[
    {
        "id": "osp-18119",
        "type": "article-journal",
        "title": "TRIM-ReID: Duplication-Aware Token Reduction and Modality-Aligned Interaction for Multi-Modal Object Re-Identification",
        "author": [
            {
                "family": "Xia",
                "given": "Wanke"
            },
            {
                "family": "Zhu",
                "given": "Ruiding"
            },
            {
                "family": "Xu",
                "given": "Xingguo"
            },
            {
                "family": "Zhang",
                "given": "Zhengbo"
            },
            {
                "family": "Liu",
                "given": "Dongxia"
            },
            {
                "family": "Jin",
                "given": "Yuan"
            },
            {
                "family": "Zhu",
                "given": "Taojie"
            },
            {
                "family": "Zhao",
                "given": "Yiting"
            },
            {
                "family": "Ding",
                "given": "Yihang"
            }
        ],
        "URL": "https://omanscience.com/ar/articles/trim-reid-duplication-aware-token-reduction-and-modality-aligned-interaction-for-multi-modal-object-re-identification",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "abstract": "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."
    }
]