Tube-Link: A Flexible Cross Tube Framework for Universal Video Segmentation

Video segmentation aims to segment and track every pixel in diverse scenarios accurately. This paper presents Tube-Link, a versatile framework that addresses multiple core tasks of video segmentation with a unified architecture.

Data and Resources

Cite this as

Guangliang Cheng, Xiangtai Li, Haobo Yuan, Wenwei Zhang, Jiangmiao Pang, Chen Change Loy (2024). Dataset: Tube-Link: A Flexible Cross Tube Framework for Universal Video Segmentation. https://doi.org/10.57702/y2thy9t3

DOI retrieved: December 2, 2024

Additional Info

Field Value
Created December 2, 2024
Last update December 2, 2024
Defined In https://doi.org/10.48550/arXiv.2303.12782
Author Guangliang Cheng
More Authors
Xiangtai Li
Haobo Yuan
Wenwei Zhang
Jiangmiao Pang
Chen Change Loy
Homepage https://github.com/lxtGH/Tube-Link