# TRIM-ReID: Duplication-Aware Token Reduction and Modality-Aligned Interaction for Multi-Modal Object Re-Identification

arXiv: https://arxiv.org/abs/2610.04361 · HTML: https://mlsanity.com/paper/2610.04361/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 16 references that are in the map.
- First posted on arXiv 3 Oct 2026.

## Builds on (most cited first, 12 of 12)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [Stop Looking for Important Tokens in Multimodal Language Models: Duplication Matters More](https://mlsanity.com/paper/2502.11494/) (2025)
- [Magic Tokens: Select Diverse Tokens for Multi-modal Object Re-Identification](https://mlsanity.com/paper/2403.10254/) (2024)
- [TOP-ReID: Multi-spectral Object Re-Identification with Token Permutation](https://mlsanity.com/paper/2312.09612/) (2023)
- [IDEA: Inverted Text with Cooperative Deformable Aggregation for Multi-modal Object Re-Identification](https://mlsanity.com/paper/2503.10324/) (2025)
- [A TRIANGLE Enables Multimodal Alignment Beyond Cosine Similarity](https://mlsanity.com/paper/2509.24734/) (2025)
- [NEXT: Multi-Grained Mixture of Experts via Text-Modulation for Multi-Modal Object Re-Identification](https://mlsanity.com/paper/2505.20001/) (2025)
- [Signal: Selective Interaction and Global-local Alignment for Multi-Modal Object Re-Identification](https://mlsanity.com/paper/2511.17965/) (2025)
- [IDPruner: Harmonizing Importance and Diversity in Visual Token Pruning for MLLMs](https://mlsanity.com/paper/2602.13315/) (2026)
- [UGG-ReID: Uncertainty-Guided Graph Model for Multi-Modal Object Re-Identification](https://mlsanity.com/paper/2507.04638/) (2025)
- [STMI: Segmentation-Guided Token Modulation with Cross-Modal Hypergraph Interaction for Multi-Modal Object Re-Identification](https://mlsanity.com/paper/2603.00695/) (2026)

## Abstract (arXiv)

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.