sandipan211/LoCATe-GAT

Official PyTorch implementation of the IEEE TETCI 2024 paper LoCATe-GAT

22
/ 100
Experimental

This project helps video analysts automatically recognize actions in video footage, even if those actions haven't been explicitly seen before. You provide video datasets, and the system outputs accurate classifications of various activities. It's designed for researchers or practitioners working with large video collections who need to identify diverse actions efficiently.

No commits in the last 6 months.

Use this if you need to classify a wide range of actions in videos, including those that are new or rare, without extensive re-training for each new action type.

Not ideal if you're only interested in recognizing a small, fixed set of well-known actions and have abundant training data for them.

video-analysis action-recognition computer-vision multimedia-analytics
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 4 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

7

Forks

Language

Python

License

MIT

Last pushed

Apr 27, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/sandipan211/LoCATe-GAT"

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