admin管理员组

文章数量:1529464

abstract

Referring video object segmentation (R-VOS) is an emerging cross-modal task that aims to segment the target object referred by a language expression in all video frames.
In this work, we propose a simple and unified framework built upon Transformer, termed ReferFormer.
It views the language as queries and directly attends to the most relevant regions in the video frames.
Concretely, we introduce a small set of object queries conditioned on the language as the input to the Transformer.
In this manner, all the queries are obligated to find the referred objects only.
They are eventually transformed into

本文标签： 对象论文视频QueriesVideo

版权声明：本文标题：[读论文]-Language as Queries for Referring Video Object Segmentation（R-VOS）有参考视频对象分割 内容由热心网友自发贡献，该文观点仅代表作者本人， 转载请联系作者并注明出处：https://m.elefans.com/xitong/1726616839a1078283.html， 本站仅提供信息存储空间服务，不拥有所有权，不承担相关法律责任。如发现本站有涉嫌抄袭侵权/违法违规的内容，一经查实，本站将立刻删除。