CMCC-ReID: Cross-Modality Clothing-Change Person Re-Identification

Haoxuan Xu; Hanzi Wang; Guanglin Niu

cs.CVApr 3, 2026

CMCC-ReID: Cross-Modality Clothing-Change Person Re-Identification

Authors: Haoxuan Xu, Hanzi Wang, Guanglin Niu

Organizations: School of Artificial Intelligence, Beihang University, Beijing, China · School of Informatics, Xiamen University, Xiamen, Fujian, China

Abstract

Person Re-Identification (ReID) faces severe challenges from modality discrepancy and clothing variation in long-term surveillance scenario. While existing studies have made significant progress in either Visible-Infrared ReID (VI-ReID) or Clothing-Change ReID (CC-ReID), real-world surveillance system often face both challenges simultaneously. To address this overlooked yet realistic problem, we define a new task, termed Cross-Modality Clothing-Change Re-Identification (CMCC-ReID), which targets pedestrian matching across variations in both modality and clothing. To advance research in this direction, we construct a new benchmark SYSU-CMCC, where each identity is captured in both visible and infrared domains with distinct outfits, reflecting the dual heterogeneity of long-term surveillance. To tackle CMCC-ReID, we propose a Progressive Identity Alignment Network (PIA) that progressively mitigates the issues of clothing variation and modality discrepancy. Specifically, a Dual-Branch Disentangling Learning (DBDL) module separates identity-related cues from clothing-related factors to achieve clothing-agnostic representation, and a Bi-Directional Prototype Learning (BPL) module performs intra-modality and inter-modality contrast in the embedding space to bridge the modality gap while further suppressing clothing interference. Extensive experiments on the SYSU-CMCC dataset demonstrate that PIA establishes a strong baseline for this new task and significantly outperforms existing methods.

Figures & tables

Figure 1: Motivation of CMCC-ReID. In the long-term surveillance scenarios, two critical issues ( i.e. , modality discrepancy and clothing variation) are not mutually exclusive but coexist. This observation motivates the CMCC-ReID task, which targets pedestrian matching across both modality and clothing changes.

Figure 2: Illustration of the key issues in CMCC-ReID. (a) In the visible modality, the high contrast enables CAL to produce a heatmap with suppressed clothing cues. (b) In the infrared modality, low contrast causes CAL to generate a heatmap dominated by clothing information. (c) Comparison between SAAI and its ResNet-50 baseline shows that direct modality alignment may even degrade performance under clothing variation. (d) Integrating SAAI into CAL yields moderate improvements once clothing interference is mitigated.

Figure 3: Cross-dataset verification protocol for SYSU-CMCC construction. Samples from PRCC camA/B and SYSU-MM01 cam1/2 serve as identity anchors due to their identical content. For remaining samples (PRCC camC and SYSU-MM01 cam3/6), manual verification is performed: inconsistent samples are marked with red bounding boxes and discarded, while consistent samples are highlighted with green bounding boxes and retained to form the SYSU-CMCC dataset.

Dataset	Clothing-change	Cross-modality	IDs	Images	Cameras
PRCC [ 55 ]	✔	✗	221	33,698	3
LTCC [ 37 ]	✔	✗	152	17,138	12
RegDB [ 35 ]	✗	✔	412	8240	2
SYSU-MM01 [ 47 ]	✗	✔	491	38,271	6
SYSU-CMCC	✔	✔	214	18,375	3

Table 1: Statistical comparisons between the SYSU-CMCC dataset with existing CC-ReID and VI-ReID datasets.

Figure 4: Overview of PIA, which consists of two key components: a Dual-Branch Disentanglement Learning (DBDL) module for clothing-invariant feature extraction in both modalities, and a Bi-Directional Prototype Learning (BPL) module for cross-modality identity alignment. Through progressive optimization, PIA achieves robust and modality-consistent identity representation.

Type	Method	SYSU-CMCC
		Visible to Infrared				Infrared to Visible
		R-1	R-10	R-20	mAP	R-1	R-10	R-20	mAP
VI-ReID	DDAG [ 58 ]	18.3	52.1	54.7	19.6	16.8	49.7	54.6	17.2
	CAJ [ 57 ]	21.5	53.4	56.9	20.7	19.8	50.6	56.2	19.6
	MPANet [ 49 ]	19.8	51.2	55.5	19.9	18.4	51.1	57.8	19.0
	PMT [ 32 ]	18.6	50.8	57.4	19.2	17.9	52.5	58.7	18.9

Table 2: Comparison with state-of-the-art VI-ReID and CC-ReID methods on the SYSU-CMCC dataset. The best and second-best results are highlighted in bold and underlined.

Index	Baseline	DBDL	$\mathcal{L}_{orth}$	Progressive	BPL		V2I		I2V
Index	Baseline	DBDL	$\mathcal{L}_{orth}$	Progressive	$\mathcal{L}_{intra}$	$\mathcal{L}_{inter}$	R-1	mAP	R-1	mAP
1	✔	✗	✗	✗	✗	✗	40.1	33.2	35.6	37.1
2	✔	✔	✗	✗	✗	✗	43.2	35.7	38.6	38.7
3	✔	✔	✔	✗	✗	✗	45.6	37.6	40.5	39.1
4	✔	✔	✔	✔	✔	✗	46.9	39.5	42.7	41.6
5	✔	✔	✔	✔	✔	✔	57.0	46.5	50.4	50.3

Table 3: Ablation studies of each component over the SYSU-CMCC dataset.

Panel of Figure 5 — Figure 5: (a) Results of parameter sensitivity analysis for key hyperparameters in our model. (b) Visualization of retrieval results.

Panel of Figure 6 — Figure 6: Visualizations of (a) cosine distance distributions and (b) attention maps.

Visible-Infrared Person Re-Identification

See all 13 papers

Jun 10, 2026

Learning Instance-Adaptive Low-Rank Orthogonal Subspaces for Clothes-Changing Person Re-Identification

Clothes-changing person re-identification (CC-ReID) aims to recognize individuals despite drastic appearance changes caused by clothing variation. While existing methods rely on adversarial learning to disentangle clothing features, we propose Ortho-ReID, which explicitly models a low-rank clothing subspace from VLM text descriptions and extracts clothing-invariant representations via direct geometric constraints. A critical component is our transformer-based Basis Maker, which refines a shared, low-dimensional clothing prior into an instance-adaptive low-rank subspace through cross-attention with image patches, enabling robust clothing feature extraction even under varying visibility conditions. This instance-adaptive subspace is supervised via alignment with clothing text embeddings, while identity features are extracted via a learnable projection head and geometrically constrained to be strictly orthogonal to it. Extensive experiments demonstrate state-of-the-art performance on PRCC (+5.9% top-1), Celeb-reID-light (+3.5%), and LaST (+5.3%), with competitive results on LTCC.

Dong-Woo Kim, Tae-Kyun Kim

School of Computing, KAIST, Daejeon, South Korea.

Invariant Representation Learning Person Re-Identification

Ask PDF

Mar 2, 2026

MSP-ReID: Hairstyle-Robust Cloth-Changing Person Re-Identification

Cloth-Changing Person Re-Identification (CC-ReID) aims to match the same individual across cameras under varying clothing conditions. Existing approaches often remove apparel and focus on the head region to reduce clothing bias. However, treating the head holistically without distinguishing between face and hair leads to over-reliance on volatile hairstyle cues, causing performance degradation under hairstyle changes. To address this issue, we propose the Mitigating Hairstyle Distraction and Structural Preservation (MSP) framework. Specifically, MSP introduces Hairstyle-Oriented Augmentation (HSOA), which generates intra-identity hairstyle diversity to reduce hairstyle dependence and enhance attention to stable facial and body cues. To prevent the loss of structural information, we design Cloth-Preserved Random Erasing (CPRE), which performs ratio-controlled erasing within clothing regions to suppress texture bias while retaining body shape and context. Furthermore, we employ Region-based Parsing Attention (RPA) to incorporate parsing-guided priors that highlight face and limb regions while suppressing hair features. Extensive experiments on multiple CC-ReID benchmarks demonstrate that MSP achieves state-of-the-art performance, providing a robust and practical solution for long-term person re-identification.

Xiangyang He, Lin Wan

School of Computer Science, China University of Geosciences, Wuhan, China

Person Re-Identification Data Augmentation

Ask PDF

Jul 16, 2026

Blurring Modal Boundaries: A Unified Survey from Single- to Multi-Modal Person Re-ldentification

Person re-identification (ReID) serves as a critical component in intelligent surveillance systems, aiming to match identities across disjoint camera networks. While traditional methods primarily rely on single-modal RGB imagery, they are often constrained by environmental challenges such as low illumination and occlusion. To overcome these limitations, the field is rapidly evolving toward cross-modal and multi-modal paradigms. This survey presents a comprehensive overview of this transition, systematically reviewing key cross-modal tasks including visible-infrared (VI-ReID), text-image (TI-ReID), sketch-based (Sketch-ReID), and the emerging Non-Line-of-Sight (NLOS) ReID, which extends perception beyond direct visibility. Furthermore, we examine tri-spectral and multi-modal fusion ReID, discussing how complementary information from diverse sensors enhances robustness. Beyond summarizing datasets, challenges, and methodologies, we propose a Transformer-based baseline framework for visible-infrared ReID, designed to effectively capture modality-invariant features. Finally, based on the current landscape, we outline several promising directions for future research.

Xiao Wang, Bing Wang, Bin Yang +3

School of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan, Hubei, 430065, China. · Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System, Wuhan University of Science and Technology, Wuhan, Hubei, 430065, China. · School of Computer, Wuhan University, Wuhan, Hubei, 430072, China. +1

Multimodal Fusion Visible-Infrared Person Re-Identification Person Re-Identification

Ask PDF

Abstract

Visible-Infrared Person Re-Identification

Explore similar work

Learning Instance-Adaptive Low-Rank Orthogonal Subspaces for Clothes-Changing Person Re-Identification

MSP-ReID: Hairstyle-Robust Cloth-Changing Person Re-Identification

Blurring Modal Boundaries: A Unified Survey from Single- to Multi-Modal Person Re-ldentification