kenshohara/video-classification-3d-cnn-pytorch

Video classification tools using 3D ResNet

51
/ 100
Established

This tool helps researchers and analysts automatically categorize actions in video footage. You provide video files as input, and it outputs the detected action categories (e.g., 'running', 'eating') along with confidence scores for segments of the video. It's designed for anyone needing to quickly identify specific actions within large video datasets without manual review.

1,131 stars. No commits in the last 6 months.

Use this if you need to automatically identify and classify actions within video content, such as for behavioral analysis, surveillance, or content moderation.

Not ideal if you need to detect objects or people in still images, or if your primary goal is general video summarization rather than action classification.

video-analysis action-recognition content-moderation behavioral-science surveillance
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

1,131

Forks

257

Language

Python

License

MIT

Last pushed

Nov 23, 2018

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/kenshohara/video-classification-3d-cnn-pytorch"

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