yassersouri/MuCon

Official Implementation for "Fast Weakly Supervised Action Segmentation Using Mutual Consistency" - TPAMI 2021

30
/ 100
Emerging

This tool helps researchers and practitioners in video analysis automatically break down long, unlabelled videos of human actions into distinct, meaningful segments. You provide a video dataset (like the Breakfast dataset with I3D features), and it outputs metrics on how well the video was segmented into individual actions, even with minimal human input. It's designed for someone working on understanding complex human activities from video footage.

No commits in the last 6 months.

Use this if you need to quickly and efficiently segment human actions in video datasets without extensive manual annotation.

Not ideal if your primary goal is real-time video processing or if you require fine-grained, frame-level action recognition rather than broader segmentation.

video-analysis action-segmentation human-activity-recognition unsupervised-learning behavioral-science
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 8 / 25

How are scores calculated?

Stars

21

Forks

2

Language

Python

License

Last pushed

Aug 30, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/yassersouri/MuCon"

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