A curated list of state-of-the-art methods, datasets, and resources for Multi-Modal Object Re-Identification (MM-ReID). This repository tracks the latest advancements in utilizing heterogeneous data sources (RGB, IR, Depth, Text, etc.) for robust object retrieval.
- 🌟 Spotlight: Our Contributions
- 📊 Publication Trend Trends
- 📝 Papers & Methods
- 💾 Datasets
- 📈 Star History
- 📚 Citation
- 📧 Contact
Below are selected works from our research group, focusing on advanced token modulation, modality alignment, and prompt learning.
-
[AAAI 2026] STMI: Segmentation-Guided Token Modulation with Cross-Modal Hypergraph Interaction for Multi-Modal Object Re-Identification (Coming Soon)
-
[AAAI 2026] Signal: Selective Interaction and Global-local Alignment for Multi-Modal Object Re-Identification Paper | Code
-
[CVPR 2025] IDEA: Inverted Text with Cooperative Deformable Aggregation for Multi-modal Object Re-Identification Paper | Code
-
[AAAI 2025] DeMo: Decoupled Feature-Based Mixture of Experts for Multi-Modal Object Re-Identification Paper | Code
-
[AAAI 2025] MambaPro: Multi-Modal Object Re-identification with Mamba Aggregation and Synergistic Prompt Paper | Code
-
[CVPR 2024] Magic Tokens: Select Diverse Tokens for Multi-modal Object Re-Identification (EDITOR)
Paper | Code -
[AAAI 2024] TOP-ReID: Multi-spectral Object Re-Identification with Token Permutation Paper | Code
Automatic statistics based on the papers listed in this repository.
| Conference / Journal | Title | Resources |
|---|---|---|
| AAAI 2026 | Signal: Selective Interaction and Global-local Alignment for Multi-Modal Object Re-Identification | Paper Code |
| AAAI 2026 | STMI: Segmentation-Guided Token Modulation with Cross-Modal Hypergraph Interaction for Multi-Modal Object Re-Identification | (Coming Soon) |
| TIFS 2025 | Prototype-Based Diversity and Integrity Learning for All-Day Multi-Modal Person Re-Identification | Paper |
| NeurIPS 2025 | MDReID: Modality-Decoupled Learning for Any-to-Any Multi-Modal Object Re-Identification | Paper Code |
| NeurIPS 2025 | UGG-ReID: Uncertainty-Guided Graph Model for Multi-Modal Object Re-Identification | Paper |
| TIP 2025 | Escaping Modal Interactions: An Efficient DESANet for Multi-Modal Object Re-identification | Paper Code |
| CSCWD 2025 | Lightweight Multi-Branch Feature Complementary Network for Multi-Modal Object Re-Identification (LMCNet) | Paper |
| ICML 2025 | Multi-Modal Object Re-Identification via Sparse Mixture-of-Experts (MFRNet) | Paper Code |
| ArXiv 2025 | NEXT: Multi-Grained Mixture of Experts via Text-Modulation for Multi-Modal Object Re-ID | Paper |
| TMM 2025 | ICPL-ReID: Identity-Conditional Prompt Learning for Multi-Spectral Object Re-Identification | Paper Code |
| ArXiv 2025 | Reliable Multi-Modal Object Re-Identification via Modality-Aware Graph Reasoning (MGRNet) | Paper |
| WACV 2025 | DMPT: Decoupled Modality-Aware Prompt Tuning for Multi-Modal Object Re-Identification | Paper |
| TIP 2025 | Prompt-Based Modality Alignment for Effective Multi-Modal Object Re-Identification | Paper Code |
| ArXiv 2025 | Modality Unified Attack for Omni-Modality Person Re-Identification | Paper |
| TCSVT 2024 | Representation Selective Coupling via Token Sparsification for Multi-Spectral Object Re-Identification (RSCNet) | Paper |
| ESWA 2025 | LRMM: Low rank multi-scale multi-modal fusion for person re-identification based on RGB-NI-TI | Paper |
| Sensors 2024 | MambaReID: Exploiting Vision Mamba for Multi-Modal Object Re-Identification | Paper |
| AAAI 2024 | Heterogeneous Test-Time Training for Multi-Modal Person Re-identifcation (HTT) | Paper Code |
| NeurIPS 2023 | UniCat: Crafting a Stronger Fusion Baseline for Multimodal Re-Identification | Paper Code |
| ArXiv 2023 | GraFT: Gradual Fusion Transformer for Multimodal Re-Identification | Paper Code |
| Conference / Journal | Title | Resources |
|---|---|---|
| TNNLS 2025 | TIENet: A Tri-Interaction Enhancement Network for Multimodal Person Reidentification | Paper |
| MLCCIM 2023 | Multimodal Consistency Co-Assisted Training for Person Re-Identification (MMCF) | Paper |
| ICSP 2023 | Low-rank Fusion Network for Multi-modality Person Re-identification (LRFNet) | Paper |
| TNNLS 2023 | Dynamic Enhancement Network for Partial Multi-modality Person Re-identification (DENet) | Paper |
| AAAI 2022 | Interact, Embed, and EnlargE: Boosting Modality-Specific Representations for Multi-Modal Person Re-identification | Paper Code |
| AAAI 2021 | Robust Multi-Modality Person Re-identification (PFNet) | Paper |
| Conference / Journal | Title | Resources |
|---|---|---|
| IEEE Access 2025 | Swin Transformer With Late-Fusion Feature Aggregation for Multi-Modal Vehicle Reidentification | Paper |
| ArXiv 2025 | Collaborative Enhancement Network for Low-quality Multi-spectral Vehicle Re-identification (CoEN) | Paper Code |
| Applied Intelligence 2025 | Generalizable Multi-spectral Vehicle Re-identification via Decoupled Subspaces | Paper |
| ESWA 2025 | Depth-driven Window-oriented Token Selection and Fusion for multi-modality vehicle re-identification (WTSF-ReID) | Paper Code |
| Inform Fusion 2024 | Flare-aware cross-modal enhancement network for multi-spectral vehicle Re-identification (FACENet) | Paper Code |
| Sensors 2023 | Progressively Hybrid Transformer for Multi-Modal Vehicle Re-Identification (PHT) | Paper |
| TITS 2023 | Graph-based progressive fusion network for multi-modality vehicle re-identification (GPFNet) | Paper |
| Inform Fusion 2022 | Multi-spectral Vehicle Re-identification with Cross-directional Consistency Network (CCNet) | Paper Code |
| ICSP 2022 | Generative and attentive fusion for multi-spectral vehicle re-identification (GAFNet) | Paper |
| AAAI 2020 | Multi-Spectral Vehicle Re-Identification: A Challenge (HAMNet) | Paper Code |
| Dataset | Modalities | Download | Access Code |
|---|---|---|---|
| RGBNT201 | RGB + NIR + TIR | Google Drive | - |
| Market1501-MM | RGB + NIR + TIR | Google Drive | - |
| Dataset | Modalities | Download | Access Code |
|---|---|---|---|
| RGBNT100 | RGB + NIR + TIR | Baidu Pan | rjin |
| RGBNT300 | RGB + NIR | Baidu Pan | 11y8 |
| MSVR310 | RGB + NIR + TIR | Google Drive | - |
| MSVWild863 | RGB + NIR + TIR | Link | msvw |
We express our sincere gratitude to the academic community and all researchers contributing to the advancement of Multi-Modal Object Re-Identification.
We welcome questions, suggestions, and collaborations. Please feel free to reach out:
- Email: [email protected]
- Homepage: 924973292.github.io
If you find our work or this repository useful in your research, please consider citing:
Click to expand BibTeX
@inproceedings{wang2024top,
title={TOP-ReID: Multi-spectral Object Re-Identification with Token Permutation},
author={Wang, Yuhao and Liu, Xuehu and Zhang, Pingping and Lu, Hu and Tu, Zhengzheng and Lu, Huchuan},
booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
volume={38},
number={6},
pages={5758--5766},
year={2024}
}
@InProceedings{Zhang_2024_CVPR,
author = {Zhang, Pingping and Wang, Yuhao and Liu, Yang and Tu, Zhengzheng and Lu, Huchuan},
title = {Magic Tokens: Select Diverse Tokens for Multi-modal Object Re-Identification},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2024},
pages = {17117-17126}
}
@inproceedings{wang2025decoupled,
title={Decoupled feature-based mixture of experts for multi-modal object re-identification},
author={Wang, Yuhao and Liu, Yang and Zheng, Aihua and Zhang, Pingping},
booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
volume={39},
number={8},
pages={8141--8149},
year={2025}
}
@inproceedings{wang2025mambapro,
title={Mambapro: Multi-modal object re-identification with mamba aggregation and synergistic prompt},
author={Wang, Yuhao and Liu, Xuehu and Yan, Tianyu and Liu, Yang and Zheng, Aihua and Zhang, Pingping and Lu, Huchuan},
booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
volume={39},
number={8},
pages={8150--8158},
year={2025}
}
@article{wang2025idea,
title={IDEA: Inverted Text with Cooperative Deformable Aggregation for Multi-modal Object Re-Identification},
author={Wang, Yuhao and Lv, Yongfeng and Zhang, Pingping and Lu, Huchuan},
journal={arXiv preprint arXiv:2503.10324},
year={2025}
}