TencentARC/ST-LLM

[ECCV 2024🔥] Official implementation of the paper "ST-LLM: Large Language Models Are Effective Temporal Learners"

34
/ 100
Emerging

This project helps video content analysts, media professionals, and researchers automatically understand what's happening in videos, even complex or long ones. You provide a video, and it outputs detailed descriptions, identifies actions, or answers questions about the content. It's designed for anyone needing to extract precise, temporal information from video footage.

151 stars. No commits in the last 6 months.

Use this if you need a sophisticated AI to accurately describe events, actions, and answer specific questions within various video types, including long and challenging clips.

Not ideal if your primary need is simple image analysis or if you require real-time processing on very constrained hardware, as it's built for detailed temporal video understanding.

video-analysis content-moderation media-monitoring event-detection video-description
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 8 / 25

How are scores calculated?

Stars

151

Forks

7

Language

Python

License

Apache-2.0

Last pushed

Sep 10, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/TencentARC/ST-LLM"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.