STMI: Segmentation-Guided Token Modulation with Cross-Modal Hypergraph Interaction for Multi-Modal Object Re-Identification

Multi-modal object Re-Identification (ReID) aims to exploit complementary information from different modalities to retrieve specific objects. However, existing methods often rely on hard token filtering or simple fusion strategies, which can lead to the loss of discriminative cues and increased background interference. To address these challenges, we propose STMI, a novel multi-modal learning framework consisting of three key components: (1) Segmentation-Guided Feature Modulation (SFM) module leverages SAM-generated masks to enhance foreground representations and suppress background noise through learnable attention modulation; (2) Semantic Token Reallocation (STR) module employs learnable query tokens and an adaptive reallocation mechanism to extract compact and informative representations without discarding any tokens; (3) Cross-Modal Hypergraph Interaction (CHI) module constructs a unified hypergraph across modalities to capture high-order semantic relationships. Extensive experiments on public benchmarks (i.e., RGBNT201, RGBNT100, and MSVR310) demonstrate the effectiveness and robustness of our proposed STMI framework in multi-modal ReID scenarios.

Authors

• Xingguo Xu School of Mathematical Sciences, Dalian University of Technology, China
• Zhanyu Liu School of Mathematical Sciences, Dalian University of Technology, China
• Weixiang Zhou School of Mathematical Sciences, Dalian University of Technology, China
• Yuansheng Gao College of Computer Science and Technology, Zhejiang University, China
• Junjie Cao School of Mathematical Sciences, Dalian University of Technology, China
• Yuhao Wang Dalian University of Technology
• Jixiang Luo Institute of Artificial Intelligence (TeleAI), China Telecom, China
• Dell Zhang

Keywords

No keywords are indexed for this paper.