infactory-ai/infactory_pulse1-4b
Text Generation • 5B • Updated • 11
Infactory
company
Verified
AI & ML interests
Multi-modal video intelligence
Recent Activity
View all activity
Organization Card
The multi-modal data company
We find what's valuable in content archives and transform it into licensable AI-ready data.
Available Models
🧠Pulse 1 (4B) — Narrative Intelligence
A narrative intelligence model for extracting structured storylines from news and editorial content. Returns machine-readable JSON with actor-action-target-outcome decomposition.
Structured Output
Full Semantic Role Labeling — WHO did WHAT to WHOM with what outcome
Runs Locally
4B parameters, Apple Silicon native via Ollama and MLX
Pipeline-Ready
JSON-only output for downstream salience scoring, search, and filtering
Available Datasets
📷 Soccer Camera Detection
Per-frame shot scale (9 classes) and camera angle (5 classes) annotations for broadcast soccer — aligned with CineScale and CineScale2 taxonomies. Larger datasets available for licensing.
View Dataset →⚽ Soccer Ball Tracking
Bounding-box annotations for detecting and tracking soccer balls in broadcast footage — designed for tiny object detection challenges with motion blur and occlusion.
View Dataset →🟨 Soccer Referee Tracking
Bounding-box annotations for detecting and tracking referees across varied broadcast conditions — distinguishing them from players, coaches, and other on-field personnel.
View Dataset →🎬 Soccer In-Match Events
Curated video clips featuring in-match soccer events with detailed annotations — ideal for action recognition and sports analytics models.
View Dataset →