antoyang/FrozenBiLM

[NeurIPS 2022] Zero-Shot Video Question Answering via Frozen Bidirectional Language Models

41
/ 100
Emerging

This project helps anyone who works with video content and needs to quickly understand what's happening or extract specific information without extensive manual review. You input a video file and a natural language question about its content, and it outputs a precise answer. This is ideal for content analysts, researchers studying video data, or media professionals.

158 stars. No commits in the last 6 months.

Use this if you need to automatically answer questions about video content, especially when you have little to no existing labeled data for training.

Not ideal if you only work with text documents or still images, as this tool is specifically designed for video analysis.

video-analysis content-moderation media-intelligence research-data-extraction
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

158

Forks

19

Language

Python

License

Apache-2.0

Last pushed

Dec 09, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/antoyang/FrozenBiLM"

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