YuqingWang1029/VisTR

[CVPR2021 Oral] End-to-End Video Instance Segmentation with Transformers

46
/ 100
Emerging

This project helps computer vision researchers and developers analyze videos by automatically identifying and outlining every distinct object across multiple frames. You provide video frames and their corresponding annotations, and it outputs a JSON file with instance segmentation results, specifying what each object is and where it is located in each frame. This is primarily for those working on advanced video analysis systems.

757 stars. No commits in the last 6 months.

Use this if you need to precisely track and segment individual objects throughout an entire video, such as for advanced behavior analysis or autonomous system perception.

Not ideal if you only need to detect static objects in single images or perform general object classification without detailed instance tracking across frames.

video-analysis object-tracking computer-vision motion-analysis instance-segmentation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

757

Forks

98

Language

Python

License

Apache-2.0

Last pushed

Jul 15, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/YuqingWang1029/VisTR"

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