Sh-31/Group-Activity-Recognition

A modern implementation of CVPR 2016 paper: "A Hierarchical Deep Temporal Model for Group Activity Recognition."

22
/ 100
Experimental

This tool analyzes video footage to automatically identify and classify complex group activities and individual player actions, initially trained on volleyball games. It takes video frames as input and outputs labels for actions like "Left Spike" or "Player Digging." Sports analysts, coaches, and researchers in human behavior would find this useful for detailed activity logging and performance analysis.

No commits in the last 6 months.

Use this if you need to automatically recognize and label specific group activities and individual actions within video footage for detailed analysis.

Not ideal if you require real-time recognition for live applications or if your primary focus is on object detection rather than activity classification.

sports-analytics coaching behavioral-science video-analysis performance-tracking
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

15

Forks

Language

Python

License

BSD-2-Clause

Last pushed

Feb 24, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Sh-31/Group-Activity-Recognition"

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