https://github.com/skyworkai/daq-vs
Code For Our Work: DVIS-DAQ: Improving Video Segmentation via Dynamic Anchor Queries [ECCV-2024]
https://github.com/skyworkai/daq-vs
Last synced: 3 months ago
JSON representation
Code For Our Work: DVIS-DAQ: Improving Video Segmentation via Dynamic Anchor Queries [ECCV-2024]
- Host: GitHub
- URL: https://github.com/skyworkai/daq-vs
- Owner: SkyworkAI
- Created: 2024-03-21T09:03:38.000Z (about 1 year ago)
- Default Branch: main
- Last Pushed: 2024-07-11T04:04:43.000Z (11 months ago)
- Last Synced: 2025-01-15T12:14:07.801Z (5 months ago)
- Homepage:
- Size: 4.88 KB
- Stars: 14
- Watchers: 6
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# [DVIS-DAQ: Improving Video Segmentation via Dynamic Anchor Queries](https://arxiv.org/pdf/2404.00086.pdf)
Yikang Zhou, Tao Zhang, Shunping Ji, Shuicheng Yan, Xiangtai Li
**Project Page: [https://zhang-tao-whu.github.io/projects/DVIS_DAQ](https://zhang-tao-whu.github.io/projects/DVIS_DAQ/)**
## News
- This work is accepted by ECCV-2024.
## TODO
- Release the code and pre-trained weights.
## Features
- We propose Dynamic Anchor Queries and Emergence and Disappearance Simulation to significantly enhance the ability to handle the emergence and disappearance of objects.
- The Dynamic Anchor Queries and Emergence and Disappearance Simulation proposed by us can be easily integrated into existing query-based video segmentation methods.
- By integrating with DVIS, we constructed DVIS-DAQ and achieved SOTA performance on YTVIS 19/21/22 and VIPSeg, with performance reaching as high as **57.1 AP** on OVIS.
## Demos
We provide visualization results for multiple challenging cases on the [project page](https://zhang-tao-whu.github.io/projects/DVIS_DAQ/).
```BibTeX
@article{dvisdaq,
title={DVIS-DAQ: Improving Video Segmentation via Dynamic Anchor Queries},
author={Yikang Zhou and Tao Zhang and Shunping Ji and Shuicheng Yan and Xiangtai Li},
journal={ECCV},
year={2024},
}
```