首页|期刊导航|Computational Visual Media|Open-vocabulary camouflaged object segmentation with cascaded vision language models

Open-vocabulary camouflaged object segmentation with cascaded vision language models

Kai Zhao Wubang Yuan Zheng Wang Guanyi Li Xiaoqiang Zhu Deng-Ping Fan Dan Zeng

Computational Visual Media2026，Vol.12Issue(2)：P.473-492,20.

Computational Visual Media2026，Vol.12Issue(2)：P.473-492,20.DOI:10.26599/CVM.2025.9450512

Open-vocabulary camouflaged object segmentation with cascaded vision language models

Kai Zhao ¹Wubang Yuan ¹Zheng Wang ¹Guanyi Li ¹Xiaoqiang Zhu ¹Deng-Ping Fan ²Dan Zeng¹

作者信息

1. School of Communication and Information Engineering,Shanghai University,Shanghai 200444,China
2. Nankai International Advanced Research Institute(Shenzhen Futian),Shenzhen 518045,China,and VCIP,and CS Department,Nankai University,Tianjin 300071,China
折叠

摘要

关键词

open-vocabulary segmentation/camouflaged objects/vision-language models(VLMs)/CLIP/segment anything model(SAM)

分类

信息技术与安全科学

引用本文复制引用

Kai Zhao,Wubang Yuan,Zheng Wang,Guanyi Li,Xiaoqiang Zhu,Deng-Ping Fan,Dan Zeng..Open-vocabulary camouflaged object segmentation with cascaded vision language models[J].Computational Visual Media,2026,12(2):P.473-492,20.

基金项目

partially supported by the National Natural Science Foundation of China(62372284,62476143) （62372284,62476143）

the National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing(TJ-02-22-01) （TJ-02-22-01）

the Pioneer R&D Program of Zhejiang Province(2024C01024). （2024C01024）

Computational Visual Media

ISSN：2096-0433

访问量0

下载量0

段落导航