mlvlab/Flipped-VQA

Large Language Models are Temporal and Causal Reasoners for Video Question Answering (EMNLP 2023)

41
/ 100
Emerging

This project helps researchers and developers advance the field of video question answering. It takes a video and a natural language question about it, then outputs an accurate answer by analyzing temporal and causal relationships within the video. This is ideal for AI researchers, machine learning engineers, and data scientists working on understanding complex video content.

No commits in the last 6 months.

Use this if you are a researcher or developer aiming to improve AI models' ability to understand video content and answer complex questions that require temporal and causal reasoning.

Not ideal if you are looking for an out-of-the-box application for everyday video analysis without deep technical expertise in machine learning.

video-understanding AI-research natural-language-processing causal-reasoning machine-learning-development
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

78

Forks

12

Language

Python

License

MIT

Last pushed

Mar 26, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/mlvlab/Flipped-VQA"

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