sauradip/fewshotQAT

[BMVC 2021]: Official PyTorch implementation of : "Few Shot Temporal Action Localization using Query Adaptive Transformers"

26
/ 100
Experimental

This tool helps video analysts and researchers quickly identify specific actions within long, untrimmed videos, even with very few example videos to learn from. You provide a small set of videos demonstrating the action you're looking for, and it pinpoints where and when that action occurs in much larger video collections. This is ideal for those studying human behavior, sports, or surveillance footage with limited labeled data.

No commits in the last 6 months.

Use this if you need to find specific actions in video footage but have very few labeled examples, especially when dealing with long, unedited videos.

Not ideal if you have extensive, precisely annotated datasets for your actions, as this tool is designed for 'few-shot' learning scenarios.

video-analysis action-recognition behavior-analysis sports-analytics security-footage
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 12 / 25

How are scores calculated?

Stars

20

Forks

3

Language

Python

License

Last pushed

Jul 12, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/sauradip/fewshotQAT"

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