AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

MOS: Mitigating Optical-SAR Modality Gap for Cross-Modal Ship Re-Identification

Yujian Zhao, Hankun Liu, Guanglin Niu

CVPR 2026 · Vision-language and multimodal › Cross-modal learning · approach: Multi-modal object re-identification · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add MCRL (SAR denoising + class-wise modality alignment loss) (ablation)TransOSS · HOSS ReID (SAR to Optical)R1: 29.9 -> 40.3Improved
add CDGF (BBDM pseudo-SAR generation and feature fusion) alone (ablation)TransOSS · HOSS ReID (ALL to ALL)R1: 65.9 -> 66.5Improved
add CDGF on top of MCRL (ablation)MOS (MCRL) · HOSS ReID (SAR to Optical)R1: 40.3 -> 46.3Improved
add MCRL on top of CDGF (ablation)MOS (CDGF) · HOSS ReID (ALL to ALL)R1: 66.5 -> 68.8Improved
MOS (MCRL + CDGF) over TransOSSTransOSS · HOSS ReID (Optical to SAR)R1: 33.8 -> 40.0Improved
set SAR denoising percentile alpha and lambda_cmal away from 5.0 and 2.0 (ablation)MOS · HOSS ReID (SAR to Optical)R1Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy