, and paves the way for more scalable and sustainable multimodal systems.

In various video-language learning tasks, the challenge of achieving cross-modality alignment with multi-grained data persists. We propose a method to tackle this challenge from two crucial perspectives: data and modeling. Given the absence of a multi-grained video-text pretraining dataset, we introduce a Granularity EXpansion (GEX) method with Integration and Compression operations to expand the granularity of a single-grained dataset. To better model multi-grained data, we introduce an Iterative Approximation Module (IAM), which embeds multi-grained videos and texts into a unified, low-dimensional semantic space while preserving essential information for cross-modal alignment. Furthermore, GEXIA is highly scalable with no restrictions on the number of video-text granularities for alignment. We evaluate our work on three categories of video tasks across seven benchmark datasets, showcasing state-of-the-art or comparable performance. Remarkably, our model excels in tasks involving long-form video understanding, even though the pretraining dataset only contains short video clips.

Achieving fine-grained spatio-temporal understanding in videos remains a major challenge for current Video Large Multimodal Models (Video LMMs). Addressing this challenge requires mastering two core capabilities: video referring understanding, which captures the semantics of video regions, and video grounding, which segments object regions based on natural language descriptions. However, most existing approaches tackle these tasks in isolation, limiting progress toward unified, referentially grounded video interaction. We identify a key bottleneck in the lack of high-quality, unified video instruction data and a comprehensive benchmark for evaluating referentially grounded video chat. To address these challenges, we contribute in three core aspects: dataset, model, and benchmark. First, we introduce SAMA-239K, a large-scale dataset comprising 15K videos specifically curated to enable joint learning of video referring understanding, grounding, and multi-turn video chat. Second, we propose the SAMA model, which incorporates a versatile spatio-temporal context aggregator and a Segment Anything Model to jointly enhance fine-grained video comprehension and precise grounding capabilities. Finally, we establish SAMA-Bench, a meticulously designed benchmark consisting of 5,067 questions from 522 videos, to comprehensively evaluate the integrated capabilities of Video LMMs in multi-turn, spatio-temporal referring understanding and grounded dialogue. Extensive experiments and benchmarking results show that SAMA not only achieves strong performance on SAMA-Bench but also sets a new state-of-the-art on general grounding benchmarks, while maintaining highly competitive performance on standard visual understanding benchmarks.

Traditional studies emphasize the significance of context information in improving matting performance. Consequently, deep learning-based matting methods delve into designing pooling or affinity-based context aggregation modules to achieve superior results. However, these modules cannot well handle the context scale shift caused by the difference in image size during training and inference, resulting in matting performance degradation. In this paper, we revisit the context aggregation mechanisms of matting networks and find that a basic encoder-decoder network without any context aggregation modules can actually learn more universal context aggregation, thereby achieving higher matting performance compared to existing methods. Building on this insight, we present AEMatter, a matting network that is straightforward yet very effective. AEMatter adopts a Hybrid-Transformer backbone with appearance-enhanced axis-wise learning (AEAL) blocks to build a basic network with strong context aggregation learning capability. Furthermore, AEMatter leverages a large image training strategy to assist the network in learning context aggregation from data. Extensive experiments on five popular matting datasets demonstrate that the proposed AEMatter outperforms state-of-the-art matting methods by a large margin.

With the explosive growth of web videos and emerging large-scale vision-language pre-training models, e.g., CLIP, retrieving videos of interest with text instructions has attracted increasing attention. A common practice is to transfer text-video pairs to the same embedding space and craft cross-modal interactions with certain entities in specific granularities for semantic correspondence. Unfortunately, the intrinsic uncertainties of optimal entity combinations in appropriate granularities for cross-modal queries are understudied, which is especially critical for modalities with hierarchical semantics, e.g., video, text, etc. In this paper, we propose an Uncertainty-Adaptive Text-Video Retrieval approach, termed UATVR, which models each look-up as a distribution matching procedure. Concretely, we add additional learnable tokens in the encoders to adaptively aggregate multi-grained semantics for flexible high-level reasoning. In the refined embedding space, we represent text-video pairs as probabilistic distributions where prototypes are sampled for matching evaluation. Comprehensive experiments on four benchmarks justify the superiority of our UATVR, which achieves new state-of-the-art results on MSR-VTT (50.8%), VATEX (64.5%), MSVD (49.7%), and DiDeMo (45.8%). The code is available at https://github.com/bofang98/UATVR.

We introduce the task of retrieving relevant video moments from a large corpus of untrimmed, unsegmented videos given a natural language query. Our task poses unique challenges as a system must efficiently identify both the relevant videos and localize the relevant moments in the videos. To address these challenges, we propose SpatioTemporal Alignment with Language (STAL), a model that represents a video moment as a set of regions within a series of short video clips and aligns a natural language query to the moment's regions. Our alignment cost compares variable-length language and video features using symmetric squared Chamfer distance, which allows for efficient indexing and retrieval of the video moments. Moreover, aligning language features to regions within a video moment allows for finer alignment compared to methods that extract only an aggregate feature from the entire video moment. We evaluate our approach on two recently proposed datasets for temporal localization of moments in video with natural language (DiDeMo and Charades-STA) extended to our video corpus moment retrieval setting. We show that our STAL re-ranking model outperforms the recently proposed Moment Context Network on all criteria across all datasets on our proposed task, obtaining relative gains of 37% - 118% for average recall and up to 30% for median rank. Moreover, our approach achieves more than 130x faster retrieval and 8x smaller index size with a 1M video corpus in an approximate setting.

Natural image matting aims to estimate the alpha matte of the foreground from a given image. Various approaches have been explored to address this problem, such as interactive matting methods that use guidance such as click or trimap, and automatic matting methods tailored to specific objects. However, existing matting methods are designed for specific objects or guidance, neglecting the common requirement of aggregating global and local contexts in image matting. As a result, these methods often encounter challenges in accurately identifying the foreground and generating precise boundaries, which limits their effectiveness in unforeseen scenarios. In this paper, we propose a simple and universal matting framework, named Dual-Context Aggregation Matting (DCAM), which enables robust image matting with arbitrary guidance or without guidance. Specifically, DCAM first adopts a semantic backbone network to extract low-level features and context features from the input image and guidance. Then, we introduce a dual-context aggregation network that incorporates global object aggregators and local appearance aggregators to iteratively refine the extracted context features. By performing both global contour segmentation and local boundary refinement, DCAM exhibits robustness to diverse types of guidance and objects. Finally, we adopt a matting decoder network to fuse the low-level features and the refined context features for alpha matte estimation. Experimental results on five matting datasets demonstrate that the proposed DCAM outperforms state-of-the-art matting methods in both automatic matting and interactive matting tasks, which highlights the strong universality and high performance of DCAM. The source code is available at https://github.com/Windaway/DCAM.

This paper studies referring video object segmentation (RVOS) by boosting video-level visual-linguistic alignment. Recent approaches model the RVOS task as a sequence prediction problem and perform multi-modal interaction as well as segmentation for each frame separately. However, the lack of a global view of video content leads to difficulties in effectively utilizing inter-frame relationships and understanding textual descriptions of object temporal variations. To address this issue, we propose Semantic-assisted Object Cluster (SOC), which aggregates video content and textual guidance for unified temporal modeling and cross-modal alignment. By associating a group of frame-level object embeddings with language tokens, SOC facilitates joint space learning across modalities and time steps. Moreover, we present multi-modal contrastive supervision to help construct well-aligned joint space at the video level. We conduct extensive experiments on popular RVOS benchmarks, and our method outperforms state-of-the-art competitors on all benchmarks by a remarkable margin. Besides, the emphasis on temporal coherence enhances the segmentation stability and adaptability of our method in processing text expressions with temporal variations. Code will be available.

Multimodal Large Language Models (MLLMs) have demonstrated significant capabilities in image understanding, but long-video are constrained by context windows and computational cost. Uniform frame sampling often leads to substantial information loss. Meanwhile existing keyframe selection methods such as text-frame retrieval or RL-based frame optimization typically yield sparse and temporally disjointed frames, overlooking scene continuity and lacking flexibility for multi-scale frame selection. To address these limitations, we introduce K-frames, a novel paradigm for scene-driven keyframe selection that preserves temporal continuity. Instead of selecting individual frames, K-frames predicts semantically coherent, query-relevant clips, which enables any-k keyframes selection to meet diverse user budgets. To achieve this approach, we first introduce PeakClips, a dataset of 200K video highlights conditioned by query. Building on this dataset, K-frames learns clip2frame selection using a three-stage progressive curriculum. It involves two Supervised Fine-Tuning stages for temporal grounding and key-clip perception, followed by a Reinforcement Learning stage that directly optimizes the scene-driven prediction policy for downstream task without further annotations. Extensive experiments on major long-video understanding benchmarks demonstrate that K-frames provides an effective, interpretable, and plug-and-play solution for keyframe selection at various scales. Our dataset and model will be available.

In text-video retrieval, recent works have benefited from the powerful learning capabilities of pre-trained text-image foundation models (e.g., CLIP) by adapting them to the video domain. A critical problem for them is how to effectively capture the rich semantics inside the video using the image encoder of CLIP. To tackle this, state-of-the-art methods adopt complex cross-modal modeling techniques to fuse the text information into video frame representations, which, however, incurs severe efficiency issues in large-scale retrieval systems as the video representations must be recomputed online for every text query. In this paper, we discard this problematic cross-modal fusion process and aim to learn semantically-enhanced representations purely from the video, so that the video representations can be computed offline and reused for different texts. Concretely, we first introduce a spatial-temporal "Prompt Cube" into the CLIP image encoder and iteratively switch it within the encoder layers to efficiently incorporate the global video semantics into frame representations. We then propose to apply an auxiliary video captioning objective to train the frame representations, which facilitates the learning of detailed video semantics by providing fine-grained guidance in the semantic space. With a naive temporal fusion strategy (i.e., mean-pooling) on the enhanced frame representations, we obtain state-of-the-art performances on three benchmark datasets, i.e., MSR-VTT, MSVD, and LSMDC.

The application of Large Multimodal Models (LMMs) to long-form video understanding is constrained by limited context lengths and the computationally prohibitive cost of processing dense video tokens. Consequently, recent research has focused on query-aware frame selection, methods that often incur significant computational overhead. This paper challenges the assumption that such complex search mechanisms are universally necessary. We first identify and validate a query typology distinguishing between global query and localized query. We demonstrate that while uniform sampling is both effective and efficient for global queries, localized queries indeed necessitate query-aware selection for optimal performance. Building on this insight, we propose DIG, a training-free frame selection framework that adapts its strategy based on the query type. Specifically,DIG employs efficient uniform sampling for global queries while activating a specialized pipeline to extract query-relevant frames for localized queries. Experiments on three long-form video understanding benchmarks demonstrate that DIG consistently outperforms existing baselines and robustly improves LMM performance, even when scaling the input frame count to 256.

This paper focuses on tackling the problem of temporal language localization in videos, which aims to identify the start and end points of a moment described by a natural language sentence in an untrimmed video. However, it is non-trivial since it requires not only the comprehensive understanding of the video and sentence query, but also the accurate semantic correspondence capture between them. Existing efforts are mainly centered on exploring the sequential relation among video clips and query words to reason the video and sentence query, neglecting the other intra-modal relations (e.g., semantic similarity among video clips and syntactic dependency among the query words). Towards this end, in this work, we propose a Multi-modal Interaction Graph Convolutional Network (MIGCN), which jointly explores the complex intra-modal relations and inter-modal interactions residing in the video and sentence query to facilitate the understanding and semantic correspondence capture of the video and sentence query. In addition, we devise an adaptive context-aware localization method, where the context information is taken into the candidate moments and the multi-scale fully connected layers are designed to rank and adjust the boundary of the generated coarse candidate moments with different lengths. Extensive experiments on Charades-STA and ActivityNet datasets demonstrate the promising performance and superior efficiency of our model.

Contextual information is vital in visual understanding problems, such as semantic segmentation and object detection. We propose a Criss-Cross Network (CCNet) for obtaining full-image contextual information in a very effective and efficient way. Concretely, for each pixel, a novel criss-cross attention module harvests the contextual information of all the pixels on its criss-cross path. By taking a further recurrent operation, each pixel can finally capture the full-image dependencies. Besides, a category consistent loss is proposed to enforce the criss-cross attention module to produce more discriminative features. Overall, CCNet is with the following merits: 1) GPU memory friendly. Compared with the non-local block, the proposed recurrent criss-cross attention module requires 11x less GPU memory usage. 2) High computational efficiency. The recurrent criss-cross attention significantly reduces FLOPs by about 85% of the non-local block. 3) The state-of-the-art performance. We conduct extensive experiments on semantic segmentation benchmarks including Cityscapes, ADE20K, human parsing benchmark LIP, instance segmentation benchmark COCO, video segmentation benchmark CamVid. In particular, our CCNet achieves the mIoU scores of 81.9%, 45.76% and 55.47% on the Cityscapes test set, the ADE20K validation set and the LIP validation set respectively, which are the new state-of-the-art results. The source codes are available at https://github.com/speedinghzl/CCNet.

Video Large Language Models (VLMs) have achieved remarkable results on a variety of vision language tasks, yet their practical use is limited by the "needle in a haystack" problem: the massive number of visual tokens produced from raw video frames exhausts the model's context window. Existing solutions alleviate this issue by selecting a sparse set of frames, thereby reducing token count, but such frame-wise selection discards essential temporal dynamics, leading to suboptimal reasoning about motion and event continuity. In this work we systematically explore the impact of temporal information and demonstrate that extending selection from isolated key frames to key clips, which are short, temporally coherent segments, improves video understanding. To maintain a fixed computational budget while accommodating the larger token footprint of clips, we propose an adaptive resolution strategy that dynamically balances spatial resolution and clip length, ensuring a constant token count per video. Experiments on three long-form video benchmarks demonstrate that our training-free approach, F2C, outperforms uniform sampling up to 8.1%, 5.6%, and 10.3% on Video-MME, LongVideoBench and MLVU benchmarks, respectively. These results highlight the importance of preserving temporal coherence in frame selection and provide a practical pathway for scaling Video LLMs to real world video understanding applications. Project webpage is available at https://guangyusun.com/f2c .

Recent advances in interactive video generation have shown promising results, yet existing approaches struggle with scene-consistent memory capabilities in long video generation due to limited use of historical context. In this work, we propose Context-as-Memory, which utilizes historical context as memory for video generation. It includes two simple yet effective designs: (1) storing context in frame format without additional post-processing; (2) conditioning by concatenating context and frames to be predicted along the frame dimension at the input, requiring no external control modules. Furthermore, considering the enormous computational overhead of incorporating all historical context, we propose the Memory Retrieval module to select truly relevant context frames by determining FOV (Field of View) overlap between camera poses, which significantly reduces the number of candidate frames without substantial information loss. Experiments demonstrate that Context-as-Memory achieves superior memory capabilities in interactive long video generation compared to SOTAs, even generalizing effectively to open-domain scenarios not seen during training. The link of our project page is https://context-as-memory.github.io/.

We present Omni, a unified multimodal model natively trained on diverse modalities, including text, images, videos, 3D geometry, and hidden representations. We find that such training enables Context Unrolling, where the model explicitly reasons across multiple modal representations before producing predictions. This process enables the model to aggregate complementary information across heterogeneous modalities, facilitating a more faithful approximation of the shared multimodal knowledge manifold and improving downstream reasoning fidelity. As a result, Omni achieves strong performance on both multimodal generation and understanding benchmarks, while demonstrating advanced multimodal reasoning capabilities, including in-context generation of text, image, video, and 3D geometry.

Referring video object segmentation aims to segment a referent throughout a video sequence according to a natural language expression. It requires aligning the natural language expression with the objects' motions and their dynamic associations at the global video level but segmenting objects at the frame level. To achieve this goal, we propose to simultaneously maintain a global referent token and a sequence of object queries, where the former is responsible for capturing video-level referent according to the language expression, while the latter serves to better locate and segment objects with each frame. Furthermore, to explicitly capture object motions and spatial-temporal cross-modal reasoning over objects, we propose a novel temporal collection-distribution mechanism for interacting between the global referent token and object queries. Specifically, the temporal collection mechanism collects global information for the referent token from object queries to the temporal motions to the language expression. In turn, the temporal distribution first distributes the referent token to the referent sequence across all frames and then performs efficient cross-frame reasoning between the referent sequence and object queries in every frame. Experimental results show that our method outperforms state-of-the-art methods on all benchmarks consistently and significantly.

Contrastive language-image pretraining has shown great success in learning visual-textual joint representation from web-scale data, demonstrating remarkable "zero-shot" generalization ability for various image tasks. However, how to effectively expand such new language-image pretraining methods to video domains is still an open problem. In this work, we present a simple yet effective approach that adapts the pretrained language-image models to video recognition directly, instead of pretraining a new model from scratch. More concretely, to capture the long-range dependencies of frames along the temporal dimension, we propose a cross-frame attention mechanism that explicitly exchanges information across frames. Such module is lightweight and can be plugged into pretrained language-image models seamlessly. Moreover, we propose a video-specific prompting scheme, which leverages video content information for generating discriminative textual prompts. Extensive experiments demonstrate that our approach is effective and can be generalized to different video recognition scenarios. In particular, under fully-supervised settings, our approach achieves a top-1 accuracy of 87.1% on Kinectics-400, while using 12 times fewer FLOPs compared with Swin-L and ViViT-H. In zero-shot experiments, our approach surpasses the current state-of-the-art methods by +7.6% and +14.9% in terms of top-1 accuracy under two popular protocols. In few-shot scenarios, our approach outperforms previous best methods by +32.1% and +23.1% when the labeled data is extremely limited. Code and models are available at https://aka.ms/X-CLIP

Recent advances in Video Large Language Models (Video-LLMs) have demonstrated their great potential in general-purpose video understanding. To verify the significance of these models, a number of benchmarks have been proposed to diagnose their capabilities in different scenarios. However, existing benchmarks merely evaluate models through video-level question-answering, lacking fine-grained event-level assessment and task diversity. To fill this gap, we introduce E.T. Bench (Event-Level & Time-Sensitive Video Understanding Benchmark), a large-scale and high-quality benchmark for open-ended event-level video understanding. Categorized within a 3-level task taxonomy, E.T. Bench encompasses 7.3K samples under 12 tasks with 7K videos (251.4h total length) under 8 domains, providing comprehensive evaluations. We extensively evaluated 8 Image-LLMs and 12 Video-LLMs on our benchmark, and the results reveal that state-of-the-art models for coarse-level (video-level) understanding struggle to solve our fine-grained tasks, e.g., grounding event-of-interests within videos, largely due to the short video context length, improper time representations, and lack of multi-event training data. Focusing on these issues, we further propose a strong baseline model, E.T. Chat, together with an instruction-tuning dataset E.T. Instruct 164K tailored for fine-grained event-level understanding. Our simple but effective solution demonstrates superior performance in multiple scenarios.

Long-context video understanding in multimodal large language models (MLLMs) faces a critical challenge: balancing computational efficiency with the retention of fine-grained spatio-temporal patterns. Existing approaches (e.g., sparse sampling, dense sampling with low resolution, and token compression) suffer from significant information loss in temporal dynamics, spatial details, or subtle interactions, particularly in videos with complex motion or varying resolutions. To address this, we propose Mavors, a novel framework that introduces Multi-granularity video representation for holistic long-video modeling. Specifically, Mavors directly encodes raw video content into latent representations through two core components: 1) an Intra-chunk Vision Encoder (IVE) that preserves high-resolution spatial features via 3D convolutions and Vision Transformers, and 2) an Inter-chunk Feature Aggregator (IFA) that establishes temporal coherence across chunks using transformer-based dependency modeling with chunk-level rotary position encodings. Moreover, the framework unifies image and video understanding by treating images as single-frame videos via sub-image decomposition. Experiments across diverse benchmarks demonstrate Mavors' superiority in maintaining both spatial fidelity and temporal continuity, significantly outperforming existing methods in tasks requiring fine-grained spatio-temporal reasoning.

In static monitoring cameras, useful contextual information can stretch far beyond the few seconds typical video understanding models might see: subjects may exhibit similar behavior over multiple days, and background objects remain static. Due to power and storage constraints, sampling frequencies are low, often no faster than one frame per second, and sometimes are irregular due to the use of a motion trigger. In order to perform well in this setting, models must be robust to irregular sampling rates. In this paper we propose a method that leverages temporal context from the unlabeled frames of a novel camera to improve performance at that camera. Specifically, we propose an attention-based approach that allows our model, Context R-CNN, to index into a long term memory bank constructed on a per-camera basis and aggregate contextual features from other frames to boost object detection performance on the current frame. We apply Context R-CNN to two settings: (1) species detection using camera traps, and (2) vehicle detection in traffic cameras, showing in both settings that Context R-CNN leads to performance gains over strong baselines. Moreover, we show that increasing the contextual time horizon leads to improved results. When applied to camera trap data from the Snapshot Serengeti dataset, Context R-CNN with context from up to a month of images outperforms a single-frame baseline by 17.9% mAP, and outperforms S3D (a 3d convolution based baseline) by 11.2% mAP.

Grounding language queries in videos aims at identifying the time interval (or moment) semantically relevant to a language query. The solution to this challenging task demands understanding videos' and queries' semantic content and the fine-grained reasoning about their multi-modal interactions. Our key idea is to recast this challenge into an algorithmic graph matching problem. Fueled by recent advances in Graph Neural Networks, we propose to leverage Graph Convolutional Networks to model video and textual information as well as their semantic alignment. To enable the mutual exchange of information across the modalities, we design a novel Video-Language Graph Matching Network (VLG-Net) to match video and query graphs. Core ingredients include representation graphs built atop video snippets and query tokens separately and used to model intra-modality relationships. A Graph Matching layer is adopted for cross-modal context modeling and multi-modal fusion. Finally, moment candidates are created using masked moment attention pooling by fusing the moment's enriched snippet features. We demonstrate superior performance over state-of-the-art grounding methods on three widely used datasets for temporal localization of moments in videos with language queries: ActivityNet-Captions, TACoS, and DiDeMo.

Video Language Models (VideoLMs) empower AI systems to understand temporal dynamics in videos. To fit to the maximum context window constraint, current methods use keyframe sampling which can miss both macro-level events and micro-level details due to the sparse temporal coverage. Furthermore, processing full images and their tokens for each frame incurs substantial computational overhead. To address these limitations, we propose to leverage video codec primitives (specifically motion vectors and residuals) which natively encode video redundancy and sparsity without requiring expensive full-image encoding for most frames. To this end, we introduce lightweight transformer-based encoders that aggregate codec primitives and align their representations with image encoder embeddings through a pre-training strategy that accelerates convergence during end-to-end fine-tuning. Our approach reduces the time-to-first-token by up to 86% and token usage by up to 93% compared to standard VideoLMs. Moreover, by varying the keyframe and codec primitive densities we are able to maintain or exceed performance on 14 diverse video understanding benchmarks spanning general question answering, temporal reasoning, long-form understanding, and spatial scene understanding.

We focus on the task of Automatic Live Video Commenting (ALVC), which aims to generate real-time video comments with both video frames and other viewers' comments as inputs. A major challenge in this task is how to properly leverage the rich and diverse information carried by video and text. In this paper, we aim to collect diversified information from video and text for informative comment generation. To achieve this, we propose a Diversified Co-Attention (DCA) model for this task. Our model builds bidirectional interactions between video frames and surrounding comments from multiple perspectives via metric learning, to collect a diversified and informative context for comment generation. We also propose an effective parameter orthogonalization technique to avoid excessive overlap of information learned from different perspectives. Results show that our approach outperforms existing methods in the ALVC task, achieving new state-of-the-art results.

In this paper, we introduce the task of automatically generating text to describe the differences between two similar images. We collect a new dataset by crowd-sourcing difference descriptions for pairs of image frames extracted from video-surveillance footage. Annotators were asked to succinctly describe all the differences in a short paragraph. As a result, our novel dataset provides an opportunity to explore models that align language and vision, and capture visual salience. The dataset may also be a useful benchmark for coherent multi-sentence generation. We perform a firstpass visual analysis that exposes clusters of differing pixels as a proxy for object-level differences. We propose a model that captures visual salience by using a latent variable to align clusters of differing pixels with output sentences. We find that, for both single-sentence generation and as well as multi-sentence generation, the proposed model outperforms the models that use attention alone.

The dual-stream transformer architecture-based joint audio-video generation method has become the dominant paradigm in current research. By incorporating pre-trained video diffusion models and audio diffusion models, along with a cross-modal interaction attention module, high-quality, temporally synchronized audio-video content can be generated with minimal training data. In this paper, we first revisit the dual-stream transformer paradigm and further analyze its limitations, including model manifold variations caused by the gating mechanism controlling cross-modal interactions, biases in multi-modal background regions introduced by cross-modal attention, and the inconsistencies in multi-modal classifier-free guidance (CFG) during training and inference, as well as conflicts between multiple conditions. To alleviate these issues, we propose Cross-Modal Context Learning (CCL), equipped with several carefully designed modules. Temporally Aligned RoPE and Partitioning (TARP) effectively enhances the temporal alignment between audio latent and video latent representations. The Learnable Context Tokens (LCT) and Dynamic Context Routing (DCR) in the Cross-Modal Context Attention (CCA) module provide stable unconditional anchors for cross-modal information, while dynamically routing based on different training tasks, further enhancing the model's convergence speed and generation quality. During inference, Unconditional Context Guidance (UCG) leverages the unconditional support provided by LCT to facilitate different forms of CFG, improving train-inference consistency and further alleviating conflicts. Through comprehensive evaluations, CCL achieves state-of-the-art performance compared with recent academic methods while requiring substantially fewer resources.

We propose a novel framework for video understanding, called Temporally Contextualized CLIP (TC-CLIP), which leverages essential temporal information through global interactions in a spatio-temporal domain within a video. To be specific, we introduce Temporal Contextualization (TC), a layer-wise temporal information infusion mechanism for videos, which 1) extracts core information from each frame, 2) connects relevant information across frames for the summarization into context tokens, and 3) leverages the context tokens for feature encoding. Furthermore, the Video-conditional Prompting (VP) module processes context tokens to generate informative prompts in the text modality. Extensive experiments in zero-shot, few-shot, base-to-novel, and fully-supervised action recognition validate the effectiveness of our model. Ablation studies for TC and VP support our design choices. Our project page with the source code is available at https://github.com/naver-ai/tc-clip

Long-form video generation presents a dual challenge: models must capture long-range dependencies while preventing the error accumulation inherent in autoregressive decoding. To address these challenges, we make two contributions. First, for dynamic context modeling, we propose MemoryPack, a learnable context-retrieval mechanism that leverages both textual and image information as global guidance to jointly model short- and long-term dependencies, achieving minute-level temporal consistency. This design scales gracefully with video length, preserves computational efficiency, and maintains linear complexity. Second, to mitigate error accumulation, we introduce Direct Forcing, an efficient single-step approximating strategy that improves training-inference alignment and thereby curtails error propagation during inference. Together, MemoryPack and Direct Forcing substantially enhance the context consistency and reliability of long-form video generation, advancing the practical usability of autoregressive video models.

Video topic segmentation unveils the coarse-grained semantic structure underlying videos and is essential for other video understanding tasks. Given the recent surge in multi-modal, relying solely on a single modality is arguably insufficient. On the other hand, prior solutions for similar tasks like video scene/shot segmentation cater to short videos with clear visual shifts but falter for long videos with subtle changes, such as livestreams. In this paper, we introduce a multi-modal video topic segmenter that utilizes both video transcripts and frames, bolstered by a cross-modal attention mechanism. Furthermore, we propose a dual-contrastive learning framework adhering to the unsupervised domain adaptation paradigm, enhancing our model's adaptability to longer, more semantically complex videos. Experiments on short and long video corpora demonstrate that our proposed solution, significantly surpasses baseline methods in terms of both accuracy and transferability, in both intra- and cross-domain settings.

The paper-to-video task converts a research paper into a structured video abstract, distilling key concepts, methods, and conclusions into an accessible, well-organized format. While state-of-the-art video generation models demonstrate potential, they are constrained by limited context windows, rigid video duration constraints, limited stylistic diversity, and an inability to represent domain-specific knowledge. To address these limitations, we introduce Preacher, the first paper-to-video agentic system. Preacher employs a topdown approach to decompose, summarize, and reformulate the paper, followed by bottom-up video generation, synthesizing diverse video segments into a coherent abstract. To align cross-modal representations, we define key scenes and introduce a Progressive Chain of Thought (P-CoT) for granular, iterative planning. Preacher successfully generates high-quality video abstracts across five research fields, demonstrating expertise beyond current video generation models. Code will be released at: https://github.com/GenVerse/Paper2Video

Handling fast, complex, and highly non-linear motion patterns has long posed challenges for video frame interpolation. Although recent diffusion-based approaches improve upon traditional optical-flow-based methods, they still struggle to cover diverse application scenarios and often fail to produce sharp, temporally consistent frames in fine-grained motion tasks such as audio-visual synchronized interpolation. To address these limitations, we introduce BBF (Beyond Boundary Frames), a context-aware video frame interpolation framework, which could be guided by audio/visual semantics. First, we enhance the input design of the interpolation model so that it can flexibly handle multiple conditional modalities, including text, audio, images, and video. Second, we propose a decoupled multimodal fusion mechanism that sequentially injects different conditional signals into a DiT backbone. Finally, to maintain the generation abilities of the foundation model, we adopt a progressive multi-stage training paradigm, where the start-end frame difference embedding is used to dynamically adjust both the data sampling and the loss weighting. Extensive experimental results demonstrate that BBF outperforms specialized state-of-the-art methods on both generic interpolation and audio-visual synchronized interpolation tasks, establishing a unified framework for video frame interpolation under coordinated multi-channel conditioning.

Recent advances in Large Language Models (LLMs) have led to significant breakthroughs in video understanding. However, existing models still struggle with long video processing due to the context length constraint of LLMs and the vast amount of information within the video. Although some recent methods are designed for long video understanding, they often lose crucial information during token compression and struggle with additional modality like audio. In this work, we propose a dynamic long video encoding method utilizing the temporal relationship between frames, named Temporal Dynamic Context (TDC). Firstly, we segment the video into semantically consistent scenes based on inter-frame similarities, then encode each frame into tokens using visual-audio encoders. Secondly, we propose a novel temporal context compressor to reduce the number of tokens within each segment. Specifically, we employ a query-based Transformer to aggregate video, audio, and instruction text tokens into a limited set of temporal context tokens. Finally, we feed the static frame tokens and the temporal context tokens into the LLM for video understanding. Furthermore, to handle extremely long videos, we propose a training-free chain-of-thought strategy that progressively extracts answers from multiple video segments. These intermediate answers serve as part of the reasoning process and contribute to the final answer. We conduct extensive experiments on general video understanding and audio-video understanding benchmarks, where our method demonstrates strong performance. The code and models are available at https://github.com/Hoar012/TDC-Video.

Recent vision-language models have achieved tremendous advances. However, their computational costs are also escalating dramatically, making model acceleration exceedingly critical. To pursue more efficient vision-language Transformers, this paper introduces Cross-Guided Ensemble of Tokens (CrossGET), a general acceleration framework for vision-language Transformers. This framework adaptively combines tokens in real-time during inference, significantly reducing computational costs while maintaining high performance. CrossGET features two primary innovations: 1) Cross-Guided Matching and Ensemble. CrossGET leverages cross-modal guided token matching and ensemble to effectively utilize cross-modal information, achieving wider applicability across both modality-independent models, e.g., CLIP, and modality-dependent ones, e.g., BLIP2. 2) Complete-Graph Soft Matching. CrossGET introduces an algorithm for the token-matching mechanism, ensuring reliable matching results while facilitating parallelizability and high efficiency. Extensive experiments have been conducted on various vision-language tasks, such as image-text retrieval, visual reasoning, image captioning, and visual question answering. The performance on both classic multimodal architectures and emerging multimodal LLMs demonstrates the framework's effectiveness and versatility. The code is available at https://github.com/sdc17/CrossGET.

Autoregressive video diffusion models have demonstrated remarkable progress, yet they remain bottlenecked by intractable linear KV-cache growth, temporal repetition, and compounding errors during long-video generation. To address these challenges, we present PackForcing, a unified framework that efficiently manages the generation history through a novel three-partition KV-cache strategy. Specifically, we categorize the historical context into three distinct types: (1) Sink tokens, which preserve early anchor frames at full resolution to maintain global semantics; (2) Mid tokens, which achieve a massive spatiotemporal compression (32x token reduction) via a dual-branch network fusing progressive 3D convolutions with low-resolution VAE re-encoding; and (3) Recent tokens, kept at full resolution to ensure local temporal coherence. To strictly bound the memory footprint without sacrificing quality, we introduce a dynamic top-k context selection mechanism for the mid tokens, coupled with a continuous Temporal RoPE Adjustment that seamlessly re-aligns position gaps caused by dropped tokens with negligible overhead. Empowered by this principled hierarchical context compression, PackForcing can generate coherent 2-minute, 832x480 videos at 16 FPS on a single H200 GPU. It achieves a bounded KV cache of just 4 GB and enables a remarkable 24x temporal extrapolation (5s to 120s), operating effectively either zero-shot or trained on merely 5-second clips. Extensive results on VBench demonstrate state-of-the-art temporal consistency (26.07) and dynamic degree (56.25), proving that short-video supervision is sufficient for high-quality, long-video synthesis. https://github.com/ShandaAI/PackForcing

Despite advancements in Video Large Language Models (Vid-LLMs) improving multimodal understanding, challenges persist in streaming video reasoning due to its reliance on contextual information. Existing paradigms feed all available historical contextual information into Vid-LLMs, resulting in a significant computational burden for visual data processing. Furthermore, the inclusion of irrelevant context distracts models from key details. This paper introduces a challenging task called Context-guided Streaming Video Reasoning (CogStream), which simulates real-world streaming video scenarios, requiring models to identify the most relevant historical contextual information to deduce answers for questions about the current stream. To support CogStream, we present a densely annotated dataset featuring extensive and hierarchical question-answer pairs, generated by a semi-automatic pipeline. Additionally, we present CogReasoner as a baseline model. It effectively tackles this task by leveraging visual stream compression and historical dialogue retrieval. Extensive experiments prove the effectiveness of this method.

Contrastive learning-based vision-language pre-training approaches, such as CLIP, have demonstrated great success in many vision-language tasks. These methods achieve cross-modal alignment by encoding a matched image-text pair with similar feature embeddings, which are generated by aggregating information from visual patches and language tokens. However, direct aligning cross-modal information using such representations is challenging, as visual patches and text tokens differ in semantic levels and granularities. To alleviate this issue, we propose a Finite Discrete Tokens (FDT) based multimodal representation. FDT is a set of learnable tokens representing certain visual-semantic concepts. Both images and texts are embedded using shared FDT by first grounding multimodal inputs to FDT space and then aggregating the activated FDT representations. The matched visual and semantic concepts are enforced to be represented by the same set of discrete tokens by a sparse activation constraint. As a result, the granularity gap between the two modalities is reduced. Through both quantitative and qualitative analyses, we demonstrate that using FDT representations in CLIP-style models improves cross-modal alignment and performance in visual recognition and vision-language downstream tasks. Furthermore, we show that our method can learn more comprehensive representations, and the learned FDT capture meaningful cross-modal correspondence, ranging from objects to actions and attributes.

Temporal modeling is crucial for various video learning tasks. Most recent approaches employ either factorized (2D+1D) or joint (3D) spatial-temporal operations to extract temporal contexts from the input frames. While the former is more efficient in computation, the latter often obtains better performance. In this paper, we attribute this to a dilemma between the sufficiency and the efficiency of interactions among various positions in different frames. These interactions affect the extraction of task-relevant information shared among frames. To resolve this issue, we prove that frame-by-frame alignments have the potential to increase the mutual information between frame representations, thereby including more task-relevant information to boost effectiveness. Then we propose Alignment-guided Temporal Attention (ATA) to extend 1-dimensional temporal attention with parameter-free patch-level alignments between neighboring frames. It can act as a general plug-in for image backbones to conduct the action recognition task without any model-specific design. Extensive experiments on multiple benchmarks demonstrate the superiority and generality of our module.

Video multimodal large language models (Video-MLLMs) have achieved remarkable progress in video understanding. However, they remain vulnerable to hallucination-producing content inconsistent with or unrelated to video inputs. Previous video hallucination benchmarks primarily focus on short-videos. They attribute hallucinations to factors such as strong language priors, missing frames, or vision-language biases introduced by the visual encoder. While these causes indeed account for most hallucinations in short videos, they still oversimplify the cause of hallucinations. Sometimes, models generate incorrect outputs but with correct frame-level semantics. We refer to this type of hallucination as Semantic Aggregation Hallucination (SAH), which arises during the process of aggregating frame-level semantics into event-level semantic groups. Given that SAH becomes particularly critical in long videos due to increased semantic complexity across multiple events, it is essential to separate and thoroughly investigate the causes of this type of hallucination. To address the above issues, we introduce ELV-Halluc, the first benchmark dedicated to long-video hallucination, enabling a systematic investigation of SAH. Our experiments confirm the existence of SAH and show that it increases with semantic complexity. Additionally, we find that models are more prone to SAH on rapidly changing semantics. Moreover, we discuss potential approaches to mitigate SAH. We demonstrate that positional encoding strategy contributes to alleviating SAH, and further adopt DPO strategy to enhance the model's ability to distinguish semantics within and across events. To support this, we curate a dataset of 8K adversarial data pairs and achieve improvements on both ELV-Halluc and Video-MME, including a substantial 27.7% reduction in SAH ratio.

This paper introduces a Transformer-based integrative feature and cost aggregation network designed for dense matching tasks. In the context of dense matching, many works benefit from one of two forms of aggregation: feature aggregation, which pertains to the alignment of similar features, or cost aggregation, a procedure aimed at instilling coherence in the flow estimates across neighboring pixels. In this work, we first show that feature aggregation and cost aggregation exhibit distinct characteristics and reveal the potential for substantial benefits stemming from the judicious use of both aggregation processes. We then introduce a simple yet effective architecture that harnesses self- and cross-attention mechanisms to show that our approach unifies feature aggregation and cost aggregation and effectively harnesses the strengths of both techniques. Within the proposed attention layers, the features and cost volume both complement each other, and the attention layers are interleaved through a coarse-to-fine design to further promote accurate correspondence estimation. Finally at inference, our network produces multi-scale predictions, computes their confidence scores, and selects the most confident flow for final prediction. Our framework is evaluated on standard benchmarks for semantic matching, and also applied to geometric matching, where we show that our approach achieves significant improvements compared to existing methods.

Seeing clearly with high resolution is a foundation of Large Multimodal Models (LMMs), which has been proven to be vital for visual perception and reasoning. Existing works usually employ a straightforward resolution upscaling method, where the image consists of global and local branches, with the latter being the sliced image patches but resized to the same resolution as the former. This means that higher resolution requires more local patches, resulting in exorbitant computational expenses, and meanwhile, the dominance of local image tokens may diminish the global context. In this paper, we dive into the problems and propose a new framework as well as an elaborate optimization strategy. Specifically, we extract contextual information from the global view using a mixture of adapters, based on the observation that different adapters excel at different tasks. With regard to local patches, learnable query embeddings are introduced to reduce image tokens, the most important tokens accounting for the user question will be further selected by a similarity-based selector. Our empirical results demonstrate a `less is more' pattern, where utilizing fewer but more informative local image tokens leads to improved performance. Besides, a significant challenge lies in the training strategy, as simultaneous end-to-end training of the global mining block and local compression block does not yield optimal results. We thus advocate for an alternating training way, ensuring balanced learning between global and local aspects. Finally, we also introduce a challenging dataset with high requirements for image detail, enhancing the training of the local compression layer. The proposed method, termed LMM with Sophisticated Tasks, Local image compression, and Mixture of global Experts (SliME), achieves leading performance across various benchmarks with only 2 million training data.

Recent advancements in AI have led to the development of large multimodal models (LMMs) capable of processing complex tasks involving joint reasoning over text and visual content in the image (e.g., navigating maps in public places). This paper introduces ConTextual, a novel benchmark comprising instructions designed explicitly to evaluate LMMs' ability to perform context-sensitive text-rich visual reasoning. ConTextual emphasizes diverse real-world scenarios (e.g., time-reading, navigation, shopping and more) demanding a deeper understanding of the interactions between textual and visual elements. Our findings reveal a significant performance gap of 30.8% between the best-performing LMM, GPT-4V(ision), and human capabilities using human evaluation indicating substantial room for improvement in context-sensitive text-rich visual reasoning. Notably, while GPT-4V excelled in abstract categories like meme and quote interpretation, its overall performance still lagged behind humans. In addition to human evaluations, we also employed automatic evaluation metrics using GPT-4, uncovering similar trends in performance disparities. We also perform a fine-grained evaluation across diverse visual contexts and provide qualitative analysis which provides a robust framework for future advancements in the LMM design. https://con-textual.github.io/

Modern computer vision pipelines handle large images in one of two sub-optimal ways: down-sampling or cropping. These two methods incur significant losses in the amount of information and context present in an image. There are many downstream applications in which global context matters as much as high frequency details, such as in real-world satellite imagery; in such cases researchers have to make the uncomfortable choice of which information to discard. We introduce xT, a simple framework for vision transformers which effectively aggregates global context with local details and can model large images end-to-end on contemporary GPUs. We select a set of benchmark datasets across classic vision tasks which accurately reflect a vision model's ability to understand truly large images and incorporate fine details over large scales and assess our method's improvement on them. By introducing a nested tokenization scheme for large images in conjunction with long-sequence length models normally used for natural language processing, we are able to increase accuracy by up to 8.6% on challenging classification tasks and F_1 score by 11.6 on context-dependent segmentation in large images.

While recent progress in video-text retrieval has been advanced by the exploration of better representation learning, in this paper, we present a novel multi-grained sparse learning framework, S3MA, to learn an aligned sparse space shared between the video and the text for video-text retrieval. The shared sparse space is initialized with a finite number of sparse concepts, each of which refers to a number of words. With the text data at hand, we learn and update the shared sparse space in a supervised manner using the proposed similarity and alignment losses. Moreover, to enable multi-grained alignment, we incorporate frame representations for better modeling the video modality and calculating fine-grained and coarse-grained similarities. Benefiting from the learned shared sparse space and multi-grained similarities, extensive experiments on several video-text retrieval benchmarks demonstrate the superiority of S3MA over existing methods. Our code is available at https://github.com/yimuwangcs/Better_Cross_Modal_Retrieval.

Recent Video-Language Models (VLMs) achieve promising results on long-video understanding, but their performance still lags behind that achieved on tasks involving images or short videos. This has led to great interest in improving the long context modeling of VLMs by introducing novel modules and additional complexity. % additional training time. In this paper, we take a different approach: rather than fine-tuning VLMs with the limited data available, we attempt to maximize the performance of existing models. To this end, we propose a novel visual prompting strategy specifically designed for long-video understanding. By combining multiple frames as panels into one image, we effectively trade off spatial details for temporal resolution. Our approach is training-free, parameter-free, and model-agnostic, and can be seamlessly integrated into existing VLMs. Extensive experiments on five established benchmarks across a wide range of model architectures, sizes, and context windows confirm the consistency of our approach. For the TimeScope (Long) dataset, which has the longest videos, the accuracy for video question answering is improved by up to 19.4\%. Overall, our method raises the bar for long video understanding models. We will make our code available upon acceptance.

Understanding 3D scenes is pivotal for autonomous driving, robotics, and augmented reality. Recent semantic Gaussian Splatting approaches leverage large-scale 2D vision models to project 2D semantic features onto 3D scenes. However, they suffer from two major limitations: (1) insufficient contextual cues for individual masks during preprocessing and (2) inconsistencies and missing details when fusing multi-view features from these 2D models. In this paper, we introduce OpenInsGaussian, an Open-vocabulary Instance Gaussian segmentation framework with Context-aware Cross-view Fusion. Our method consists of two modules: Context-Aware Feature Extraction, which augments each mask with rich semantic context, and Attention-Driven Feature Aggregation, which selectively fuses multi-view features to mitigate alignment errors and incompleteness. Through extensive experiments on benchmark datasets, OpenInsGaussian achieves state-of-the-art results in open-vocabulary 3D Gaussian segmentation, outperforming existing baselines by a large margin. These findings underscore the robustness and generality of our proposed approach, marking a significant step forward in 3D scene understanding and its practical deployment across diverse real-world scenarios.

Image-text retrieval, as a fundamental and important branch of information retrieval, has attracted extensive research attentions. The main challenge of this task is cross-modal semantic understanding and matching. Some recent works focus more on fine-grained cross-modal semantic matching. With the prevalence of large scale multimodal pretraining models, several state-of-the-art models (e.g. X-VLM) have achieved near-perfect performance on widely-used image-text retrieval benchmarks, i.e. MSCOCO-Test-5K and Flickr30K-Test-1K. In this paper, we review the two common benchmarks and observe that they are insufficient to assess the true capability of models on fine-grained cross-modal semantic matching. The reason is that a large amount of images and texts in the benchmarks are coarse-grained. Based on the observation, we renovate the coarse-grained images and texts in the old benchmarks and establish the improved benchmarks called MSCOCO-FG and Flickr30K-FG. Specifically, on the image side, we enlarge the original image pool by adopting more similar images. On the text side, we propose a novel semi-automatic renovation approach to refine coarse-grained sentences into finer-grained ones with little human effort. Furthermore, we evaluate representative image-text retrieval models on our new benchmarks to demonstrate the effectiveness of our method. We also analyze the capability of models on fine-grained semantic comprehension through extensive experiments. The results show that even the state-of-the-art models have much room for improvement in fine-grained semantic understanding, especially in distinguishing attributes of close objects in images. Our code and improved benchmark datasets are publicly available at: https://github.com/cwj1412/MSCOCO-Flikcr30K_FG, which we hope will inspire further in-depth research on cross-modal retrieval.

Ad-hoc Video Search (AVS) enables users to search for unlabeled video content using on-the-fly textual queries. Current deep learning-based models for AVS are trained to optimize holistic similarity between short videos and their associated descriptions. However, due to the diversity of ad-hoc queries, even for a short video, its truly relevant part w.r.t. a given query can be of shorter duration. In such a scenario, the holistic similarity becomes suboptimal. To remedy the issue, we propose in this paper CLIPRerank, a fine-grained re-scoring method. We compute cross-modal similarities between query and video frames using a pre-trained CLIP model, with multi-frame scores aggregated by max pooling. The fine-grained score is weightedly added to the initial score for search result reranking. As such, CLIPRerank is agnostic to the underlying video retrieval models and extremely simple, making it a handy plug-in for boosting AVS. Experiments on the challenging TRECVID AVS benchmarks (from 2016 to 2021) justify the effectiveness of the proposed strategy. CLIPRerank consistently improves the TRECVID top performers and multiple existing models including SEA, W2VV++, Dual Encoding, Dual Task, LAFF, CLIP2Video, TS2-Net and X-CLIP. Our method also works when substituting BLIP-2 for CLIP.

In this work, we present a novel method to tackle the token generation challenge in Vision Language Models (VLMs) for video and image understanding, called LLaMA-VID. Current VLMs, while proficient in tasks like image captioning and visual question answering, face computational burdens when processing long videos due to the excessive visual tokens. LLaMA-VID addresses this issue by representing each frame with two distinct tokens, namely context token and content token. The context token encodes the overall image context based on user input, whereas the content token encapsulates visual cues in each frame. This dual-token strategy significantly reduces the overload of long videos while preserving critical information. Generally, LLaMA-VID empowers existing frameworks to support hour-long videos and pushes their upper limit with an extra context token. It is proved to surpass previous methods on most of video- or image-based benchmarks. Code is available https://github.com/dvlab-research/LLaMA-VID}{https://github.com/dvlab-research/LLaMA-VID

Existing evaluation frameworks for Multimodal Large Language Models (MLLMs) primarily focus on image reasoning or general video understanding tasks, largely overlooking the significant role of image context in video comprehension. To bridge this gap, we propose IV-Bench, the first comprehensive benchmark for evaluating Image-Grounded Video Perception and Reasoning. IV-Bench consists of 967 videos paired with 2,585 meticulously annotated image-text queries across 13 tasks (7 perception and 6 reasoning tasks) and 5 representative categories. Extensive evaluations of state-of-the-art open-source (e.g., InternVL2.5, Qwen2.5-VL) and closed-source (e.g., GPT-4o, Gemini2-Flash and Gemini2-Pro) MLLMs demonstrate that current models substantially underperform in image-grounded video Perception and Reasoning, merely achieving at most 28.9% accuracy. Further analysis reveals key factors influencing model performance on IV-Bench, including inference pattern, frame number, and resolution. Additionally, through a simple data synthesis approach, we demonstratethe challenges of IV- Bench extend beyond merely aligning the data format in the training proecss. These findings collectively provide valuable insights for future research. Our codes and data are released in https://github.com/multimodal-art-projection/IV-Bench.

The exponential growth of video content necessitates effective video summarization to efficiently extract key information from long videos. However, current approaches struggle to fully comprehend complex videos, primarily because they employ static or modality-agnostic fusion strategies. These methods fail to account for the dynamic, frame-dependent variations in modality saliency inherent in video data. To overcome these limitations, we propose TripleSumm, a novel architecture that adaptively weights and fuses the contributions of visual, text, and audio modalities at the frame level. Furthermore, a significant bottleneck for research into multimodal video summarization has been the lack of comprehensive benchmarks. Addressing this bottleneck, we introduce MoSu (Most Replayed Multimodal Video Summarization), the first large-scale benchmark that provides all three modalities. Extensive experiments demonstrate that TripleSumm achieves state-of-the-art performance, outperforming existing methods by a significant margin on four benchmarks, including MoSu. Our code and dataset are available at https://github.com/smkim37/TripleSumm.

Large-scale video-language pre-training has made remarkable strides in advancing video-language understanding tasks. However, the heavy computational burden of video encoding remains a formidable efficiency bottleneck, particularly for long-form videos. These videos contain massive visual tokens due to their inherent 3D properties and spatiotemporal redundancy, making it challenging to capture complex temporal and spatial relationships. To tackle this issue, we propose an efficient method called TEmporal-Spatial Token Aggregation (TESTA). TESTA condenses video semantics by adaptively aggregating similar frames, as well as similar patches within each frame. TESTA can reduce the number of visual tokens by 75% and thus accelerate video encoding. Building upon TESTA, we introduce a pre-trained video-language model equipped with a divided space-time token aggregation module in each video encoder block. We evaluate our model on five datasets for paragraph-to-video retrieval and long-form VideoQA tasks. Experimental results show that TESTA improves computing efficiency by 1.7 times, and achieves significant performance gains from its scalability in processing longer input frames, e.g., +13.7 R@1 on QuerYD and +6.5 R@1 on Condensed Movie.

Dual encoder architectures like CLIP models map two types of inputs into a shared embedding space and predict similarities between them. Despite their success, it is, however, not understood how these models compare their two inputs. Common first-order feature-attribution methods can only provide limited insights into dual-encoders since their predictions depend on feature-interactions rather than on individual features. In this paper, we first derive a second-order method enabling the attribution of predictions by any differentiable dual encoder onto feature-interactions between its inputs. Second, we apply our method to CLIP models and show that they learn fine-grained correspondences between parts of captions and regions in images. They match objects across input modes also account for mismatches. This visual-linguistic grounding ability, however, varies heavily between object classes and exhibits pronounced out-of-domain effects. We can identify individual errors as well as systematic failure categories including object coverage, unusual scenes and correlated contexts.

Recent image generation models excel at creating high-quality images from brief captions. However, they fail to maintain consistency of multiple instances across images when encountering lengthy contexts. This inconsistency is largely due to in existing training datasets the absence of granular instance feature labeling in existing training datasets. To tackle these issues, we introduce Openstory++, a large-scale dataset combining additional instance-level annotations with both images and text. Furthermore, we develop a training methodology that emphasizes entity-centric image-text generation, ensuring that the models learn to effectively interweave visual and textual information. Specifically, Openstory++ streamlines the process of keyframe extraction from open-domain videos, employing vision-language models to generate captions that are then polished by a large language model for narrative continuity. It surpasses previous datasets by offering a more expansive open-domain resource, which incorporates automated captioning, high-resolution imagery tailored for instance count, and extensive frame sequences for temporal consistency. Additionally, we present Cohere-Bench, a pioneering benchmark framework for evaluating the image generation tasks when long multimodal context is provided, including the ability to keep the background, style, instances in the given context coherent. Compared to existing benchmarks, our work fills critical gaps in multi-modal generation, propelling the development of models that can adeptly generate and interpret complex narratives in open-domain environments. Experiments conducted within Cohere-Bench confirm the superiority of Openstory++ in nurturing high-quality visual storytelling models, enhancing their ability to address open-domain generation tasks. More details can be found at https://openstorypp.github.io/

Video DiTs have advanced video generation, yet they still struggle to model multi-instance or subject-object interactions. This raises a key question: How do these models internally represent interactions? To answer this, we curate MATRIX-11K, a video dataset with interaction-aware captions and multi-instance mask tracks. Using this dataset, we conduct a systematic analysis that formalizes two perspectives of video DiTs: semantic grounding, via video-to-text attention, which evaluates whether noun and verb tokens capture instances and their relations; and semantic propagation, via video-to-video attention, which assesses whether instance bindings persist across frames. We find both effects concentrate in a small subset of interaction-dominant layers. Motivated by this, we introduce MATRIX, a simple and effective regularization that aligns attention in specific layers of video DiTs with multi-instance mask tracks from the MATRIX-11K dataset, enhancing both grounding and propagation. We further propose InterGenEval, an evaluation protocol for interaction-aware video generation. In experiments, MATRIX improves both interaction fidelity and semantic alignment while reducing drift and hallucination. Extensive ablations validate our design choices. Codes and weights will be released.

We focus on grounding (i.e., localizing or linking) referring expressions in images, e.g., "largest elephant standing behind baby elephant". This is a general yet challenging vision-language task since it does not only require the localization of objects, but also the multimodal comprehension of context --- visual attributes (e.g., "largest", "baby") and relationships (e.g., "behind") that help to distinguish the referent from other objects, especially those of the same category. Due to the exponential complexity involved in modeling the context associated with multiple image regions, existing work oversimplifies this task to pairwise region modeling by multiple instance learning. In this paper, we propose a variational Bayesian method, called Variational Context, to solve the problem of complex context modeling in referring expression grounding. Our model exploits the reciprocal relation between the referent and context, i.e., either of them influences the estimation of the posterior distribution of the other, and thereby the search space of context can be greatly reduced, resulting in better localization of referent. We develop a novel cue-specific language-vision embedding network that learns this reciprocity model end-to-end. We also extend the model to the unsupervised setting where no annotation for the referent is available. Extensive experiments on various benchmarks show consistent improvement over state-of-the-art methods in both supervised and unsupervised settings.

Information retrieval is indispensable for today's Internet applications, yet traditional semantic matching techniques often fall short in capturing the fine-grained cross-modal interactions required for complex queries. Although late-fusion two-tower architectures attempt to bridge this gap by independently encoding visual and textual data before merging them at a high level, they frequently overlook the subtle interplay essential for comprehensive understanding. In this work, we rigorously assess these limitations and introduce a unified retrieval framework that fuses visual and textual cues from the ground up, enabling early cross-modal interactions for enhancing context interpretation. Through a two-stage training process--comprising post-training adaptation followed by instruction tuning--we adapt MLLMs as retrievers using a simple one-tower architecture. Our approach outperforms conventional methods across diverse retrieval scenarios, particularly when processing complex multi-modal inputs. Notably, the joint fusion encoder yields greater improvements on tasks that require modality fusion compared to those that do not, underscoring the transformative potential of early integration strategies and pointing toward a promising direction for contextually aware and effective information retrieval.

As video content creation shifts toward long-form narratives, composing short clips into coherent storylines becomes increasingly important. However, prevailing retrieval formulations remain context-agnostic at inference time, prioritizing local semantic alignment while neglecting state and identity consistency. To address this structural limitation, we formalize the task of Consistent Video Retrieval (CVR) and introduce a diagnostic benchmark spanning YouCook2, COIN, and CrossTask. We propose CAST (Context-Aware State Transition), a lightweight, plug-and-play adapter compatible with diverse frozen vision-language embedding spaces. By predicting a state-conditioned residual update (Δ) from visual history, CAST introduces an explicit inductive bias for latent state evolution. Extensive experiments show that CAST improves performance on YouCook2 and CrossTask, remains competitive on COIN, and consistently outperforms zero-shot baselines across diverse foundation backbones. Furthermore, CAST provides a useful reranking signal for black-box video generation candidates (e.g., from Veo), promoting more temporally coherent continuations.

Recent advances in unified multimodal models (UMMs) have enabled impressive progress in visual comprehension and generation. However, existing datasets and benchmarks focus primarily on single-turn interactions, failing to capture the multi-turn, context-dependent nature of real-world image creation and editing. To address this gap, we present WEAVE, the first suite for in-context interleaved cross-modality comprehension and generation. Our suite consists of two complementary parts. WEAVE-100k is a large-scale dataset of 100K interleaved samples spanning over 370K dialogue turns and 500K images, covering comprehension, editing, and generation tasks that require reasoning over historical context. WEAVEBench is a human-annotated benchmark with 100 tasks based on 480 images, featuring a hybrid VLM judger evaluation framework based on both the reference image and the combination of the original image with editing instructions that assesses models' abilities in multi-turn generation, visual memory, and world-knowledge reasoning across diverse domains. Experiments demonstrate that training on WEAVE-100k enables vision comprehension, image editing, and comprehension-generation collaboration capabilities. Furthermore, it facilitates UMMs to develop emergent visual-memory capabilities, while extensive evaluations on WEAVEBench expose the persistent limitations and challenges of current approaches in multi-turn, context-aware image generation and editing. We believe WEAVE provides a view and foundation for studying in-context interleaved comprehension and generation for multi-modal community.

We present a new large-scale multilingual video description dataset, VATEX, which contains over 41,250 videos and 825,000 captions in both English and Chinese. Among the captions, there are over 206,000 English-Chinese parallel translation pairs. Compared to the widely-used MSR-VTT dataset, VATEX is multilingual, larger, linguistically complex, and more diverse in terms of both video and natural language descriptions. We also introduce two tasks for video-and-language research based on VATEX: (1) Multilingual Video Captioning, aimed at describing a video in various languages with a compact unified captioning model, and (2) Video-guided Machine Translation, to translate a source language description into the target language using the video information as additional spatiotemporal context. Extensive experiments on the VATEX dataset show that, first, the unified multilingual model can not only produce both English and Chinese descriptions for a video more efficiently, but also offer improved performance over the monolingual models. Furthermore, we demonstrate that the spatiotemporal video context can be effectively utilized to align source and target languages and thus assist machine translation. In the end, we discuss the potentials of using VATEX for other video-and-language research.

While recent advancements in vision-language models have improved video understanding, diagnosing their capacity for deep, narrative comprehension remains a challenge. Existing benchmarks often test short-clip recognition or use template-based questions, leaving a critical gap in evaluating fine-grained reasoning over long-form narrative content. To address these gaps, we introduce Cinacute{easte}, a comprehensive benchmark for long-form movie understanding. Our dataset comprises 3,119 multiple-choice question-answer pairs derived from 1,805 scenes across 200 diverse movies, spanning five novel fine-grained contextual reasoning categories. We use GPT-4o to generate diverse, context-rich questions by integrating visual descriptions, captions, scene titles, and summaries, which require deep narrative understanding. To ensure high-quality evaluation, our pipeline incorporates a two-stage filtering process: Context-Independence filtering ensures questions require video context, while Contextual Veracity filtering validates factual consistency against the movie content, mitigating hallucinations. Experiments show that existing MLLMs struggle on Cinacute{easte}; our analysis reveals that long-range temporal reasoning is a primary bottleneck, with the top open-source model achieving only 63.15\% accuracy. This underscores significant challenges in fine-grained contextual understanding and the need for advancements in long-form movie comprehension.

Detecting visual content on language expression has become an emerging topic in the community. However, in the video domain, the existing setting, i.e., spatial-temporal video grounding (STVG), is formulated to only detect one pre-existing object in each frame, ignoring the fact that language descriptions can involve none or multiple entities within a video. In this work, we advance the STVG to a more practical setting called described spatial-temporal video detection (DSTVD) by overcoming the above limitation. To facilitate the exploration of DSTVD, we first introduce a new benchmark, namely DVD-ST. Notably, DVD-ST supports grounding from none to many objects onto the video in response to queries and encompasses a diverse range of over 150 entities, including appearance, actions, locations, and interactions. The extensive breadth and diversity of the DVD-ST dataset make it an exemplary testbed for the investigation of DSTVD. In addition to the new benchmark, we further present two baseline methods for our proposed DSTVD task by extending two representative STVG models, i.e., TubeDETR, and STCAT. These extended models capitalize on tubelet queries to localize and track referred objects across the video sequence. Besides, we adjust the training objectives of these models to optimize spatial and temporal localization accuracy and multi-class classification capabilities. Furthermore, we benchmark the baselines on the introduced DVD-ST dataset and conduct extensive experimental analysis to guide future investigation. Our code and benchmark will be publicly available.

Large video language models (LVLMs) have made notable progress in video understanding, spurring the development of corresponding evaluation benchmarks. However, existing benchmarks generally assess overall performance across entire video sequences, overlooking nuanced behaviors such as contextual positional bias, a critical yet under-explored aspect of LVLM performance. We present Video-LevelGauge, a dedicated benchmark designed to systematically assess positional bias in LVLMs. We employ standardized probes and customized contextual setups, allowing flexible control over context length, probe position, and contextual types to simulate diverse real-world scenarios. In addition, we introduce a comprehensive analysis method that combines statistical measures with morphological pattern recognition to characterize bias. Our benchmark comprises 438 manually curated videos spanning multiple types, yielding 1,177 high-quality multiple-choice questions and 120 open-ended questions, validated for their effectiveness in exposing positional bias. Based on these, we evaluate 27 state-of-the-art LVLMs, including both commercial and open-source models. Our findings reveal significant positional biases in many leading open-source models, typically exhibiting head or neighbor-content preferences. In contrast, commercial models such as Gemini2.5-Pro show impressive, consistent performance across entire video sequences. Further analyses on context length, context variation, and model scale provide actionable insights for mitigating bias and guiding model enhancement.

The standard approach for visual place recognition is to use global image descriptors to retrieve the most similar database images for a given query image. The results can then be further improved with re-ranking methods that re-order the top scoring images. However, existing methods focus on re-ranking based on the same image descriptors that were used for the initial retrieval, which we argue provides limited additional signal. In this work we propose Generalized Contextual Similarity Aggregation (GCSA), which is a graph neural network-based re-ranking method that, in addition to the visual descriptors, can leverage other types of available side information. This can for example be other sensor data (such as signal strength of nearby WiFi or BlueTooth endpoints) or geometric properties such as camera poses for database images. In many applications this information is already present or can be acquired with low effort. Our architecture leverages the concept of affinity vectors to allow for a shared encoding of the heterogeneous multi-modal input. Two large-scale datasets, covering both outdoor and indoor localization scenarios, are utilized for training and evaluation. In experiments we show significant improvement not only on image retrieval metrics, but also for the downstream visual localization task.

Text-video retrieval is a challenging cross-modal task, which aims to align visual entities with natural language descriptions. Current methods either fail to leverage the local details or are computationally expensive. What's worse, they fail to leverage the heterogeneous concepts in data. In this paper, we propose the Disentangled Conceptualization and Set-to-set Alignment (DiCoSA) to simulate the conceptualizing and reasoning process of human beings. For disentangled conceptualization, we divide the coarse feature into multiple latent factors related to semantic concepts. For set-to-set alignment, where a set of visual concepts correspond to a set of textual concepts, we propose an adaptive pooling method to aggregate semantic concepts to address the partial matching. In particular, since we encode concepts independently in only a few dimensions, DiCoSA is superior at efficiency and granularity, ensuring fine-grained interactions using a similar computational complexity as coarse-grained alignment. Extensive experiments on five datasets, including MSR-VTT, LSMDC, MSVD, ActivityNet, and DiDeMo, demonstrate that our method outperforms the existing state-of-the-art methods.

Long video understanding remains challenging for Multi-modal Large Language Models (MLLMs) due to high memory costs and context-length limits. Prior approaches mitigate this by scoring and selecting frames/tokens within short clips, but they lack a principled mechanism to (i) compare relevance across distant video clips and (ii) stop processing once sufficient evidence has been gathered. We propose AdaptToken, a training-free framework that turns an MLLM's self-uncertainty into a global control signal for long-video token selection. AdaptToken splits a video into groups, extracts cross-modal attention to rank tokens within each group, and uses the model's response entropy to estimate each group's prompt relevance. This entropy signal enables a global token budget allocation across groups and further supports early stopping (AdaptToken-Lite), skipping the remaining groups when the model becomes sufficiently certain. Across four long-video benchmarks (VideoMME, LongVideoBench, LVBench, and MLVU) and multiple base MLLMs (7B-72B), AdaptToken consistently improves accuracy (e.g., +6.7 on average over Qwen2.5-VL 7B) and continues to benefit from extremely long inputs (up to 10K frames), while AdaptToken-Lite reduces inference time by about half with comparable performance. Project page: https://haozheqi.github.io/adapt-token

The ability to integrate context, including perceptual and temporal cues, plays a pivotal role in grounding the meaning of a linguistic utterance. In order to measure to what extent current vision-and-language models master this ability, we devise a new multimodal challenge, Image Retrieval from Contextual Descriptions (ImageCoDe). In particular, models are tasked with retrieving the correct image from a set of 10 minimally contrastive candidates based on a contextual description. As such, each description contains only the details that help distinguish between images. Because of this, descriptions tend to be complex in terms of syntax and discourse and require drawing pragmatic inferences. Images are sourced from both static pictures and video frames. We benchmark several state-of-the-art models, including both cross-encoders such as ViLBERT and bi-encoders such as CLIP, on ImageCoDe. Our results reveal that these models dramatically lag behind human performance: the best variant achieves an accuracy of 20.9 on video frames and 59.4 on static pictures, compared with 90.8 in humans. Furthermore, we experiment with new model variants that are better equipped to incorporate visual and temporal context into their representations, which achieve modest gains. Our hope is that ImageCoDE will foster progress in grounded language understanding by encouraging models to focus on fine-grained visual differences.

Synthesizing motion-rich and temporally consistent videos remains a challenge in artificial intelligence, especially when dealing with extended durations. Existing text-to-video (T2V) models commonly employ spatial cross-attention for text control, equivalently guiding different frame generations without frame-specific textual guidance. Thus, the model's capacity to comprehend the temporal logic conveyed in prompts and generate videos with coherent motion is restricted. To tackle this limitation, we introduce FancyVideo, an innovative video generator that improves the existing text-control mechanism with the well-designed Cross-frame Textual Guidance Module (CTGM). Specifically, CTGM incorporates the Temporal Information Injector (TII), Temporal Affinity Refiner (TAR), and Temporal Feature Booster (TFB) at the beginning, middle, and end of cross-attention, respectively, to achieve frame-specific textual guidance. Firstly, TII injects frame-specific information from latent features into text conditions, thereby obtaining cross-frame textual conditions. Then, TAR refines the correlation matrix between cross-frame textual conditions and latent features along the time dimension. Lastly, TFB boosts the temporal consistency of latent features. Extensive experiments comprising both quantitative and qualitative evaluations demonstrate the effectiveness of FancyVideo. Our approach achieves state-of-the-art T2V generation results on the EvalCrafter benchmark and facilitates the synthesis of dynamic and consistent videos. The video show results can be available at https://fancyvideo.github.io/, and we will make our code and model weights publicly available.

Person search aims to jointly localize and identify a query person from natural, uncropped images, which has been actively studied over the past few years. In this paper, we delve into the rich context information globally and locally surrounding the target person, which we refer to as scene and group context, respectively. Unlike previous works that treat the two types of context individually, we exploit them in a unified global-local context network (GLCNet) with the intuitive aim of feature enhancement. Specifically, re-ID embeddings and context features are simultaneously learned in a multi-stage fashion, ultimately leading to enhanced, discriminative features for person search. We conduct the experiments on two person search benchmarks (i.e., CUHK-SYSU and PRW) as well as extend our approach to a more challenging setting (i.e., character search on MovieNet). Extensive experimental results demonstrate the consistent improvement of the proposed GLCNet over the state-of-the-art methods on all three datasets. Our source codes, pre-trained models, and the new dataset are publicly available at: https://github.com/ZhengPeng7/GLCNet.

While multimodal large language models (MLLMs) exhibit strong performance on single-video tasks (e.g., video question answering), their ability across multiple videos remains critically underexplored. However, this capability is essential for real-world applications, including multi-camera surveillance and cross-video procedural learning. To bridge this gap, we present CVBench, the first comprehensive benchmark designed to assess cross-video relational reasoning rigorously. CVBench comprises 1,000 question-answer pairs spanning three hierarchical tiers: cross-video object association (identifying shared entities), cross-video event association (linking temporal or causal event chains), and cross-video complex reasoning (integrating commonsense and domain knowledge). Built from five domain-diverse video clusters (e.g., sports, life records), the benchmark challenges models to synthesise information across dynamic visual contexts. Extensive evaluation of 10+ leading MLLMs (including GPT-4o, Gemini-2.0-flash, Qwen2.5-VL) under zero-shot or chain-of-thought prompting paradigms. Key findings reveal stark performance gaps: even top models, such as GPT-4o, achieve only 60% accuracy on causal reasoning tasks, compared to the 91% accuracy of human performance. Crucially, our analysis reveals fundamental bottlenecks inherent in current MLLM architectures, notably deficient inter-video context retention and poor disambiguation of overlapping entities. CVBench establishes a rigorous framework for diagnosing and advancing multi-video reasoning, offering architectural insights for next-generation MLLMs. The data and evaluation code are available at https://github.com/Hokhim2/CVBench.

High-quality image captions play a crucial role in improving the performance of cross-modal applications such as text-to-image generation, text-to-video generation, and text-image retrieval. To generate long-form, high-quality captions, many recent studies have employed multimodal large language models (MLLMs). However, current MLLMs often produce captions that lack fine-grained details or suffer from hallucinations, a challenge that persists in both open-source and closed-source models. Inspired by Feature-Integration theory, which suggests that attention must focus on specific regions to integrate visual information effectively, we propose a divide-then-aggregate strategy. Our method first divides the image into semantic and spatial patches to extract fine-grained details, enhancing the model's local perception of the image. These local details are then hierarchically aggregated to generate a comprehensive global description. To address hallucinations and inconsistencies in the generated captions, we apply a semantic-level filtering process during hierarchical aggregation. This training-free pipeline can be applied to both open-source models (LLaVA-1.5, LLaVA-1.6, Mini-Gemini) and closed-source models (Claude-3.5-Sonnet, GPT-4o, GLM-4V-Plus). Extensive experiments demonstrate that our method generates more detailed, reliable captions, advancing multimodal description generation without requiring model retraining. The source code are available at https://github.com/GeWu-Lab/Patch-Matters

Leveraging the generative ability of image diffusion models offers great potential for zero-shot video-to-video translation. The key lies in how to maintain temporal consistency across generated video frames by image diffusion models. Previous methods typically adopt cross-frame attention, i.e., sharing the key and value tokens across attentions of different frames, to encourage the temporal consistency. However, in those works, temporal inconsistency issue may not be thoroughly solved, rendering the fidelity of generated videos limited.%The current state of the art cross-frame attention method aims at maintaining fine-grained visual details across frames, but it is still challenged by the temporal coherence problem. In this paper, we find the bottleneck lies in the unconstrained query tokens and propose a new zero-shot video-to-video translation framework, named LatentWarp. Our approach is simple: to constrain the query tokens to be temporally consistent, we further incorporate a warping operation in the latent space to constrain the query tokens. Specifically, based on the optical flow obtained from the original video, we warp the generated latent features of last frame to align with the current frame during the denoising process. As a result, the corresponding regions across the adjacent frames can share closely-related query tokens and attention outputs, which can further improve latent-level consistency to enhance visual temporal coherence of generated videos. Extensive experiment results demonstrate the superiority of LatentWarp in achieving video-to-video translation with temporal coherence.

We present MCQA, a learning-based algorithm for multimodal question answering. MCQA explicitly fuses and aligns the multimodal input (i.e. text, audio, and video), which forms the context for the query (question and answer). Our approach fuses and aligns the question and the answer within this context. Moreover, we use the notion of co-attention to perform cross-modal alignment and multimodal context-query alignment. Our context-query alignment module matches the relevant parts of the multimodal context and the query with each other and aligns them to improve the overall performance. We evaluate the performance of MCQA on Social-IQ, a benchmark dataset for multimodal question answering. We compare the performance of our algorithm with prior methods and observe an accuracy improvement of 4-7%.

Long video understanding (LVU) remains a core challenge in multimodal learning. Although recent vision-language models (VLMs) have made notable progress, existing benchmarks mainly focus on either fine-grained perception or coarse summarization, offering limited insight into temporal understanding over long contexts. In this work, we define a scene as a coherent segment of a video in which both visual and semantic contexts remain consistent, aligning with human perception. This leads us to a key question: can current VLMs reason effectively over long, scene-level contexts? To answer this, we introduce a new benchmark, SceneBench, designed to provide scene-level challenges. Our evaluation reveals a sharp drop in accuracy when VLMs attempt to answer scene-level questions, indicating significant forgetting of long-range context. To further validate these findings, we propose Scene Retrieval-Augmented Generation (Scene-RAG), which constructs a dynamic scene memory by retrieving and integrating relevant context across scenes. This Scene-RAG improves VLM performance by +2.50%, confirming that current models still struggle with long-context retention. We hope SceneBench will encourage future research toward VLMs with more robust, human-like video comprehension.

Extending image-based Large Multimodal Models (LMM) to videos is challenging due to the inherent complexity of video data. The recent approaches extending image-based LMM to videos either lack the grounding capabilities (e.g., VideoChat, Video-ChatGPT, Video-LLaMA) or do not utilize the audio-signals for better video understanding (e.g., Video-ChatGPT). Addressing these gaps, we propose Video-LLaVA, the first LMM with pixel-level grounding capability, integrating audio cues by transcribing them into text to enrich video-context understanding. Our framework uses an off-the-shelf tracker and a novel grounding module, enabling it to spatially and temporally localize objects in videos following user instructions. We evaluate Video-LLaVA using video-based generative and question-answering benchmarks and introduce new benchmarks specifically designed to measure prompt-based object grounding performance in videos. Further, we propose the use of Vicuna over GPT-3.5, as utilized in Video-ChatGPT, for video-based conversation benchmarking, ensuring reproducibility of results which is a concern with the proprietary nature of GPT-3.5. Our framework builds on SoTA image-based LLaVA model and extends its advantages to the video domain, delivering promising gains on video-based conversation and grounding tasks. Project Page: https://github.com/mbzuai-oryx/Video-LLaVA

Recently proposed fine-grained 3D visual grounding is an essential and challenging task, whose goal is to identify the 3D object referred by a natural language sentence from other distractive objects of the same category. Existing works usually adopt dynamic graph networks to indirectly model the intra/inter-modal interactions, making the model difficult to distinguish the referred object from distractors due to the monolithic representations of visual and linguistic contents. In this work, we exploit Transformer for its natural suitability on permutation-invariant 3D point clouds data and propose a TransRefer3D network to extract entity-and-relation aware multimodal context among objects for more discriminative feature learning. Concretely, we devise an Entity-aware Attention (EA) module and a Relation-aware Attention (RA) module to conduct fine-grained cross-modal feature matching. Facilitated by co-attention operation, our EA module matches visual entity features with linguistic entity features while RA module matches pair-wise visual relation features with linguistic relation features, respectively. We further integrate EA and RA modules into an Entity-and-Relation aware Contextual Block (ERCB) and stack several ERCBs to form our TransRefer3D for hierarchical multimodal context modeling. Extensive experiments on both Nr3D and Sr3D datasets demonstrate that our proposed model significantly outperforms existing approaches by up to 10.6% and claims the new state-of-the-art. To the best of our knowledge, this is the first work investigating Transformer architecture for fine-grained 3D visual grounding task.

Visual storytelling involves generating a sequence of coherent frames from a textual storyline while maintaining consistency in characters and scenes. Existing autoregressive methods, which rely on previous frame-sentence pairs, struggle with high memory usage, slow generation speeds, and limited context integration. To address these issues, we propose ContextualStory, a novel framework designed to generate coherent story frames and extend frames for visual storytelling. ContextualStory utilizes Spatially-Enhanced Temporal Attention to capture spatial and temporal dependencies, handling significant character movements effectively. Additionally, we introduce a Storyline Contextualizer to enrich context in storyline embedding, and a StoryFlow Adapter to measure scene changes between frames for guiding the model. Extensive experiments on PororoSV and FlintstonesSV datasets demonstrate that ContextualStory significantly outperforms existing SOTA methods in both story visualization and continuation. Code is available at https://github.com/sixiaozheng/ContextualStory.

With the development of video generation models has advanced significantly in recent years, we adopt large-scale image-to-video diffusion models for video frame interpolation. We present a conditional encoder designed to adapt an image-to-video model for large-motion frame interpolation. To enhance performance, we integrate a dual-branch feature extractor and propose a cross-frame attention mechanism that effectively captures both spatial and temporal information, enabling accurate interpolations of intermediate frames. Our approach demonstrates superior performance on the Fr\'echet Video Distance (FVD) metric when evaluated against other state-of-the-art approaches, particularly in handling large motion scenarios, highlighting advancements in generative-based methodologies.

CLIP achieves strong zero-shot image-text retrieval by aligning global vision and text representations, yet it falls behind on fine-grained tasks even when fine-tuned on long, detailed captions. In this work, we propose β-CLIP, a multi-granular text-conditioned contrastive learning framework designed to achieve hierarchical alignment between multiple textual granularities-from full captions to sentences and phrases-and their corresponding visual regions. For each level of granularity, β-CLIP utilizes cross-attention to dynamically pool image patches, producing contextualized visual embeddings. To address the semantic overlap inherent in this hierarchy, we introduce the β-Contextualized Contrastive Alignment Loss (β-CAL). This objective parameterizes the trade-off between strict query-specific matching and relaxed intra-image contextualization, supporting both soft Cross-Entropy and hard Binary Cross-Entropy formulations. Through extensive experiments, we demonstrate that β-CLIP significantly improves dense alignment: achieving 91.8% T2I 92.3% I2T at R@1 on Urban1K and 30.9% on FG-OVD (Hard), setting state-of-the-art among methods trained without hard negatives. β-CLIP establishes a robust, adaptive baseline for dense vision-language correspondence. The code and models are released at https://github.com/fzohra/B-CLIP.

Cross-modal metric learning is a prominent research topic that bridges the semantic heterogeneity between vision and language. Existing methods frequently utilize simple cosine or complex distance metrics to transform the pairwise features into a similarity score, which suffers from an inadequate or inefficient capability for distance measurements. Consequently, we propose a Generalized Structural Sparse Function to dynamically capture thorough and powerful relationships across modalities for pair-wise similarity learning while remaining concise but efficient. Specifically, the distance metric delicately encapsulates two formats of diagonal and block-diagonal terms, automatically distinguishing and highlighting the cross-channel relevancy and dependency inside a structured and organized topology. Hence, it thereby empowers itself to adapt to the optimal matching patterns between the paired features and reaches a sweet spot between model complexity and capability. Extensive experiments on cross-modal and two extra uni-modal retrieval tasks (image-text retrieval, person re-identification, fine-grained image retrieval) have validated its superiority and flexibility over various popular retrieval frameworks. More importantly, we further discover that it can be seamlessly incorporated into multiple application scenarios, and demonstrates promising prospects from Attention Mechanism to Knowledge Distillation in a plug-and-play manner. Our code is publicly available at: https://github.com/Paranioar/GSSF.

Recently, Vision Large Language Models (VLLMs) integrated with vision encoders have shown promising performance in vision understanding. The key of VLLMs is to encode visual content into sequences of visual tokens, enabling VLLMs to simultaneously process both visual and textual content. However, understanding videos, especially long videos, remain a challenge to VLLMs as the number of visual tokens grows rapidly when encoding videos, resulting in the risk of exceeding the context window of VLLMs and introducing heavy computation burden. To restrict the number of visual tokens, existing VLLMs either: (1) uniformly downsample videos into a fixed number of frames or (2) reducing the number of visual tokens encoded from each frame. We argue the former solution neglects the rich temporal cue in videos and the later overlooks the spatial details in each frame. In this work, we present Balanced-VLLM (B-VLLM): a novel VLLM framework that aims to effectively leverage task relevant spatio-temporal cues while restricting the number of visual tokens under the VLLM context window length. At the core of our method, we devise a text-conditioned adaptive frame selection module to identify frames relevant to the visual understanding task. The selected frames are then de-duplicated using a temporal frame token merging technique. The visual tokens of the selected frames are processed through a spatial token sampling module and an optional spatial token merging strategy to achieve precise control over the token count. Experimental results show that B-VLLM is effective in balancing the number of frames and visual tokens in video understanding, yielding superior performance on various video understanding benchmarks. Our code is available at https://github.com/zhuqiangLu/B-VLLM.

Despite the prevailing transition from single-task to multi-task approaches in video anomaly detection, we observe that many adopt sub-optimal frameworks for individual proxy tasks. Motivated by this, we contend that optimizing single-task frameworks can advance both single- and multi-task approaches. Accordingly, we leverage middle-frame prediction as the primary proxy task, and introduce an effective hybrid framework designed to generate accurate predictions for normal frames and flawed predictions for abnormal frames. This hybrid framework is built upon a bi-directional structure that seamlessly integrates both vision transformers and ConvLSTMs. Specifically, we utilize this bi-directional structure to fully analyze the temporal dimension by predicting frames in both forward and backward directions, significantly boosting the detection stability. Given the transformer's capacity to model long-range contextual dependencies, we develop a convolutional temporal transformer that efficiently associates feature maps from all context frames to generate attention-based predictions for target frames. Furthermore, we devise a layer-interactive ConvLSTM bridge that facilitates the smooth flow of low-level features across layers and time-steps, thereby strengthening predictions with fine details. Anomalies are eventually identified by scrutinizing the discrepancies between target frames and their corresponding predictions. Several experiments conducted on public benchmarks affirm the efficacy of our hybrid framework, whether used as a standalone single-task approach or integrated as a branch in a multi-task approach. These experiments also underscore the advantages of merging vision transformers and ConvLSTMs for video anomaly detection.

Cross-Video Reasoning (CVR) presents a significant challenge in video understanding, which requires simultaneous understanding of multiple videos to aggregate and compare information across groups of videos. Most existing video understanding benchmarks focus on single-video analysis, failing to assess the ability of multimodal large language models (MLLMs) to simultaneously reason over various videos. Recent benchmarks evaluate MLLMs' capabilities on multi-view videos that capture different perspectives of the same scene. However, their limited tasks hinder a thorough assessment of MLLMs in diverse real-world CVR scenarios. To this end, we introduce CrossVid, the first benchmark designed to comprehensively evaluate MLLMs' spatial-temporal reasoning ability in cross-video contexts. Firstly, CrossVid encompasses a wide spectrum of hierarchical tasks, comprising four high-level dimensions and ten specific tasks, thereby closely reflecting the complex and varied nature of real-world video understanding. Secondly, CrossVid provides 5,331 videos, along with 9,015 challenging question-answering pairs, spanning single-choice, multiple-choice, and open-ended question formats. Through extensive experiments on various open-source and closed-source MLLMs, we observe that Gemini-2.5-Pro performs best on CrossVid, achieving an average accuracy of 50.4%. Notably, our in-depth case study demonstrates that most current MLLMs struggle with CVR tasks, primarily due to their inability to integrate or compare evidence distributed across multiple videos for reasoning. These insights highlight the potential of CrossVid to guide future advancements in enhancing MLLMs' CVR capabilities.

Empowered by Large Language Models (LLMs), recent advancements in Video-based LLMs (VideoLLMs) have driven progress in various video understanding tasks. These models encode video representations through pooling or query aggregation over a vast number of visual tokens, making computational and memory costs affordable. Despite successfully providing an overall comprehension of video content, existing VideoLLMs still face challenges in achieving detailed understanding due to overlooking local information in long-term videos. To tackle this challenge, we introduce LongVLM, a simple yet powerful VideoLLM for long video understanding, building upon the observation that long videos often consist of sequential key events, complex actions, and camera movements. Our approach proposes to decompose long videos into multiple short-term segments and encode local features for each segment via a hierarchical token merging module. These features are concatenated in temporal order to maintain the storyline across sequential short-term segments. Additionally, we propose to integrate global semantics into each local feature to enhance context understanding. In this way, we encode video representations that incorporate both local and global information, enabling the LLM to generate comprehensive responses for long-term videos. Experimental results on the VideoChatGPT benchmark and zero-shot video question-answering datasets demonstrate the superior capabilities of our model over the previous state-of-the-art methods. Qualitative examples show that our model produces more precise responses for long video understanding. Code is available at https://github.com/ziplab/LongVLM.

Long-context large language models (LC LLMs) combined with retrieval-augmented generation (RAG) hold strong potential for complex multi-hop and large-document tasks. However, existing RAG systems often suffer from imprecise retrieval, incomplete context coverage under constrained windows, and fragmented information from suboptimal context construction. We introduce Multi-scale Adaptive Context RAG (MacRAG), a hierarchical RAG framework that compresses and partitions documents into coarse-to-fine granularities, then adaptively merges relevant contexts through real-time chunk- and document-level expansions. By initiating with finest-level retrieval and progressively incorporating broader, higher-level context, MacRAG constructs effective query-specific long contexts, optimizing both precision and coverage. Evaluations on challenging LongBench expansions of HotpotQA, 2WikiMultihopQA, and Musique confirm MacRAG consistently surpasses baseline RAG pipelines in single- and multi-step generation using Llama-3.1-8B, Gemini-1.5-pro, and GPT-4o. Our results establish MacRAG as an efficient, scalable solution for real-world long-context, multi-hop reasoning. Our code is available at https://github.com/Leezekun/MacRAG.

Large Multimodal Models (LMMs) have demonstrated impressive performance in short video understanding tasks but face great challenges when applied to long video understanding. In contrast, Large Language Models (LLMs) exhibit outstanding capabilities in modeling long texts. Existing work attempts to address this issue by introducing long video-text pairs during training. However, these approaches require substantial computational and data resources. In this paper, we tackle the challenge of long video understanding from the perspective of context windows, aiming to apply LMMs to long video tasks without retraining on long video datasets. We first conduct an in-depth analysis of why pretrained LMMs struggle to understand lengthy video content, identifying that discrepancies between visual and language modalities lead to different context windows for visual and language tokens, making it difficult to directly extend the visual tokens to match the language context window. Based on this, we propose to adapt LMMs for long video understanding tasks by extending the visual context window, eliminating the need for retraining on large scalelong video datasets. To further mitigate the significant memory consumption caused by long sequences, we introduce a progressive pooling inference strategy that selectively adjusts the spatial resolution of frame embeddings, reducing the number of visual tokens while retaining important spatial information. Across multiple long video understanding benchmarks, our method consistently improves the performance as the number of video frames increases. On the MLVU benchmark, our method outperforms GPT-4o, even though our model size is only 7B. Additionally, in the 256-frame setting, our method reduces memory usage by approximately 45% compared to the baseline, without introducing any performance loss.

Referring Audio-Visual Segmentation (Ref-AVS) aims to segment specific objects in videos based on natural language expressions involving audio, vision, and text information. This task poses significant challenges in cross-modal reasoning and fine-grained object localization. In this paper, we propose a simple framework, SimToken, that integrates a multimodal large language model (MLLM) with the Segment Anything Model (SAM). The MLLM is guided to generate a special semantic token representing the referred object. This compact token, enriched with contextual information from all modalities, acts as a prompt to guide SAM to segment objectsacross video frames. To further improve semantic learning, we introduce a novel target-consistent semantic alignment loss that aligns token embeddings from different expressions but referring to the same object. Experiments on the Ref-AVS benchmark demonstrate that our approach achieves superior performance compared to existing methods.

Previous research has studied the task of segmenting cinematic videos into scenes and into narrative acts. However, these studies have overlooked the essential task of multimodal alignment and fusion for effectively and efficiently processing long-form videos (>60min). In this paper, we introduce Multimodal alignmEnt aGgregation and distillAtion (MEGA) for cinematic long-video segmentation. MEGA tackles the challenge by leveraging multiple media modalities. The method coarsely aligns inputs of variable lengths and different modalities with alignment positional encoding. To maintain temporal synchronization while reducing computation, we further introduce an enhanced bottleneck fusion layer which uses temporal alignment. Additionally, MEGA employs a novel contrastive loss to synchronize and transfer labels across modalities, enabling act segmentation from labeled synopsis sentences on video shots. Our experimental results show that MEGA outperforms state-of-the-art methods on MovieNet dataset for scene segmentation (with an Average Precision improvement of +1.19%) and on TRIPOD dataset for act segmentation (with a Total Agreement improvement of +5.51%)

Video summarization aims to distill the most important information from a source video to produce either an abridged clip or a textual narrative. Traditionally, different methods have been proposed depending on whether the output is a video or text, thus ignoring the correlation between the two semantically related tasks of visual summarization and textual summarization. We propose a new joint video and text summarization task. The goal is to generate both a shortened video clip along with the corresponding textual summary from a long video, collectively referred to as a cross-modal summary. The generated shortened video clip and text narratives should be semantically well aligned. To this end, we first build a large-scale human-annotated dataset -- VideoXum (X refers to different modalities). The dataset is reannotated based on ActivityNet. After we filter out the videos that do not meet the length requirements, 14,001 long videos remain in our new dataset. Each video in our reannotated dataset has human-annotated video summaries and the corresponding narrative summaries. We then design a novel end-to-end model -- VTSUM-BILP to address the challenges of our proposed task. Moreover, we propose a new metric called VT-CLIPScore to help evaluate the semantic consistency of cross-modality summary. The proposed model achieves promising performance on this new task and establishes a benchmark for future research.

While video foundation models excel at single-shot generation, real-world cinematic storytelling inherently relies on complex multi-shot sequencing. Further progress is constrained by the absence of datasets that address three core challenges: authentic narrative logic, spatiotemporal text-video alignment conflicts, and the "copy-paste" dilemma prevalent in Subject-to-Video (S2V) generation. To bridge this gap, we introduce MuSS, a large-scale, dual-track dataset tailored for multi-shot video and S2V generation. Sourced from over 3,000 movies, MuSS explicitly supports both complex montage transitions and subject-centric narratives. To construct this dataset, we pioneer a progressive captioning pipeline that eliminates contextual conflicts by ensuring local shot-level accuracy before enforcing global narrative coherence. Crucially, we implement a cross-shot matching mechanism to fundamentally eradicate the S2V copy-paste shortcut. Alongside the dataset, we propose the Cinematic Narrative Benchmark, featuring a visual-logic-driven paradigm and a novel Anti-Copy-Paste Variance (ACP-Var) metric to rigorously assess continuous storytelling and 3D structural consistency. Extensive experiments demonstrate that while current baselines struggle with continuous narrative logic or degenerate into trivial 2D sticker generators, our MuSS-augmented model achieves state-of-the-art narrative effectiveness and cross-shot identity preservation.

We present a frame interpolation algorithm that synthesizes multiple intermediate frames from two input images with large in-between motion. Recent methods use multiple networks to estimate optical flow or depth and a separate network dedicated to frame synthesis. This is often complex and requires scarce optical flow or depth ground-truth. In this work, we present a single unified network, distinguished by a multi-scale feature extractor that shares weights at all scales, and is trainable from frames alone. To synthesize crisp and pleasing frames, we propose to optimize our network with the Gram matrix loss that measures the correlation difference between feature maps. Our approach outperforms state-of-the-art methods on the Xiph large motion benchmark. We also achieve higher scores on Vimeo-90K, Middlebury and UCF101, when comparing to methods that use perceptual losses. We study the effect of weight sharing and of training with datasets of increasing motion range. Finally, we demonstrate our model's effectiveness in synthesizing high quality and temporally coherent videos on a challenging near-duplicate photos dataset. Codes and pre-trained models are available at https://film-net.github.io.

This paper presents the first study on adapting the visual in-context learning (V-ICL) paradigm to optical character recognition tasks, specifically focusing on text removal and segmentation. Most existing V-ICL generalists employ a reasoning-as-reconstruction approach: they turn to using a straightforward image-label compositor as the prompt and query input, and then masking the query label to generate the desired output. This direct prompt confines the model to a challenging single-step reasoning process. To address this, we propose a task-chaining compositor in the form of image-removal-segmentation, providing an enhanced prompt that elicits reasoning with enriched intermediates. Additionally, we introduce context-aware aggregation, integrating the chained prompt pattern into the latent query representation, thereby strengthening the model's in-context reasoning. We also consider the issue of visual heterogeneity, which complicates the selection of homogeneous demonstrations in text recognition. Accordingly, this is effectively addressed through a simple self-prompting strategy, preventing the model's in-context learnability from devolving into specialist-like, context-free inference. Collectively, these insights culminate in our ConText model, which achieves new state-of-the-art across both in- and out-of-domain benchmarks. The code is available at https://github.com/Ferenas/ConText.

Transformer-based methods have shown impressive performance in low-level vision tasks, such as image super-resolution. However, we find that these networks can only utilize a limited spatial range of input information through attribution analysis. This implies that the potential of Transformer is still not fully exploited in existing networks. In order to activate more input pixels for better reconstruction, we propose a novel Hybrid Attention Transformer (HAT). It combines both channel attention and window-based self-attention schemes, thus making use of their complementary advantages of being able to utilize global statistics and strong local fitting capability. Moreover, to better aggregate the cross-window information, we introduce an overlapping cross-attention module to enhance the interaction between neighboring window features. In the training stage, we additionally adopt a same-task pre-training strategy to exploit the potential of the model for further improvement. Extensive experiments show the effectiveness of the proposed modules, and we further scale up the model to demonstrate that the performance of this task can be greatly improved. Our overall method significantly outperforms the state-of-the-art methods by more than 1dB. Codes and models are available at https://github.com/XPixelGroup/HAT.

Despite advancements in multimodal large language models (MLLMs), current approaches struggle in medium-to-long video understanding due to frame and context length limitations. As a result, these models often depend on frame sampling, which risks missing key information over time and lacks task-specific relevance. To address these challenges, we introduce HierarQ, a task-aware hierarchical Q-Former based framework that sequentially processes frames to bypass the need for frame sampling, while avoiding LLM's context length limitations. We introduce a lightweight two-stream language-guided feature modulator to incorporate task awareness in video understanding, with the entity stream capturing frame-level object information within a short context and the scene stream identifying their broader interactions over longer period of time. Each stream is supported by dedicated memory banks which enables our proposed Hierachical Querying transformer (HierarQ) to effectively capture short and long-term context. Extensive evaluations on 10 video benchmarks across video understanding, question answering, and captioning tasks demonstrate HierarQ's state-of-the-art performance across most datasets, proving its robustness and efficiency for comprehensive video analysis.

Given a single labeled example, in-context segmentation aims to segment corresponding objects. This setting, known as one-shot segmentation in few-shot learning, explores the segmentation model's generalization ability and has been applied to various vision tasks, including scene understanding and image/video editing. While recent Segment Anything Models have achieved state-of-the-art results in interactive segmentation, these approaches are not directly applicable to in-context segmentation. In this work, we propose the Dual Consistency SAM (DC-SAM) method based on prompt-tuning to adapt SAM and SAM2 for in-context segmentation of both images and videos. Our key insights are to enhance the features of the SAM's prompt encoder in segmentation by providing high-quality visual prompts. When generating a mask prior, we fuse the SAM features to better align the prompt encoder. Then, we design a cycle-consistent cross-attention on fused features and initial visual prompts. Next, a dual-branch design is provided by using the discriminative positive and negative prompts in the prompt encoder. Furthermore, we design a simple mask-tube training strategy to adopt our proposed dual consistency method into the mask tube. Although the proposed DC-SAM is primarily designed for images, it can be seamlessly extended to the video domain with the support of SAM2. Given the absence of in-context segmentation in the video domain, we manually curate and construct the first benchmark from existing video segmentation datasets, named In-Context Video Object Segmentation (IC-VOS), to better assess the in-context capability of the model. Extensive experiments demonstrate that our method achieves 55.5 (+1.4) mIoU on COCO-20i, 73.0 (+1.1) mIoU on PASCAL-5i, and a J&F score of 71.52 on the proposed IC-VOS benchmark. Our source code and benchmark are available at https://github.com/zaplm/DC-SAM.

Video Large Language Models have demonstrated strong video understanding capabilities, yet their practical deployment is hindered by substantial inference costs caused by redundant video tokens. Existing pruning techniques fail to fully exploit the spatiotemporal redundancy inherent in video data. To bridge this gap, we perform a systematic analysis of video redundancy from two perspectives: temporal context and visual context. Leveraging these insights, we propose Dynamic Density Pruning for Fast Video LLMs termed FastVID. Specifically, FastVID dynamically partitions videos into temporally ordered segments to preserve temporal structure and applies a density-based token pruning strategy to maintain essential visual information. Our method significantly reduces computational overhead while maintaining temporal and visual integrity. Extensive evaluations show that FastVID achieves state-of-the-art performance across various short- and long-video benchmarks on leading Video LLMs, including LLaVA-OneVision and LLaVA-Video. Notably, on LLaVA-OneVision-7B, FastVID effectively prunes 90.3% of video tokens, reduces FLOPs to 8.3%, and accelerates the prefilling stage by 7.1times, while maintaining 98.0% of the original accuracy. The code is available at https://github.com/LunarShen/FastVID.