sauradip/DiffusionTAD

[ICCV 2023] Official PyTorch implementation of the paper "DiffTAD: Temporal Action Detection with Proposal Denoising Diffusion"

15
/ 100
Experimental

This project helps video analysts and researchers automatically pinpoint specific actions within long, untrimmed video footage. It takes an untrimmed video as input and outputs precise start and end times for actions detected within that video. This is ideal for professionals working with large volumes of video data who need to identify events efficiently.

No commits in the last 6 months.

Use this if you need to accurately detect and localize specific actions or events within lengthy video recordings.

Not ideal if your primary need is image classification or object detection in still images rather than temporal analysis in videos.

video-analysis action-recognition video-indexing event-detection multimedia-processing
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 0 / 25

How are scores calculated?

Stars

37

Forks

Language

License

Last pushed

Mar 30, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/sauradip/DiffusionTAD"

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