A Self-Semantic-Structural-Guided Approach for Training-Free Full-Hand De-Identification

Face De-Identification: A Domain-Centric Survey from Capture to Processing.

Face de-identification (De-ID) aims to remove or conceal personally identifiable facial features in images or videos to prevent identity recognition while preserving utility for downstream tasks. With the rising emphasis on data privacy and responsible AI, face De-ID has emerged as an active research area spanning computer vision and privacy-preserving communities. Early approaches, and many contemporary ones, operate in the digital domain by modifying pixel-level or appearance-level features through post-capture processing. Recent advances extend face De-ID beyond post-processing by integrating privacy mechanisms directly into sensors during image acquisition, bridging sensing systems and downstream vision algorithms. In parallel, physical-domain methods explore wearable accessories and materials that conceal identity information in real-world environments prior to capture. In this survey, we present the first unified overview that spans the full data acquisition pipeline, encompassing the physical, sensor, and digital domains. Through this domain-centric lens, we systematically analyze current methodologies, technical progress, and the distinct challenges inherent to each stage. We then review and organize existing evaluation protocols, examining current practices and highlighting the critical need for standardized, comprehensive benchmarks. Finally, we identify key open problems and outline emerging research directions to guide future work in this rapidly evolving field. To support ongoing research, we maintain a project page that organizes relevant literature with collected datasets and open source code: https://github.com/CV-AC/Awesome-FaceDe-ID.

CLIP-SGI: A Semantic-Guided and Instance-Consistent Framework for Generalizable Person Re-Identification.

Generalizable person re-identification (ReID) requires a model trained on labeled source domains to remain discriminative in unseen environments. Although vision-language models provide rich cross-modal priors, the appearance semantics used by CLIP-based ReID are often encoded implicitly in learned prompts and are not explicitly organized into reusable part-level cues. Moreover, conventional identity supervision mainly emphasizes the separation of source identities and makes limited use of the local relationships among visually similar instances. To address these issues, we propose CLIP-SGI, a semantic-guided and instance-consistent framework for generalizable person ReID. First, multiple off-the-shelf vision-language models generate pedestrian descriptions. For each VLM, upper- and lower-body attributes are first voted across images of the same identity and then across the VLM-specific identity labels. Second, we construct an Attribute Prototype Bank (APB) that uses the resulting attributes as region-aware semantic anchors to guide appearance-sensitive feature learning. Third, we introduce a similarity-aware and frequency-normalized soft-label constraint that preserves ground-truth identity supervision while exploiting reliable neighborhood relationships as auxiliary signals. The three-stage training scheme combines semantic guidance, domain-aware representation learning, and instance consistency to improve robustness under domain shifts. Extensive experiments on multiple benchmark datasets demonstrate the effectiveness of the proposed method and its consistent improvements in mean average precision (mAP) and Rank-1 (R1) accuracy.

Uncertainty-guided collaborative learning for noise-robust text-to-image person re-identification

Structural-Semantic Reciprocal Learning for Unsupervised Visible-Infrared Person Re-Identification

Unsupervised visible-infrared person re-identification (USVI-ReID) is challenging due to the large modality gap and the lack of cross-modal identity annotations. Progressive association paradigms have been proposed to gradually bridge the gap, but they suffer from two critical bottlenecks: reliance on ambiguous global representations and unchecked propagation of pseudo-label noise in an open-loop manner. To address these issues, we propose Structural-Semantic Reciprocal Learning (SSRL), a framework that transforms open-loop association into a self-correcting closed-loop system. Structurally, we introduce Fine-grained Structural Decoupling (FSD) to extract discriminative body-part primitives as reliable spatial anchors, complementing ambiguous holistic silhouettes with spatially consistent structural details. Semantically, we design a Closed-loop Semantic Calibration (CSC) mechanism that reconstructs shared semantic prototypes at each epoch and feeds them back into the training loop, effectively filtering pseudo-label noise before the next clustering cycle. Through the reciprocal interaction between structural and semantic learning, SSRL achieves robust cross-modal representation. Extensive experiments demonstrate the competitive performance of SSRL against state-of-the-art USVI-ReID methods on both SYSU-MM01 and RegDB, notably surpassing several supervised counterparts on RegDB.

Mask-Guided Asymmetric Contrastive and Semantic Alignment for Unsupervised Person Re-Identification

Unsupervised person re-identification (ReID) aims to learn identity-discriminative representations without manual annotations, which is challenging due to noisy pseudo labels, background clutter, and large appearance variations. Recent studies have shown that exploiting fine-grained local cues is crucial for improving robustness in unsupervised ReID. In this context, random masking has emerged as a simple and annotation-free way to encourage the model to focus on informative regions. However, existing masking-based unsupervised ReID methods still suffer from two limitations: (1) Underused masked views: masked views are treated as degraded auxiliaries rather than exploited as fine-grained supervisory signals; (2) Weak cross-view alignment: feature alignment is restricted to mini-batch pairs, lacking explicit global alignment between masked and unmasked views across clusters. To address these issues, we propose the Mask-guided Asymmetric Contrastive and Semantic Alignment (ACSA) framework. Specifically, we introduce an Asymmetric Contrastive Learning (ACL) module with a dual-memory mechanism to separately encode masked and unmasked features, allowing masked views to serve as informative and discriminative supervision. In parallel, a Semantic Alignment Learning (SAL) module conducts multi-granularity distribution alignment by aligning both cluster-level prototypes and randomly sampled instance-level features, thereby preserving semantic consistency and intra-cluster diversity. Furthermore, to provide more reliable semantic anchors for SAL under noisy pseudo labels, we introduce a Progressive Refinement Module (PRM), which refines prototypes and features via exponential moving averaging for more stable semantic alignment. Extensive experiments validate the superiority of our method, even outperforming certain supervised counterparts. Code is available at https://github.com/Trangle12/ACSA

Multi-Level Semantic-Guided Framework for Cloth-Changing Person Re-Identification

Cloth-changing person re-identification (CC-ReID) aims to match persons who change clothing across multiple surveillance cameras. Recent approaches strive to extract clothing-agnostic features by utilizing biological information, including skeleton, texture, gait, and 3D data. However, most methods rely on additional features at a single aspect, leading to a lack of comprehensive understanding of concepts and semantics. This limitation introduces biases and restricts both accuracy and functionality, thereby diminishing their effectiveness in handling variations in clothing. To alleviate this problem, we propose a Multi-level Semantic-Guided (MSG) framework that integrates contextual and fine-grained visual information to eliminate clothing variance across both conceptual and pixel dimensions. This innovative solution consists of two key components: the Contextual Semantic Guidance (CSG) module adeptly utilizes textual features from clothing descriptions to decouple clothing concepts at a higher semantic level. In contrast, the Low-Level Robust Feature Disentanglement (LRD) module meticulously analyzes images featuring clothing to disentangle texture information at the granular pixel level, and the integration of a momentum update mechanism significantly bolsters the model’s robustness. The two approaches collaboratively eliminate clothing information by interacting across different semantic levels. Extensive experiments demonstrate the effectiveness of our method, achieving new state-of-the-art performance on several popular CC-ReID benchmarks. Our code will be available on GitHub at https://github.com/ShijuanHuang/MSG.