Nuclei instance segmentation is fundamental to quantitative pathology. Yet high-accuracy methods mostly build on large vision transformers (ViTs) or heavy convolutional backbones, whose parameter count and compute cost hinder deployment in clinical and edge settings. We present NucShare, a lightweight model whose share...
Wen-Yang Li, Xiang-Yang Jia, Wen-Long Zhong et al.· 0 citations
Cross-modal hashing enables efficient retrieval by encoding heterogeneous data into compact binary codes. Recent methods exploit fine-grained relations encoded in multi-label training structure, yet none of them constrains how those relations survive as consistent candidate rankings in finite, multi-length Hamming spac...
Xi Chen, Xu Chen, Xiang-Yang Jia et al.· 1 citation
Text-video retrieval, which aims to bridge visual and textual modalities by learning a joint embedding space, has become a crucial task in multimodal intelligence. Despite extensive efforts to mitigate visual redundancy, previous methods typically rely on a single-aspect criterion to assess visual importance, overlooki...
Shu-Quan Wei, Xi Chen, Xu Chen et al.· arXiv.org· 0 citations
DARAD is proposed, a dual-adapter and ranking-aware distillation framework that preserves the historical cross-modal ranking structure while learning new visual and textual concepts from evolving archives to address the challenge of continual RS-ITR.
Xi Chen, Xu Chen, Xiang-Yang Jia et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.