الملخص
Multi-modal object re-identification exploits complementary RGB, near-infrared (NIR), and thermal-infrared (TIR) observations to retrieve target objects. However, existing methods commonly employ visual encoders optimized for global image-text alignment and select tokens using learned importance scores. Such designs fail to preserve fine-grained identity cues or explicitly account for token redundancy, resulting in underrepresented local evidence and duplicated tokens that lead to noisy and costly cross-modal interaction. To address this gap, we propose TRIM-ReID, a compact framework that unifies dense feature extraction, intra-modal token reduction, and inter-modal aligned interaction. Specifically, semantically rich and spatially coherent patch features are extracted by Dense Identity Representation (DIR), which leverages DINOv3 to preserve fine-grained identity information. We then introduce Token Diversity Mining (TDM) to identify complementary local evidence and construct compact modality-specific token sets by suppressing repetitive patches while preserving informative diversity. Retained tokens are subsequently fused by Modal Relational Interaction (MRI) to enable effective information exchange across modalities, while a triangular alignment loss explicitly regularizes their joint relationships to maintain cross-modal semantic consistency under independent token selection. Extensive experiments on RGBNT201, RGBNT100, and MSVR310 demonstrate that TRIM-ReID achieves state-of-the-art performance.
الكلمات المفتاحية
الموضوع
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Xia, W., Zhu, R., Xu, X., Zhang, Z., Liu, D., Jin, Y., Zhu, T., Zhao, Y., & Ding, Y. (2026). TRIM-ReID: Duplication-Aware Token Reduction and Modality-Aligned Interaction for Multi-Modal Object Re-Identification. https://omanscience.com/ar/articles/trim-reid-duplication-aware-token-reduction-and-modality-aligned-interaction-for-multi-modal-object-re-identification
MLA 9
Xia, Wanke, et al. "TRIM-ReID: Duplication-Aware Token Reduction and Modality-Aligned Interaction for Multi-Modal Object Re-Identification." https://omanscience.com/ar/articles/trim-reid-duplication-aware-token-reduction-and-modality-aligned-interaction-for-multi-modal-object-re-identification.
شيكاغو (المؤلف–التاريخ)
Xia, Wanke, Ruiding Zhu, Xingguo Xu, Zhengbo Zhang, Dongxia Liu, Yuan Jin, Taojie Zhu, Yiting Zhao, and Yihang Ding. 2026. "TRIM-ReID: Duplication-Aware Token Reduction and Modality-Aligned Interaction for Multi-Modal Object Re-Identification." https://omanscience.com/ar/articles/trim-reid-duplication-aware-token-reduction-and-modality-aligned-interaction-for-multi-modal-object-re-identification.
هارفارد
Xia, W., Zhu, R., Xu, X., Zhang, Z., Liu, D., Jin, Y., Zhu, T., Zhao, Y. and Ding, Y. (2026) 'TRIM-ReID: Duplication-Aware Token Reduction and Modality-Aligned Interaction for Multi-Modal Object Re-Identification', Available at: https://omanscience.com/ar/articles/trim-reid-duplication-aware-token-reduction-and-modality-aligned-interaction-for-multi-modal-object-re-identification.
فانكوفر
Xia W, Zhu R, Xu X, Zhang Z, Liu D, Jin Y, et al. TRIM-ReID: Duplication-Aware Token Reduction and Modality-Aligned Interaction for Multi-Modal Object Re-Identification. https://omanscience.com/ar/articles/trim-reid-duplication-aware-token-reduction-and-modality-aligned-interaction-for-multi-modal-object-re-identification
IEEE
W. Xia, R. Zhu, X. Xu, Z. Zhang, D. Liu, Y. Jin, T. Zhu, Y. Zhao, and Y. Ding, "TRIM-ReID: Duplication-Aware Token Reduction and Modality-Aligned Interaction for Multi-Modal Object Re-Identification," https://omanscience.com/ar/articles/trim-reid-duplication-aware-token-reduction-and-modality-aligned-interaction-for-multi-modal-object-re-identification.