Author name: Miaojing Shi, Jun Huang, Zijie Yue, Hanli Wang

arXiv:2604.17797v2 Announce Type: replace
Abstract: Referring video object segmentation (RVOS) aims to segment the target instance in a video, referred by a text expression. Conventional approaches are mostly supervised learning, requiring expensive p…

arXiv:2604.17797v1 Announce Type: new
Abstract: Referring video object segmentation (RVOS) aims to segment the target instance in a video, referred by a text expression. Conventional approaches are mostly supervised learning, requiring expensive pixel…