Re-identification
-
From Calibration to Refinement: Seeking Certainty via Probabilistic Evidence Propagation for Noisy-Label Person Re-Identification
2026-02-26 15:50:15Xin Yuan, Zhiyong Zhang, Xin Xu, Zheng Wang, Chia-Wen LinAbstract
With the increasing demand for robust person Re-ID in unconstrained environments, learning from datasets with noisy labels and sparse per-identity samples remains a critical challenge. Existing noise-robust person Re-ID methods primarily rely on loss-correction or sample-selection strategies using softmax outputs. However, these methods suffer from two key limitations: 1) Softmax exhibits translation invariance, leading to over-confident and unreliable predictions on corrupted labels. 2) Conventional sample selection based on small-loss criteria often discards valuable hard positives that are crucial for learning discriminative features. To overcome these issues, we propose the CAlibration-to-REfinement (CARE) method, a two-stage framework that seeks certainty through probabilistic evidence propagation from calibration to refinement. In the calibration stage, we propose the probabilistic evidence calibration (PEC) that dismantles softmax translation invariance by injecting adaptive learnable parameters into the similarity function, and employs an evidential calibration loss to mitigate overconfidence on mislabeled samples. In the refinement stage, we design the evidence propagation refinement (EPR) that can more accurately distinguish between clean and noisy samples. Specifically, the EPR contains two steps: Firstly, the composite angular margin (CAM) metric is proposed to precisely distinguish clean but hard-to-learn positive samples from mislabeled ones in a hyperspherical space; Secondly, the certainty-oriented sphere weighting (COSW) is developed to dynamically allocate the importance of samples according to CAM, ensuring clean instances drive model updates. Extensive experimental results on Market1501, DukeMTMC-ReID, and CUHK03 datasets under both random and patterned noises show that CARE achieves competitive performance.
Abstract (translated)
随着对未约束环境中鲁棒人物重识别（Re-ID）需求的增加，从带有噪声标签和稀疏身份样本的数据集中学习仍然是一个关键挑战。现有的抗噪人物重识别方法主要依赖于利用softmax输出进行损失校正或样本选择策略。然而，这些方法存在两个关键限制：1) softmax具有平移不变性，在面对损坏的标签时会导致过于自信且不可靠的预测；2) 基于小损失标准的传统样本选择往往排除了对学习鉴别特征至关重要的有价值的困难正例。 为克服这些问题，我们提出了CAlibration-to-REfinement（CARE）方法，这是一种两阶段框架，通过校准到细化过程中的概率证据传播寻求确定性。在校准阶段，我们提出了一种基于注入适应性可学习参数分解softmax平移不变性的概率证据校正（PEC），并通过使用证据校准损失来减轻对错误标签样本的过度自信问题。在细化阶段，我们设计了证据传播细化（EPR）方法，能够更准确地区分干净和噪声样本。 具体而言，EPR包含两个步骤：首先，提出了一种复合角度余量（CAM）度量，在高维球形空间中精确区分难以学习的正例与误标样例；其次，开发了以确定性为中心的球体加权（COSW），根据CAM动态分配样本的重要性，确保干净实例驱动模型更新。 在Market1501、DukeMTMC-ReID和CUHK03数据集上进行的大量实验表明，在随机噪声和模式化噪声环境下，CARE方法实现了具有竞争力的表现。
URL
https://arxiv.org/abs/2602.23133
PDF
-
StoryMovie: A Dataset for Semantic Alignment of Visual Stories with Movie Scripts and Subtitles
2026-02-25 12:01:05Daniel Oliveira, David Martins de MatosAbstract
Visual storytelling models that correctly ground entities in images may still hallucinate semantic relationships, generating incorrect dialogue attribution, character interactions, or emotional states. We introduce StoryMovie, a dataset of 1,757 stories aligned with movie scripts and subtitles through LCS matching. Our alignment pipeline synchronizes screenplay dialogue with subtitle timestamps, enabling dialogue attribution by linking character names from scripts to temporal positions from subtitles. Using this aligned content, we generate stories that maintain visual grounding tags while incorporating authentic character names, dialogue, and relationship dynamics. We fine-tune Qwen Storyteller3 on this dataset, building on prior work in visual grounding and entity re-identification. Evaluation using DeepSeek V3 as judge shows that Storyteller3 achieves an 89.9% win rate against base Qwen2.5-VL 7B on subtitle alignment. Compared to Storyteller, trained without script grounding, Storyteller3 achieves 48.5% versus 38.0%, confirming that semantic alignment progressively improves dialogue attribution beyond visual grounding alone.
Abstract (translated)
视觉叙事模型可能正确地将图像中的实体进行定位，但仍可能出现语义关系上的幻觉，从而生成不正确的对话归属、角色互动或情绪状态。为此，我们引入了StoryMovie数据集，该数据集包含1,757个故事，并通过最长公共子序列（LCS）匹配与电影剧本和字幕进行了对齐。我们的对齐管道同步了脚本中的对话与时长标记的时间戳，从而能够将角色名称从脚本中链接到字幕的时序位置上进行对话归属。使用这种对齐的内容生成故事时，我们在保持视觉定位标签的同时，融入真实的角色名、对话和关系动态。 我们在此数据集上对Qwen Storyteller3进行了微调，建立在先前的工作基础上，这些工作涵盖了视觉定位与实体重新识别领域。通过使用DeepSeek V3作为评判标准进行评估后发现，Storyteller3相对于基础版的Qwen2.5-VL 7B，在字幕对齐上获得了89.9%的胜率。相比于未经脚本对齐训练的故事生成器（即仅依赖视觉信息），Storyteller3在对话归属方面的性能得到了显著提升：48.5%对比38.0%，这表明语义上的精确对齐可以逐步改进对话归属，超越单纯依靠视觉定位的效果。
URL
https://arxiv.org/abs/2602.21829
PDF
-
CityGuard: Graph-Aware Private Descriptors for Bias-Resilient Identity Search Across Urban Cameras
2026-02-20 08:00:17Rong Fu, Wenxin Zhang, Yibo Meng, Jia Yee Tan, Jiaxuan Lu, Rui Lu, Jiekai Wu, Zhaolu Kang, Simon FongAbstract
City-scale person re-identification across distributed cameras must handle severe appearance changes from viewpoint, occlusion, and domain shift while complying with data protection rules that prevent sharing raw imagery. We introduce CityGuard, a topology-aware transformer for privacy-preserving identity retrieval in decentralized surveillance. The framework integrates three components. A dispersion-adaptive metric learner adjusts instance-level margins according to feature spread, increasing intra-class compactness. Spatially conditioned attention injects coarse geometry, such as GPS or deployment floor plans, into graph-based self-attention to enable projectively consistent cross-view alignment using only coarse geometric priors without requiring survey-grade calibration. Differentially private embedding maps are coupled with compact approximate indexes to support secure and cost-efficient deployment. Together these designs produce descriptors robust to viewpoint variation, occlusion, and domain shifts, and they enable a tunable balance between privacy and utility under rigorous differential-privacy accounting. Experiments on Market-1501 and additional public benchmarks, complemented by database-scale retrieval studies, show consistent gains in retrieval precision and query throughput over strong baselines, confirming the practicality of the framework for privacy-critical urban identity matching.
Abstract (translated)
跨分布式摄像头的城市级人员再识别系统必须处理由于视角、遮挡和领域偏移造成的严重外观变化，同时还要遵守数据保护规则，防止分享原始图像。我们引入了CityGuard，这是一种拓扑感知变换器，用于在分散监控中实现隐私保护的身份检索。该框架整合了三个组成部分： 1. **自适应散度测度学习器**：根据特征分布调整实例级别的边界值，增加同一类别的紧密性。 2. **空间条件注意机制**：将粗略几何信息（如GPS或部署楼层图）注入基于图的自我注意中，以利用仅需粗糙几何先验的知识实现跨视角的一致对齐，而无需进行高精度校准。 3. **差分隐私嵌入映射和紧凑近似索引结合**：支持安全且成本效益高的部署。 这些设计共同生成了能够在视角变化、遮挡以及领域偏移下保持鲁棒性的描述符，并能够调整隐私与实用性的平衡，同时在严格的差分隐私计算中表现出色。实验表明，在Market-1501和其他公开基准测试上，该框架的检索精度和查询吞吐量均超越了强大的基线系统，证实了其在关键隐私保护的城市身份匹配场景中的实用性。
URL
https://arxiv.org/abs/2602.18047
PDF
-
Automated Re-Identification of Holstein-Friesian Cattle in Dense Crowds
2026-02-17 19:25:50Phoenix Yu, Tilo Burghardt, Andrew W Dowsey, Neill W CampbellAbstract
Holstein-Friesian detection and re-identification (Re-ID) methods capture individuals well when targets are spatially separate. However, existing approaches, including YOLO-based species detection, break down when cows group closely together. This is particularly prevalent for species which have outline-breaking coat patterns. To boost both effectiveness and transferability in this setting, we propose a new detect-segment-identify pipeline that leverages the Open-Vocabulary Weight-free Localisation and the Segment Anything models as pre-processing stages alongside Re-ID networks. To evaluate our approach, we publish a collection of nine days CCTV data filmed on a working dairy farm. Our methodology overcomes detection breakdown in dense animal groupings, resulting in a 98.93% accuracy. This significantly outperforms current oriented bounding box-driven, as well as SAM species detection baselines with accuracy improvements of 47.52% and 27.13%, respectively. We show that unsupervised contrastive learning can build on this to yield 94.82% Re-ID accuracy on our test data. Our work demonstrates that Re-ID in crowded scenarios is both practical as well as reliable in working farm settings with no manual intervention. Code and dataset are provided for reproducibility.
Abstract (translated)
URL
https://arxiv.org/abs/2602.15962
PDF
-
Unleashing MLLMs on the Edge: A Unified Framework for Cross-Modal ReID via Adaptive SVD Distillation
2026-02-13 13:48:08Hongbo Jiang, Jie Li, Xinqi Cai, Tianyu Xie, Yunhang Shen, Pingyang Dai, Liujuan CaoAbstract
Practical cloud-edge deployment of Cross-Modal Re-identification (CM-ReID) faces challenges due to maintaining a fragmented ecosystem of specialized cloud models for diverse modalities. While Multi-Modal Large Language Models (MLLMs) offer strong unification potential, existing approaches fail to adapt them into a single end-to-end backbone and lack effective knowledge distillation strategies for edge deployment. To address these limitations, we propose MLLMEmbed-ReID, a unified framework based on a powerful cloud-edge architecture. First, we adapt a foundational MLLM into a state-of-the-art cloud model. We leverage instruction-based prompting to guide the MLLM in generating a unified embedding space across RGB, infrared, sketch, and text modalities. This model is then trained efficiently with a hierarchical Low-Rank Adaptation finetuning (LoRA-SFT) strategy, optimized under a holistic cross-modal alignment objective. Second, to deploy its knowledge onto an edge-native student, we introduce a novel distillation strategy motivated by the low-rank property in the teacher's feature space. To prioritize essential information, this method employs a Principal Component Mapping loss, while relational structures are preserved via a Feature Relation loss. Our lightweight edge-based model achieves state-of-the-art performance on multiple visual CM-ReID benchmarks, while its cloud-based counterpart excels across all CM-ReID benchmarks. The MLLMEmbed-ReID framework thus presents a complete and effective solution for deploying unified MLLM-level intelligence on resource-constrained devices. The code and models will be open-sourced soon.
Abstract (translated)
URL
https://arxiv.org/abs/2602.12936
PDF
-
RAT-Bench: A Comprehensive Benchmark for Text Anonymization
2026-02-13 10:41:44Nata\v{s}a Kr\v{c}o, Zexi Yao, Matthieu Meeus, Yves-Alexandre de MontjoyeAbstract
Data containing personal information is increasingly used to train, fine-tune, or query Large Language Models (LLMs). Text is typically scrubbed of identifying information prior to use, often with tools such as Microsoft's Presidio or Anthropic's PII purifier. These tools have traditionally been evaluated on their ability to remove specific identifiers (e.g., names), yet their effectiveness at preventing re-identification remains unclear. We introduce RAT-Bench, a comprehensive benchmark for text anonymization tools based on re-identification risk. Using U.S. demographic statistics, we generate synthetic text containing various direct and indirect identifiers across domains, languages, and difficulty levels. We evaluate a range of NER- and LLM-based text anonymization tools and, based on the attributes an LLM-based attacker is able to correctly infer from the anonymized text, we report the risk of re-identification in the U.S. population, while properly accounting for the disparate impact of identifiers. We find that, while capabilities vary widely, even the best tools are far from perfect in particular when direct identifiers are not written in standard ways and when indirect identifiers enable re-identification. Overall we find LLM-based anonymizers, including new iterative anonymizers, to provide a better privacy-utility trade-off albeit at a higher computational cost. Importantly, we also find them to work well across languages. We conclude with recommendations for future anonymization tools and will release the benchmark and encourage community efforts to expand it, in particular to other geographies.
Abstract (translated)
URL
https://arxiv.org/abs/2602.12806
PDF
-
Simple Image Processing and Similarity Measures Can Link Data Samples across Databases through Brain MRI
2026-02-10 18:10:12Gaurang Sharma, Harri Polonen, Juha Pajula, Jutta Suksi, Jussi TohkaAbstract
Head Magnetic Resonance Imaging (MRI) is routinely collected and shared for research under strict regulatory frameworks. These frameworks require removing potential identifiers before sharing. But, even after skull stripping, the brain parenchyma contains unique signatures that can match other MRIs from the same participants across databases, posing a privacy risk if additional data features are available. Current regulatory frameworks often mandate evaluating such risks based on the assessment of a certain level of reasonableness. Prior studies have already suggested that a brain MRI could enable participant linkage, but they have relied on training-based or computationally intensive methods. Here, we demonstrate that linking an individual's skull-stripped T1-weighted MRI, which may lead to re-identification if other identifiers are available, is possible using standard preprocessing followed by image similarity computation. Nearly perfect linkage accuracy was achieved in matching data samples across various time intervals, scanner types, spatial resolutions, and acquisition protocols, despite potential cognitive decline, simulating MRI matching across databases. These results aim to contribute meaningfully to the development of thoughtful, forward-looking policies in medical data sharing.
Abstract (translated)
头部磁共振成像（MRI）通常在严格的监管框架下收集和共享用于研究。这些框架要求在分享数据前移除潜在的身份标识符。然而，即使去除了颅骨信息后，脑实质中仍然包含独特的特征，这些特征可以在不同数据库中的同一参与者的其他MRI图像之间进行匹配，从而构成隐私风险，特别是当有额外的数据特性可用时。现有的监管框架通常规定需要基于某一合理水平的评估来评定此类风险。 先前的研究已经表明，通过脑部MRI可以实现参与者之间的关联，但它们依赖于训练基或计算密集型方法。在这里，我们展示了使用标准预处理后进行图像相似性计算的方法，可以将去除了颅骨信息后的T1加权MRI与个人匹配起来，即使在有其他身份标识符可用的情况下也可能导致重新识别的问题。 我们在跨不同时间间隔、扫描类型、空间分辨率和采集协议的数据样本中实现了近乎完美的链接准确性，即便考虑到潜在的认知衰退。这些结果模拟了跨数据库进行MRI匹配的情况，并且旨在为医疗数据共享的发展提供有意义的贡献，制定更加周到前瞻性的政策。
URL
https://arxiv.org/abs/2602.10043
PDF
-
Paradox of De-identification: A Critique of HIPAA Safe Harbour in the Age of LLMs
2026-02-09 18:43:19Lavender Y. Jiang, Xujin Chris Liu, Kyunghyun Cho, Eric K. OermannAbstract
Privacy is a human right that sustains patient-provider trust. Clinical notes capture a patient's private vulnerability and individuality, which are used for care coordination and research. Under HIPAA Safe Harbor, these notes are de-identified to protect patient privacy. However, Safe Harbor was designed for an era of categorical tabular data, focusing on the removal of explicit identifiers while ignoring the latent information found in correlations between identity and quasi-identifiers, which can be captured by modern LLMs. We first formalize these correlations using a causal graph, then validate it empirically through individual re-identification of patients from scrubbed notes. The paradox of de-identification is further shown through a diagnosis ablation: even when all other information is removed, the model can predict the patient's neighborhood based on diagnosis alone. This position paper raises the question of how we can act as a community to uphold patient-provider trust when de-identification is inherently imperfect. We aim to raise awareness and discuss actionable recommendations.
Abstract (translated)
隐私是一项人权，它维系了患者与提供者之间的信任。临床笔记记录了患者的私人脆弱性和个体性，这些信息用于护理协调和研究。根据《健康保险流通与责任法案》（HIPAA）的安全港规定，这些笔记会被去标识化以保护患者隐私。然而，安全港规则是为处理类别化的表格数据而设计的，在这种情况下，主要关注的是去除显式识别符，却忽视了身份识别符和准识别符之间相关性所蕴含的信息，后者可以通过现代大型语言模型（LLM）捕捉到。 我们首先通过因果图形式化这些关联，并通过从清理后的笔记中单独重新识别患者来实证验证。去标识化的悖论还通过诊断消除进一步展现出来：即使移除了所有其他信息，仅凭诊断也能让模型预测患者的居住区域。这篇立场论文提出了一个问题——当去标识化本质上是不完美的时候，我们作为社区应该如何行动以维护患者与提供者之间的信任。我们的目标是提高意识，并讨论可操作的建议。
URL
https://arxiv.org/abs/2602.08997
PDF
-
Privacy in Image Datasets: A Case Study on Pregnancy Ultrasounds
2026-02-06 19:47:10Rawisara Lohanimit, Yankun Wu, Amelia Katirai, Yuta Nakashima, Noa GarciaAbstract
The rise of generative models has led to increased use of large-scale datasets collected from the internet, often with minimal or no data curation. This raises concerns about the inclusion of sensitive or private information. In this work, we explore the presence of pregnancy ultrasound images, which contain sensitive personal information and are often shared online. Through a systematic examination of LAION-400M dataset using CLIP embedding similarity, we retrieve images containing pregnancy ultrasound and detect thousands of entities of private information such as names and locations. Our findings reveal that multiple images have high-risk information that could enable re-identification or impersonation. We conclude with recommended practices for dataset curation, data privacy, and ethical use of public image datasets.
Abstract (translated)
生成模型的兴起导致了大规模数据集的广泛使用，这些数据集通常是从互联网上收集而来，并且很少或根本没有进行数据整理。这引发了对敏感或私人信息被包含在内的担忧。在这项工作中，我们探讨了妊娠超声图像的存在情况，这类图像是在网上经常分享的并包含了高度个人化的敏感信息。通过系统地检查LAION-400M数据集中的CLIP嵌入相似性，我们检索到了含有妊娠超声图像的内容，并检测到数千个私人信息实例，如姓名和地点。我们的研究发现表明，多个图像中存在高风险的信息，这些信息可能使重新识别或冒充成为可能。最后，我们提出了关于数据整理、数据隐私以及公共图像数据集的伦理使用方面的建议实践方法。
URL
https://arxiv.org/abs/2602.07149
PDF
-
ReText: Text Boosts Generalization in Image-Based Person Re-identification
2026-02-05 15:43:31Timur Mamedov, Karina Kvanchiani, Anton Konushin, Vadim KonushinAbstract
Generalizable image-based person re-identification (Re-ID) aims to recognize individuals across cameras in unseen domains without retraining. While multiple existing approaches address the domain gap through complex architectures, recent findings indicate that better generalization can be achieved by stylistically diverse single-camera data. Although this data is easy to collect, it lacks complexity due to minimal cross-view variation. We propose ReText, a novel method trained on a mixture of multi-camera Re-ID data and single-camera data, where the latter is complemented by textual descriptions to enrich semantic cues. During training, ReText jointly optimizes three tasks: (1) Re-ID on multi-camera data, (2) image-text matching, and (3) image reconstruction guided by text on single-camera data. Experiments demonstrate that ReText achieves strong generalization and significantly outperforms state-of-the-art methods on cross-domain Re-ID benchmarks. To the best of our knowledge, this is the first work to explore multimodal joint learning on a mixture of multi-camera and single-camera data in image-based person Re-ID.
Abstract (translated)
基于图像的人再识别（Re-ID）的泛化目标是跨不同摄像机在未见过的领域中识别个人，而无需重新训练。虽然目前有许多方法通过复杂的架构来解决域差距问题，但最近的研究表明，使用风格多样化的单摄像头数据可以实现更好的泛化效果。尽管这种数据容易收集，但由于视图变化较小，它缺乏复杂性。 为此，我们提出了ReText这一新方法，该方法是在多摄像机Re-ID数据和通过文本描述补充的单摄像头数据混合体上训练的。通过这种方式，在单摄像头数据中添加了丰富的语义线索。在训练过程中，ReText同时优化三个任务：（1）基于多摄像机数据的人再识别；（2）图像与文本匹配；以及（3）由文本指导的单摄像头数据中的图像重建。 实验表明，ReText在跨域人再识别基准测试中表现出强大的泛化能力，并显著优于现有方法。据我们所知，这是首次探索基于图像的人再识别任务中，在多摄像机和单摄像机数据混合体上的多模态联合学习的工作。
URL
https://arxiv.org/abs/2602.05785
PDF
-
DRFormer: A Dual-Regularized Bidirectional Transformer for Person Re-identification
2026-02-01 06:59:53Ying Shu, Pujian Zhan, Huiqi Yang, Hehe Fan, Youfang Lin, Kai LvAbstract
Both fine-grained discriminative details and global semantic features can contribute to solving person re-identification challenges, such as occlusion and pose variations. Vision foundation models (\textit{e.g.}, DINO) excel at mining local textures, and vision-language models (\textit{e.g.}, CLIP) capture strong global semantic difference. Existing methods predominantly rely on a single paradigm, neglecting the potential benefits of their integration. In this paper, we analyze the complementary roles of these two architectures and propose a framework to synergize their strengths by a \textbf{D}ual-\textbf{R}egularized Bidirectional \textbf{Transformer} (\textbf{DRFormer}). The dual-regularization mechanism ensures diverse feature extraction and achieves a better balance in the contributions of the two models. Extensive experiments on five benchmarks show that our method effectively harmonizes local and global representations, achieving competitive performance against state-of-the-art methods.
Abstract (translated)
URL
https://arxiv.org/abs/2602.01059
PDF
-
Contrastive Domain Generalization for Cross-Instrument Molecular Identification in Mass Spectrometry
2026-01-31 06:18:47Seunghyun Yoo, Sanghong Kim, Namkyung Yoon, Hwangnam KimAbstract
Identifying molecules from mass spectrometry (MS) data remains a fundamental challenge due to the semantic gap between physical spectral peaks and underlying chemical structures. Existing deep learning approaches often treat spectral matching as a closed-set recognition task, limiting their ability to generalize to unseen molecular scaffolds. To overcome this limitation, we propose a cross-modal alignment framework that directly maps mass spectra into the chemically meaningful molecular structure embedding space of a pretrained chemical language model. On a strict scaffold-disjoint benchmark, our model achieves a Top-1 accuracy of 42.2% in fixed 256-way zero-shot retrieval and demonstrates strong generalization under a global retrieval setting. Moreover, the learned embedding space demonstrates strong chemical coherence, reaching 95.4% accuracy in 5-way 5-shot molecular re-identification. These results suggest that explicitly integrating physical spectral resolution with molecular structure embedding is key to solving the generalization bottleneck in molecular identification from MS data.
Abstract (translated)
URL
https://arxiv.org/abs/2602.00547
PDF
-
Rectifying Geometry-Induced Similarity Distortions for Real-World Aerial-Ground Person Re-Identification
2026-01-29 08:41:42Kailash A. Hambarde, Hugo Proen\c{c}aAbstract
Aerial-ground person re-identification (AG-ReID) is fundamentally challenged by extreme viewpoint and distance discrepancies between aerial and ground cameras, which induce severe geometric distortions and invalidate the assumption of a shared similarity space across views. Existing methods primarily rely on geometry-aware feature learning or appearance-conditioned prompting, while implicitly assuming that the geometry-invariant dot-product similarity used in attention mechanisms remains reliable under large viewpoint and scale variations. We argue that this assumption does not hold. Extreme camera geometry systematically distorts the query-key similarity space and degrades attention-based matching, even when feature representations are partially aligned. To address this issue, we introduce Geometry-Induced Query-Key Transformation (GIQT), a lightweight low-rank module that explicitly rectifies the similarity space by conditioning query-key interactions on camera geometry. Rather than modifying feature representations or the attention formulation itself, GIQT adapts the similarity computation to compensate for dominant geometry-induced anisotropic distortions. Building on this local similarity rectification, we further incorporate a geometry-conditioned prompt generation mechanism that provides global, view-adaptive representation priors derived directly from camera geometry. Experiments on four aerial-ground person re-identification benchmarks demonstrate that the proposed framework consistently improves robustness under extreme and previously unseen geometric conditions, while introducing minimal computational overhead compared to state-of-the-art methods.
Abstract (translated)
URL
https://arxiv.org/abs/2601.21405
PDF
-
Person Re-ID in 2025: Supervised, Self-Supervised, and Language-Aligned. What Works?
2026-01-28 13:35:31Lakshman BalasubramanianAbstract
Person Re-Identification (ReID) remains a challenging problem in computer vision. This work reviews various training paradigm and evaluates the robustness of state-of-the-art ReID models in cross-domain applications and examines the role of foundation models in improving generalization through richer, more transferable visual representations. We compare three training paradigms, supervised, self-supervised, and language-aligned models. Through the study the aim is to answer the following questions: Can supervised models generalize in cross-domain scenarios? How does foundation models like SigLIP2 perform for the ReID tasks? What are the weaknesses of current supervised and foundational models for ReID? We have conducted the analysis across 11 models and 9 datasets. Our results show a clear split: supervised models dominate their training domain but crumble on cross-domain data. Language-aligned models, however, show surprising robustness cross-domain for ReID tasks, even though they are not explicitly trained to do so. Code and data available at: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2601.20598
PDF
-
QA-ReID: Quality-Aware Query-Adaptive Convolution Leveraging Fused Global and Structural Cues for Clothes-Changing ReID
2026-01-27 03:01:41Yuxiang Wang, Kunming Jiang, Tianxiang Zhang, Ke Tian, Gaozhe JiangAbstract
Unlike conventional person re-identification (ReID), clothes-changing ReID (CC-ReID) presents severe challenges due to substantial appearance variations introduced by clothing changes. In this work, we propose the Quality-Aware Dual-Branch Matching (QA-ReID), which jointly leverages RGB-based features and parsing-based representations to model both global appearance and clothing-invariant structural cues. These heterogeneous features are adaptively fused through a multi-modal attention module. At the matching stage, we further design the Quality-Aware Query Adaptive Convolution (QAConv-QA), which incorporates pixel-level importance weighting and bidirectional consistency constraints to enhance robustness against clothing variations. Extensive experiments demonstrate that QA-ReID achieves state-of-the-art performance on multiple benchmarks, including PRCC, LTCC, and VC-Clothes, and significantly outperforms existing approaches under cross-clothing scenarios.
Abstract (translated)
URL
https://arxiv.org/abs/2601.19133
PDF
-
Affinity Contrastive Learning for Skeleton-based Human Activity Understanding
2026-01-23 12:20:36Hongda Liu, Yunfan Liu, Min Ren, Lin Sui, Yunlong Wang, Zhenan SunAbstract
In skeleton-based human activity understanding, existing methods often adopt the contrastive learning paradigm to construct a discriminative feature space. However, many of these approaches fail to exploit the structural inter-class similarities and overlook the impact of anomalous positive samples. In this study, we introduce ACLNet, an Affinity Contrastive Learning Network that explores the intricate clustering relationships among human activity classes to improve feature discrimination. Specifically, we propose an affinity metric to refine similarity measurements, thereby forming activity superclasses that provide more informative contrastive signals. A dynamic temperature schedule is also introduced to adaptively adjust the penalty strength for various superclasses. In addition, we employ a margin-based contrastive strategy to improve the separation of hard positive and negative samples within classes. Extensive experiments on NTU RGB+D 60, NTU RGB+D 120, Kinetics-Skeleton, PKU-MMD, FineGYM, and CASIA-B demonstrate the superiority of our method in skeleton-based action recognition, gait recognition, and person re-identification. The source code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2601.16694
PDF
-
IIR-VLM: In-Context Instance-level Recognition for Large Vision-Language Models
2026-01-20 17:45:24Liang Shi, Wei Li, Kevin M Beussman, Lin Chen, Yun FuAbstract
Instance-level recognition (ILR) concerns distinguishing individual instances from one another, with person re-identification as a prominent example. Despite the impressive visual perception capabilities of modern VLMs, we find their performance on ILR unsatisfactory, often dramatically underperforming domain-specific ILR models. This limitation hinders many practical application of VLMs, e.g. where recognizing familiar people and objects is crucial for effective visual understanding. Existing solutions typically learn to recognize instances one at a time using instance-specific datasets, which not only incur substantial data collection and training costs but also struggle with fine-grained discrimination. In this work, we propose IIR-VLM, a VLM enhanced for In-context Instance-level Recognition. We integrate pre-trained ILR expert models as auxiliary visual encoders to provide specialized features for learning diverse instances, which enables VLMs to learn new instances in-context in a one-shot manner. Further, IIR-VLM leverages this knowledge for instance-aware visual understanding. We validate IIR-VLM's efficacy on existing instance personalization benchmarks. Finally, we demonstrate its superior ILR performance on a challenging new benchmark, which assesses ILR capabilities across varying difficulty and diverse categories, with person, face, pet and general objects as the instances at task.
Abstract (translated)
实例级识别（ILR）涉及区分个体实例，其中行人再识别是一个显著的例子。尽管现代视觉语言模型（VLMs）在视觉感知能力方面表现出色，但我们在其实例级识别性能上发现令人不满意的结果，通常大幅落后于特定领域的ILR模型。这种限制阻碍了VLM在许多实际应用中的有效性，例如，在有效视觉理解中需要认出熟悉的人和物体的场景中。现有的解决方案通常通过使用特定于每个实例的数据集一次一个地学习来实现实例识别，这不仅会产生大量的数据收集和训练成本，而且难以进行细微的区分。 为此，我们提出了IIR-VLM（In-context Instance-level Recognition增强型视觉语言模型），这是一种经过优化以在上下文中执行一次性实例级识别任务的VLM。我们在该模型中集成了预训练的ILR专家模型作为辅助视觉编码器，为学习多样化的实例提供了专门的功能特征，这使得VLM能够在一次输入后学会新的实例（即无需额外数据训练）。此外，IIR-VLM利用这种知识来实现对实例的理解。 我们已经在现有的实例个性化基准测试上验证了IIR-VLM的有效性。最后，我们在一个具有挑战性的新基准上展示了其优越的ILR性能评估，在这个基准中，评估了不同难度和多样类别下的ILR能力，任务中的实例包括人、面部、宠物以及一般对象。
URL
https://arxiv.org/abs/2601.14188
PDF
-
Anonpsy: A Graph-Based Framework for Structure-Preserving De-identification of Psychiatric Narratives
2026-01-20 01:37:44Kyung Ho Lim, Byung-Hoon KimAbstract
Psychiatric narratives encode patient identity not only through explicit identifiers but also through idiosyncratic life events embedded in their clinical structure. Existing de-identification approaches, including PHI masking and LLM-based synthetic rewriting, operate at the text level and offer limited control over which semantic elements are preserved or altered. We introduce Anonpsy, a de-identification framework that reformulates the task as graph-guided semantic rewriting. Anonpsy (1) converts each narrative into a semantic graph encoding clinical entities, temporal anchors, and typed relations; (2) applies graph-constrained perturbations that modify identifying context while preserving clinically essential structure; and (3) regenerates text via graph-conditioned LLM generation. Evaluated on 90 clinician-authored psychiatric case narratives, Anonpsy preserves diagnostic fidelity while achieving consistently low re-identification risk under expert, semantic, and GPT-5-based evaluations. Compared with a strong LLM-only rewriting baseline, Anonpsy yields substantially lower semantic similarity and identifiability. These results demonstrate that explicit structural representations combined with constrained generation provide an effective approach to de-identification for psychiatric narratives.
Abstract (translated)
精神健康叙述通过明确的身份标识符以及嵌入在临床结构中的个人化生活事件来编码患者身份。现有的去识别方法，包括PHI屏蔽和基于LLM的合成重写，在文本层面操作，并且对保留或更改哪些语义元素控制有限。我们引入了Anonpsy，这是一种以引导语义重写的图谱为指导的去标识框架。Anonpsy（1）将每个叙述转换成一个包含临床实体、时间锚点和类型化关系的语义图；（2）应用受约束的图谱修改，改变识别性上下文的同时保留临床结构的关键部分；（3）通过条件生成的LLM再生文本。在对90个由精神科医生撰写的案例叙述进行评估时，Anonpsy在保持诊断准确性的同时，在专家、语义和GPT-5基线测试中均表现出一致低水平的再识别风险。与一个强大的基于LLM的重写基准相比，Anonpsy显著降低了语义相似性和可标识性。这些结果表明，结合显式结构表示和受约束生成的方法为精神健康叙述的去标识提供了有效途径。
URL
https://arxiv.org/abs/2601.13503
PDF
-
Language-Based Swarm Perception: Decentralized Person Re-Identification via Natural Language Descriptions
2026-01-18 16:43:27Miquel Kegeleirs, Lorenzo Garattoni, Gianpiero Francesca, Mauro BirattariAbstract
We introduce a method for decentralized person re-identification in robot swarms that leverages natural language as the primary representational modality. Unlike traditional approaches that rely on opaque visual embeddings -- high-dimensional feature vectors extracted from images -- the proposed method uses human-readable language to represent observations. Each robot locally detects and describes individuals using a vision-language model (VLM), producing textual descriptions of appearance instead of feature vectors. These descriptions are compared and clustered across the swarm without centralized coordination, allowing robots to collaboratively group observations of the same individual. Each cluster is distilled into a representative description by a language model, providing an interpretable, concise summary of the swarm's collective perception. This approach enables natural-language querying, enhances transparency, and supports explainable swarm behavior. Preliminary experiments demonstrate competitive performance in identity consistency and interpretability compared to embedding-based methods, despite current limitations in text similarity and computational load. Ongoing work explores refined similarity metrics, semantic navigation, and the extension of language-based perception to environmental elements. This work prioritizes decentralized perception and communication, while active navigation remains an open direction for future study.
Abstract (translated)
我们提出了一种在机器人集群中进行去中心化人员再识别的方法，该方法利用自然语言作为主要的表现形式。与传统的依赖于不透明的视觉嵌入（从图像提取的高度维特征向量）的方法不同，所提出的方法使用人类可读的语言来表示观察结果。每个机器人本地检测并描述个体，并使用视觉-语言模型（VLM）生成外观的文字描述，而不是特征向量。这些描述在没有集中协调的情况下在整个集群中进行比较和聚类，使机器人能够协作地对同一个人的观察结果进行分组。每个聚类由一个语言模型提炼成一个代表性的描述，提供了一个可解释且简洁的群体感知总结。这种方法支持自然语言查询、增强透明度并支持可解释群集行为。初步实验表明，在身份一致性以及与基于嵌入的方法相比在可解释性方面表现出了竞争力，尽管目前文本相似性和计算负荷方面存在限制。正在进行的工作探索了更精细的相似度指标、语义导航以及将基于语言的感知扩展到环境元素的可能性。这项工作优先考虑去中心化感知和通信，而主动导航仍然是未来研究的一个开放方向。
URL
https://arxiv.org/abs/2601.12479
PDF
-
Learning Language-Driven Sequence-Level Modal-Invariant Representations for Video-Based Visible-Infrared Person Re-Identification
2026-01-17 14:18:23Xiaomei Yang, Xizhan Gao, Antai Liu, Kang Wei, Fa Zhu, Guang Feng, Xiaofeng Qu, Sijie NiuAbstract
The core of video-based visible-infrared person re-identification (VVI-ReID) lies in learning sequence-level modal-invariant representations across different modalities. Recent research tends to use modality-shared language prompts generated by CLIP to guide the learning of modal-invariant representations. Despite achieving optimal performance, such methods still face limitations in efficient spatial-temporal modeling, sufficient cross-modal interaction, and explicit modality-level loss guidance. To address these issues, we propose the language-driven sequence-level modal-invariant representation learning (LSMRL) method, which includes spatial-temporal feature learning (STFL) module, semantic diffusion (SD) module and cross-modal interaction (CMI) module. To enable parameter- and computation-efficient spatial-temporal modeling, the STFL module is built upon CLIP with minimal modifications. To achieve sufficient cross-modal interaction and enhance the learning of modal-invariant features, the SD module is proposed to diffuse modality-shared language prompts into visible and infrared features to establish preliminary modal consistency. The CMI module is further developed to leverage bidirectional cross-modal self-attention to eliminate residual modality gaps and refine modal-invariant representations. To explicitly enhance the learning of modal-invariant representations, two modality-level losses are introduced to improve the features' discriminative ability and their generalization to unseen categories. Extensive experiments on large-scale VVI-ReID datasets demonstrate the superiority of LSMRL over AOTA methods.
Abstract (translated)
视频基础的可见光-红外人员再识别（VVI-ReID）的核心在于学习不同模态之间的序列级模态不变表示。最近的研究倾向于使用由CLIP生成的模态共享语言提示来指导模态不变表示的学习。尽管这些方法已经达到了最优性能，但在高效的时空建模、充分的跨模态交互以及明确的模态级别损失引导方面仍然存在局限性。为了解决这些问题，我们提出了一种基于语言驱动的序列级模态不变表征学习（LSMRL）的方法，该方法包括时空特征学习（STFL）模块、语义扩散（SD）模块和跨模态交互（CMI）模块。 为了实现参数高效且计算高效的时空建模，STFL模块是在CLIP的基础上进行少量修改而构建的。为了达到充分的跨模态交互并增强模态不变特征的学习，提出了一个语义扩散模块，将模态共享的语言提示扩散到可见光和红外特征中，以建立初步的模态一致性。此外，通过发展双向跨模态自注意力机制来消除残余模态差距，并细化模态不变表示，进一步改进了CMI模块。 为了明确增强模态不变表示的学习，我们引入了两种模态级损失，以提高特征的判别能力和其对未见类别的泛化能力。在大规模VVI-ReID数据集上的广泛实验表明，LSMRL方法优于现有的AOTA（Attention-based One-to-Many Alignment）方法。
URL
https://arxiv.org/abs/2601.12062
PDF
