Remote sensing (RS) image-text retrieval plays a critical role in understanding massive RS imagery. However, the dense multi-object distribution and complex backgrounds in RS imagery make it difficult to simultaneously achieve fine-grained cross-modal alignment and efficient retrieval. Existing methods either rely on c...
Xi Chen, Xu Chen, Xiamgyang Jia 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
A change-aware remote sensing STF method via frequency decoupling and symmetric gating, termed CA-STF, which achieves superior fusion accuracy and visual quality in complex spatiotemporal dynamics.
Meng Li, Hui-Hui Song, Xu Zhang et al.· IEEE Journal of Selected Top...· 0 citations
AdaDINO is presented, a pair-aware in-backbone adaptation framework that equips a frozen DINO encoder with bi-temporal interaction for efficient change detection and achieves competitive or superior performance against VFM-based baselines.
Xu Zhang, Xinqi Li, Jianpeng Xie et al.· 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.
