TencentARC/ST-LLM
[ECCV 2024🔥] Official implementation of the paper "ST-LLM: Large Language Models Are Effective Temporal Learners"
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.
Stars
151
Forks
7
Language
Python
License
Apache-2.0
Category
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.
Higher-rated alternatives
KimMeen/Time-LLM
[ICLR 2024] Official implementation of " 🦙 Time-LLM: Time Series Forecasting by Reprogramming...
om-ai-lab/VLM-R1
Solve Visual Understanding with Reinforced VLMs
bytedance/SALMONN
SALMONN family: A suite of advanced multi-modal LLMs
NVlabs/OmniVinci
OmniVinci is an omni-modal LLM for joint understanding of vision, audio, and language.
fixie-ai/ultravox
A fast multimodal LLM for real-time voice