fansunqi/VideoTool

Official Repository for NeurIPS'25 Paper "Tool-Augmented Spatiotemporal Reasoning for Streamlining Video Question Answering Task"

29
/ 100
Experimental

This project helps researchers and developers working with AI models to better understand and answer questions about video content. It takes a video and a question as input, intelligently analyzes the video using a suite of specialized tools, and outputs a more accurate answer to the question. It's designed for AI practitioners focused on improving video comprehension and reasoning in large multimodal models.

Use this if you are developing or researching advanced AI systems that need to perform complex spatiotemporal reasoning and answer detailed questions based on video content.

Not ideal if you are looking for a simple, off-the-shelf video analysis tool for general business or creative tasks.

AI research Video understanding Multimodal AI Spatiotemporal reasoning Question answering
No Package No Dependents
Maintenance 10 / 25
Adoption 6 / 25
Maturity 13 / 25
Community 0 / 25

How are scores calculated?

Stars

17

Forks

Language

Python

License

MIT

Last pushed

Mar 08, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/fansunqi/VideoTool"

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