Papers
arxiv:1901.00484

Action2Vec: A Crossmodal Embedding Approach to Action Learning

Published on Jan 2, 2019
Authors:
,
,

Abstract

Action2Vec combines linguistic and spatio-temporal features using a hierarchical recurrent network to create a cross-modal embedding space for actions, achieving state-of-the-art zero-shot recognition and demonstrating strong distributional semantics through novel analogy tests.

We describe a novel cross-modal embedding space for actions, named Action2Vec, which combines linguistic cues from class labels with spatio-temporal features derived from video clips. Our approach uses a hierarchical recurrent network to capture the temporal structure of video features. We train our embedding using a joint loss that combines classification accuracy with similarity to Word2Vec semantics. We evaluate Action2Vec by performing zero shot action recognition and obtain state of the art results on three standard datasets. In addition, we present two novel analogy tests which quantify the extent to which our joint embedding captures distributional semantics. This is the first joint embedding space to combine verbs and action videos, and the first to be thoroughly evaluated with respect to its distributional semantics.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/1901.00484 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/1901.00484 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/1901.00484 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.