# Modality-Transition Representation Learning for Visible-Infrared Person Re-Identification arXiv: https://arxiv.org/abs/2511.02685 ยท HTML: https://mlsanity.com/paper/2511.02685/ ## Key facts - Cited by 6 papers in the map (data through 14 Oct 2026). - Builds on 30 of its 53 references that are in the map. - First posted on arXiv 4 Nov 2025. ## Builds on (most cited first, 30 of 30) - [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020) - [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021) - [Palette: Image-to-Image Diffusion Models](https://mlsanity.com/paper/2111.05826/) (2021) - [Deep Learning for Person Re-identification: A Survey and Outlook](https://mlsanity.com/paper/2001.04193/) (2020) - [TransReID: Transformer-based Object Re-Identification](https://mlsanity.com/paper/2102.04378/) (2021) - [Re-ranking Person Re-identification with k-reciprocal Encoding](https://mlsanity.com/paper/1701.08398/) (2017) - [UNIT-DDPM: UNpaired Image Translation with Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2104.05358/) (2021) - [Dynamic Dual-Attentive Aggregation Learning for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2007.09314/) (2020) - [Visible-Thermal UAV Tracking: A Large-Scale Benchmark and New Baseline](https://mlsanity.com/paper/2204.04120/) (2022) - [Cross-modality Person re-identification with Shared-Specific Feature Transfer](https://mlsanity.com/paper/2002.12489/) (2020) - [Diverse Embedding Expansion Network and Low-Light Cross-Modality Benchmark for Visible-Infrared Person Re-identification](https://mlsanity.com/paper/2303.14481/) (2023) - [Neural Feature Search for RGB-Infrared Person Re-Identification](https://mlsanity.com/paper/2104.02366/) (2021) - [Shape-Erased Feature Learning for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2304.04205/) (2023) - [UnrealPerson: An Adaptive Pipeline towards Costless Person Re-identification](https://mlsanity.com/paper/2012.04268/) (2020) - [Dynamic Prototype Mask for Occluded Person Re-Identification](https://mlsanity.com/paper/2207.09046/) (2022) - [Modality Unifying Network for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2309.06262/) (2023) - [Modality-Adaptive Mixup and Invariant Decomposition for RGB-Infrared Person Re-Identification](https://mlsanity.com/paper/2203.01735/) (2022) - [Implicit Discriminative Knowledge Learning for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2403.11708/) (2024) - [PartMix: Regularization Strategy to Learn Part Discovery for Visible-Infrared Person Re-identification](https://mlsanity.com/paper/2304.01537/) (2023) - [From Poses to Identity: Training-Free Person Re-Identification via Feature Centralization](https://mlsanity.com/paper/2503.00938/) (2025) - [CMTR: Cross-modality Transformer for Visible-infrared Person Re-identification](https://mlsanity.com/paper/2110.08994/) (2021) - [IR2VI: Enhanced Night Environmental Perception by Unsupervised Thermal Image Translation](https://mlsanity.com/paper/1806.09565/) (2018) - [I2V-GAN: Unpaired Infrared-to-Visible Video Translation](https://mlsanity.com/paper/2108.00913/) (2021) - [Unpaired Thermal to Visible Spectrum Transfer using Adversarial Training](https://mlsanity.com/paper/1904.02242/) (2019) - [Denoising Diffusion Probabilistic Models in Six Simple Steps](https://mlsanity.com/paper/2402.04384/) (2024) - [Identity-aware Feature Decoupling Learning for Clothing-change Person Re-identification](https://mlsanity.com/paper/2501.05851/) (2025) - [Adaptive Generation of Privileged Intermediate Information for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2307.03240/) (2023) - [CCUP: A Controllable Synthetic Data Generation Pipeline for Pretraining Cloth-Changing Person Re-Identification Models](https://mlsanity.com/paper/2410.13567/) (2024) - [Neighbor-Based Feature and Index Enhancement for Person Re-Identification](https://mlsanity.com/paper/2504.11798/) (2025) - [Try Harder: Hard Sample Generation and Learning for Clothes-Changing Person Re-ID](https://mlsanity.com/paper/2507.11119/) (2025) ## Built on by (most cited first, 6 of 6) - [When Shared Knowledge Hurts: Spectral Over-Accumulation in Model Merging](https://mlsanity.com/paper/2602.05536/) (2026) - [BIT: Matching-based Bi-directional Interaction Transformation Network for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2603.14243/) (2026) - [Towards Robust Text-to-Image Person Retrieval: Multi-View Reformulation for Semantic Compensation](https://mlsanity.com/paper/2604.18376/) (2026) - [OmniPerson: Unified Identity-Preserving Pedestrian Generation](https://mlsanity.com/paper/2512.02554/) (2025) - [CMCC-ReID: Cross-Modality Clothing-Change Person Re-Identification](https://mlsanity.com/paper/2604.02808/) (2026) - [Dual-Space Modality Consistency Learning for Universal Cross-Modal Re-Identification](https://mlsanity.com/paper/2608.06943/) (2026) ## Abstract (arXiv) Visible-infrared person re-identification (VI-ReID) technique could associate the pedestrian images across visible and infrared modalities in the practical scenarios of background illumination changes. However, a substantial gap inherently exists between these two modalities. Besides, existing methods primarily rely on intermediate representations to align cross-modal features of the same person. The intermediate feature representations are usually create by generating intermediate images (kind of data enhancement), or fusing intermediate features (more parameters, lack of interpretability), and they do not make good use of the intermediate features. Thus, we propose a novel VI-ReID framework via Modality-Transition Representation Learning (MTRL) with a middle generated image as a transmitter from visible to infrared modals, which are fully aligned with the original visible images and similar to the infrared modality. After that, using a modality-transition contrastive loss and a modality-query regularization loss for training, which could align the cross-modal features more effectively. Notably, our proposed framework does not need any additional parameters, which achieves the same inference speed to the backbone while improving its performance on VI-ReID task. Extensive experimental results illustrate that our model significantly and consistently outperforms existing SOTAs on three typical VI-ReID datasets.