suyukun666/UFO

Official PyTorch implementation of the “A Unified Transformer Framework for Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection”. (TMM2023)

46
/ 100
Emerging

This framework helps computer vision researchers and practitioners efficiently identify and segment common objects across multiple images or within video sequences. You input a group of related images or a video, and it outputs precise masks highlighting the shared or salient objects. It's ideal for those working on tasks like identifying recurring products in an advertising campaign or tracking specific objects in surveillance footage.

302 stars. No commits in the last 6 months.

Use this if you need a unified tool to perform co-segmentation, co-saliency detection, or video salient object detection with a consistent approach.

Not ideal if your primary goal is single object tracking or complex video inpainting, as these functionalities are optional or not fully developed.

computer-vision image-segmentation video-analysis object-detection visual-content-analysis
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

302

Forks

50

Language

Python

License

MIT

Last pushed

Apr 02, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/suyukun666/UFO"

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