2 papers
cs.CV2026
ViCo-SAM3: Vision-Conditioned Alignment for Open-Vocabulary Camouflaged Object Segmentation
Qiangqiang Zhou, Wenjun Tang, Yong Chen +2
Open-vocabulary camouflaged object segmentation (OVCOS) aims to segment unseen camouflaged objects under text guidance. We observe that SAM3 still suffers from a pronounced semanti…
cs.CV2026
DifferSeg: Towards Diverse Multimodal Binary Segmentation via Differential Perception and Frequency Guidance
Qiangqiang Zhou, Jiawei Xu, Yong Chen +3
In many binary segmentation tasks, most multimodal methods rely on fixed feature concatenation for cross-modal interaction and straightforward decoder designs dominated by low-freq…