Re-identification
-
Privacy-Preserving Synthetic Dataset of Individual Daily Trajectories for City-Scale Mobility Analytics
2025-12-19 04:59:41Jun'ichi Ozaki, Ryosuke Susuta, Takuhiro Moriyama, Yohei ShidaAbstract
Urban mobility data are indispensable for urban planning, transportation demand forecasting, pandemic modeling, and many other applications; however, individual mobile phone-derived Global Positioning System traces cannot generally be shared with third parties owing to severe re-identification risks. Aggregated records, such as origin-destination (OD) matrices, offer partial insights but fail to capture the key behavioral properties of daily human movement, limiting realistic city-scale analyses. This study presents a privacy-preserving synthetic mobility dataset that reconstructs daily trajectories from aggregated inputs. The proposed method integrates OD flows with two complementary behavioral constraints: (1) dwell-travel time quantiles that are available only as coarse summary statistics and (2) the universal law for the daily distribution of the number of visited locations. Embedding these elements in a multi-objective optimization framework enables the reproduction of realistic distributions of human mobility while ensuring that no personal identifiers are required. The proposed framework is validated in two contrasting regions of Japan: (1) the 23 special wards of Tokyo, representing a dense metropolitan environment; and (2) Fukuoka Prefecture, where urban and suburban mobility patterns coexist. The resulting synthetic mobility data reproduce dwell-travel time and visit frequency distributions with high fidelity, while deviations in OD consistency remain within the natural range of daily fluctuations. The results of this study establish a practical synthesis pathway under real-world constraints, providing governments, urban planners, and industries with scalable access to high-resolution mobility data for reliable analytics without the need for sensitive personal records, and supporting practical deployments in policy and commercial domains.
Abstract (translated)
城市移动数据对于城市规划、交通需求预测、疫情建模及其他多种应用来说至关重要；然而，由于严重的重新识别风险，个人手机获取的全球定位系统轨迹通常不能与第三方共享。尽管聚合记录（如出发地-目的地矩阵）能够提供部分见解，但它们无法捕捉日常人类活动的关键行为特征，这限制了对大规模城市的现实分析。这项研究提出了一种隐私保护型合成移动数据集，该数据集从聚合输入中重建每日轨迹。所提出的方法将出发地-目的地流量与两种互补的行为约束相结合：（1）仅以粗略统计数据形式存在的逗留出行时间分位数；以及（2）一天内访问地点数量的普遍规律。在多目标优化框架中嵌入这些元素能够再现真实的人类移动分布，同时确保不需要个人标识符。该框架在日本两个对比鲜明的地区得到了验证：（1）代表密集都市环境的东京特别区23区；和（2）福冈县，其中城市与郊区的出行模式共存。生成的合成移动数据在准确性上能够高度再现逗留出行时间和访问频率分布，而出发地-目的地一致性偏差仍保持在日常波动范围内。本研究的结果建立了实用综合路径的方法，在现实世界条件下为政府、城市规划者和行业提供可扩展且无需敏感个人记录就能获取高分辨率移动数据的可靠分析途径，并支持政策与商业领域的实际部署。
URL
https://arxiv.org/abs/2512.17239
PDF
-
Memory-Enhanced SAM3 for Occlusion-Robust Surgical Instrument Segmentation
2025-12-18 18:49:33Valay Bundele, Mehran Hosseinzadeh, Hendrik P. A. LenschAbstract
Accurate surgical instrument segmentation in endoscopic videos is crucial for computer-assisted interventions, yet remains challenging due to frequent occlusions, rapid motion, specular artefacts, and long-term instrument re-entry. While SAM3 provides a powerful spatio-temporal framework for video object segmentation, its performance in surgical scenes is limited by indiscriminate memory updates, fixed memory capacity, and weak identity recovery after occlusions. We propose ReMeDI-SAM3, a training-free memory-enhanced extension of SAM3, that addresses these limitations through three components: (i) relevance-aware memory filtering with a dedicated occlusion-aware memory for storing pre-occlusion frames, (ii) a piecewise interpolation scheme that expands the effective memory capacity, and (iii) a feature-based re-identification module with temporal voting for reliable post-occlusion identity disambiguation. Together, these components mitigate error accumulation and enable reliable recovery after occlusions. Evaluations on EndoVis17 and EndoVis18 under a zero-shot setting show absolute mcIoU improvements of around 7% and 16%, respectively, over vanilla SAM3, outperforming even prior training-based approaches. Project page: this https URL.
Abstract (translated)
在内窥镜视频中精确分割手术器械对于计算机辅助干预至关重要，但由于频繁的遮挡、快速移动、镜面伪影和长时间工具重新进入等问题，这一任务仍然具有挑战性。虽然SAM3提供了一种强大的时空框架来进行视频对象分割，但在外科场景中的性能受限于不分青红皂白的记忆更新、固定内存容量以及遮挡后身份恢复能力较弱的问题。 为此，我们提出了ReMeDI-SAM3，这是一个无需训练的增强记忆版本的SAM3扩展，通过三个组成部分来解决上述限制：（i）相关性感知的记忆过滤机制和一个专门用于存储被遮挡前帧的遮挡意识内存；（ii）一种分段插值方案以扩大有效内存容量；以及（iii）一种基于特征的身份重新识别模块，并结合时间投票技术，以便在遮挡后可靠地区分身份。这些组件共同作用减少错误积累，并支持在遮挡后的可靠恢复。 实验结果表明，在EndoVis17和EndoVis18数据集上的零样本设置下，ReMeDI-SAM3相较于基础版本的SAM3分别取得了大约7%和16%的绝对mcIoU改进，甚至超过了基于训练的方法的表现。项目主页：[请参见原文链接]。 这一研究成果展示了在不进行额外训练的前提下通过增强记忆机制提高视频分割性能的可能性，并为未来的研究提供了一个有价值的框架。
URL
https://arxiv.org/abs/2512.16880
PDF
-
Few-Shot Fingerprinting Subject Re-Identification in 3D-MRI and 2D-X-Ray
2025-12-18 15:50:54Gon\c{c}alo Gaspar Alves, Shekoufeh Gorgi Zadeh, Andreas Husch, Ben BauschAbstract
Combining open-source datasets can introduce data leakage if the same subject appears in multiple sets, leading to inflated model performance. To address this, we explore subject fingerprinting, mapping all images of a subject to a distinct region in latent space, to enable subject re-identification via similarity matching. Using a ResNet-50 trained with triplet margin loss, we evaluate few-shot fingerprinting on 3D MRI and 2D X-ray data in both standard (20-way 1-shot) and challenging (1000-way 1-shot) scenarios. The model achieves high Mean- Recall-@-K scores: 99.10% (20-way 1-shot) and 90.06% (500-way 5-shot) on ChestXray-14; 99.20% (20-way 1-shot) and 98.86% (100-way 3-shot) on BraTS- 2021.
Abstract (translated)
将开源数据集合并时，如果同一个主体在多个数据集中出现，可能会引入数据泄漏问题，从而导致模型性能被高估。为了解决这个问题，我们探索了主体指纹识别技术，即把一个主题的所有图像映射到潜在空间中的独特区域中，以便通过相似性匹配来重新识别该主题。利用带有三元组边际损失的ResNet-50模型，在标准（20类1样本）和挑战性（1000类1样本）场景下评估了在3D MRI和2D X射线数据上的少量示例指纹识别性能。 模型获得了高Mean Recall @ K分数：在ChestXray-14上，分别为99.10%（20类1样本）和90.06%（500类5样本）；在BraTS 2021数据集上，分别为99.20%（20类1样本）和98.86%（100类3样本）。
URL
https://arxiv.org/abs/2512.16685
PDF
-
LCMem: A Universal Model for Robust Image Memorization Detection
2025-12-16 14:06:58Mischa Dombrowski, Felix N\"utzel, Bernhard KainzAbstract
Recent advances in generative image modeling have achieved visual realism sufficient to deceive human experts, yet their potential for privacy preserving data sharing remains insufficiently understood. A central obstacle is the absence of reliable memorization detection mechanisms, limited quantitative evaluation, and poor generalization of existing privacy auditing methods across domains. To address this, we propose to view memorization detection as a unified problem at the intersection of re-identification and copy detection, whose complementary goals cover both identity consistency and augmentation-robust duplication, and introduce Latent Contrastive Memorization Network (LCMem), a cross-domain model evaluated jointly on both tasks. LCMem achieves this through a two-stage training strategy that first learns identity consistency before incorporating augmentation-robust copy detection. Across six benchmark datasets, LCMem achieves improvements of up to 16 percentage points on re-identification and 30 percentage points on copy detection, enabling substantially more reliable memorization detection at scale. Our results show that existing privacy filters provide limited performance and robustness, highlighting the need for stronger protection mechanisms. We show that LCMem sets a new standard for cross-domain privacy auditing, offering reliable and scalable memorization detection. Code and model is publicly available at this https URL.
Abstract (translated)
近期在生成图像模型方面的进展已经达到了足以欺骗人类专家的视觉逼真度，然而这些技术在保护隐私的数据共享中的潜力仍然不够充分地被理解。一个主要障碍是缺乏可靠的内存检测机制、有限的定量评估以及现有隐私审计方法跨领域的差泛化能力。为了解决这个问题，我们建议将内存检测视为识别和复制检测交叉点上的统一问题，其互补目标涵盖了身份一致性与增强鲁棒性复制，并引入了潜对比记忆网络（LCMem），这是一种在两个任务上联合评估的跨领域模型。 LCMem 通过两阶段训练策略实现这一目标，首先学习身份一致性，然后将增强鲁棒性复制检测纳入其中。在六个基准数据集上，LCMem 在重新识别方面提高了多达16个百分点，在复制检测方面提高了30个百分点，从而实现了更大规模下更可靠的内存检测。我们的结果显示现有的隐私过滤器提供的性能和稳健性有限，强调了需要更强的保护机制。我们证明 LCMem 为跨域隐私审计设定了新的标准，提供了可靠且可扩展的记忆检测方法。代码和模型在以下链接公开提供：[此 URL]（请将括号内的文本替换为实际发布的URL）。
URL
https://arxiv.org/abs/2512.14421
PDF
-
Face Identity Unlearning for Retrieval via Embedding Dispersion
2025-12-15 13:35:28Mikhail ZakharovAbstract
Face recognition systems rely on learning highly discriminative and compact identity clusters to enable accurate retrieval. However, as with other surveillance-oriented technologies, such systems raise serious privacy concerns due to their potential for unauthorized identity tracking. While several works have explored machine unlearning as a means of privacy protection, their applicability to face retrieval - especially for modern embedding-based recognition models - remains largely unexplored. In this work, we study the problem of face identity unlearning for retrieval systems and present its inherent challenges. The goal is to make selected identities unretrievable by dispersing their embeddings on the hypersphere and preventing the formation of compact identity clusters that enable re-identification in the gallery. The primary challenge is to achieve this forgetting effect while preserving the discriminative structure of the embedding space and the retrieval performance of the model for the remaining identities. To address this, we evaluate several existing approximate class unlearning methods (e.g., Random Labeling, Gradient Ascent, Boundary Unlearning, and other recent approaches) in the context of face retrieval and propose a simple yet effective dispersion-based unlearning approach. Extensive experiments on standard benchmarks (VGGFace2, CelebA) demonstrate that our method achieves superior forgetting behavior while preserving retrieval utility.
Abstract (translated)
面部识别系统依赖于学习高度判别性和紧凑的身份聚类，以实现准确的检索。然而，与其他监控技术一样，这类系统由于其潜在的未经授权的身份追踪能力而引发了严重的隐私问题。尽管已有几项研究探索了机器遗忘作为隐私保护手段的应用，但它们在面部检索（尤其是针对现代嵌入式识别模型）中的适用性仍然鲜有探讨。 在这项工作中，我们研究了面向检索系统的面部身份遗忘问题，并展示了其固有的挑战。我们的目标是通过分散选定身份的嵌入以使其无法被检索，在超球面上防止紧凑的身份聚类形成，从而阻止重新识别。主要挑战在于在保留嵌入空间的判别性结构和模型对剩余身份的检索性能的同时实现这种忘记效果。 为解决这一问题，我们评估了几种现有的近似类别遗忘方法（如随机标签法、梯度上升法、边界遗忘法及其他最近的方法）在面部检索中的应用，并提出了一种简单而有效的基于分散的遗忘策略。我们在标准基准测试集（VGGFace2和CelebA）上的广泛实验表明，我们的方法能够实现更优的忘记行为同时保持检索效用。
URL
https://arxiv.org/abs/2512.13317
PDF
-
Prior-Enhanced Gaussian Splatting for Dynamic Scene Reconstruction from Casual Video
2025-12-12 08:09:15Meng-Li Shih, Ying-Huan Chen, Yu-Lun Liu, Brian CurlessAbstract
We introduce a fully automatic pipeline for dynamic scene reconstruction from casually captured monocular RGB videos. Rather than designing a new scene representation, we enhance the priors that drive Dynamic Gaussian Splatting. Video segmentation combined with epipolar-error maps yields object-level masks that closely follow thin structures; these masks (i) guide an object-depth loss that sharpens the consistent video depth, and (ii) support skeleton-based sampling plus mask-guided re-identification to produce reliable, comprehensive 2-D tracks. Two additional objectives embed the refined priors in the reconstruction stage: a virtual-view depth loss removes floaters, and a scaffold-projection loss ties motion nodes to the tracks, preserving fine geometry and coherent motion. The resulting system surpasses previous monocular dynamic scene reconstruction methods and delivers visibly superior renderings
Abstract (translated)
我们介绍了一种从随意拍摄的单目RGB视频中进行动态场景重建的全自动管道。而不是设计一个新的场景表示，我们改进了驱动动态高斯点置（Dynamic Gaussian Splatting）的先验知识。结合视频分割和极线误差图可以产生与细长结构紧密贴合的对象级蒙版；这些蒙版(i)引导一个对象深度损失，以锐化一致的视频深度，并(ii)支持基于骨架采样以及蒙版引导下的重新识别，从而生成可靠且全面的二维轨迹。两个额外的目标将精炼后的先验知识嵌入到重建阶段：虚拟视图深度损失可以去除漂浮物，而支架投影损失则将运动节点绑定至轨迹中，保留了精细几何结构和连贯的运动。该系统超越了之前的单目动态场景重建方法，并提供了明显更优的渲染效果。
URL
https://arxiv.org/abs/2512.11356
PDF
-
Label-free Motion-Conditioned Diffusion Model for Cardiac Ultrasound Synthesis
2025-12-10 08:32:34Zhe Li, Hadrien Reynaud, Johanna P M\"uller, Bernhard KainzAbstract
Ultrasound echocardiography is essential for the non-invasive, real-time assessment of cardiac function, but the scarcity of labelled data, driven by privacy restrictions and the complexity of expert annotation, remains a major obstacle for deep learning methods. We propose the Motion Conditioned Diffusion Model (MCDM), a label-free latent diffusion framework that synthesises realistic echocardiography videos conditioned on self-supervised motion features. To extract these features, we design the Motion and Appearance Feature Extractor (MAFE), which disentangles motion and appearance representations from videos. Feature learning is further enhanced by two auxiliary objectives: a re-identification loss guided by pseudo appearance features and an optical flow loss guided by pseudo flow fields. Evaluated on the EchoNet-Dynamic dataset, MCDM achieves competitive video generation performance, producing temporally coherent and clinically realistic sequences without reliance on manual labels. These results demonstrate the potential of self-supervised conditioning for scalable echocardiography synthesis. Our code is available at this https URL.
Abstract (translated)
超声心动图是评估心脏功能的非侵入性和实时方法，但受隐私限制和专家标注复杂性影响的数据标记不足，仍然是深度学习方法面临的主要障碍。我们提出了一种无标签的潜在扩散框架——运动条件扩散模型（MCDM），该模型可以在自监督运动特征条件下合成逼真的超声心动图视频。为了提取这些特征，我们设计了运动与外观特征提取器（MAFE），它可以将运动和外观表示从视频中分离出来。通过两个辅助目标进一步增强了特性学习：一个由伪外观特征引导的重新识别损失，以及一个由伪流场引导的光流损失。 在EchoNet-Dynamic数据集上进行评估时，MCDM达到了竞争性的视频生成性能，能够产生时间一致性高且临床真实的序列，并且无需依赖手动标签。这些结果展示了自监督条件对于可扩展超声心动图合成的潜力。我们的代码可在[此处](https://this https URL)获取。
URL
https://arxiv.org/abs/2512.09418
PDF
-
What really matters for person re-identification? A Mixture-of-Experts Framework for Semantic Attribute Importance
2025-12-09 15:14:28Athena Psalta, Vasileios Tsironis, Konstantinos KarantzalosAbstract
State-of-the-art person re-identification methods achieve impressive accuracy but remain largely opaque, leaving open the question: which high-level semantic attributes do these models actually rely on? We propose MoSAIC-ReID, a Mixture-of-Experts framework that systematically quantifies the importance of pedestrian attributes for re-identification. Our approach uses LoRA-based experts, each linked to a single attribute, and an oracle router that enables controlled attribution analysis. While MoSAIC-ReID achieves competitive performance on Market-1501 and DukeMTMC under the assumption that attribute annotations are available at test time, its primary value lies in providing a large-scale, quantitative study of attribute importance across intrinsic and extrinsic cues. Using generalized linear models, statistical tests, and feature-importance analyses, we reveal which attributes, such as clothing colors and intrinsic characteristics, contribute most strongly, while infrequent cues (e.g. accessories) have limited effect. This work offers a principled framework for interpretable ReID and highlights the requirements for integrating explicit semantic knowledge in practice. Code is available at this https URL
Abstract (translated)
最先进的人员重新识别方法实现了令人印象深刻的准确度，但其内部运作仍相对不透明，这引发了一个问题：这些模型实际上依赖哪些高层次的语义属性？我们提出了MoSAIC-ReID，这是一种Mixture-of-Experts（专家混合）框架，能够系统地量化行人属性在重新识别中的重要性。我们的方法使用基于LoRA（低秩适应）的专家模块，每个模块与单一属性相关联，并且采用了一个oracle router（预言路由器），它能进行受控归因分析。 尽管假设测试时可以获取到属性标注的情况下，MoSAIC-ReID在Market-1501和DukeMTMC数据集上达到了竞争力的性能，但其主要价值在于通过大规模、定量研究来揭示跨内在和外在线索的各种属性的重要性。我们利用广义线性模型、统计测试以及特征重要度分析方法，揭示了哪些属性（如衣物颜色及内在特性）贡献最为显著，而那些不常见的提示（例如配饰）则影响有限。 这项工作为可解释的人员重新识别提供了一个原则性的框架，并强调了在实践中整合显式语义知识的需求。代码可以在提供的网址上获取。
URL
https://arxiv.org/abs/2512.08697
PDF
-
Team-Aware Football Player Tracking with SAM: An Appearance-Based Approach to Occlusion Recovery
2025-12-09 10:40:17Chamath Ranasinghe, Uthayasanker ThayasivamAbstract
Football player tracking is challenged by frequent occlusions, similar appearances, and rapid motion in crowded scenes. This paper presents a lightweight SAM-based tracking method combining the Segment Anything Model (SAM) with CSRT trackers and jersey color-based appearance models. We propose a team-aware tracking system that uses SAM for precise initialization and HSV histogram-based re-identification to improve occlusion recovery. Our evaluation measures three dimensions: processing speed (FPS and memory), tracking accuracy (success rate and box stability), and robustness (occlusion recovery and identity consistency). Experiments on football video sequences show that the approach achieves 7.6-7.7 FPS with stable memory usage (~1880 MB), maintaining 100 percent tracking success in light occlusions and 90 percent in crowded penalty-box scenarios with 5 or more players. Appearance-based re-identification recovers 50 percent of heavy occlusions, demonstrating the value of domain-specific cues. Analysis reveals key trade-offs: the SAM + CSRT combination provides consistent performance across crowd densities but struggles with long-term occlusions where players leave the frame, achieving only 8.66 percent re-acquisition success. These results offer practical guidelines for deploying football tracking systems under resource constraints, showing that classical tracker-based methods work well with continuous visibility but require stronger re-identification mechanisms for extended absences.
Abstract (translated)
足球运动员追踪面临频繁遮挡、相似外观和快速运动等挑战。本文提出了一种基于Segment Anything Model (SAM) 的轻量级跟踪方法，结合了CSRT跟踪器和球衣颜色外观模型。我们提出了一个团队感知的跟踪系统，利用SAM进行精确初始化，并采用HSV直方图重识别技术来改进遮挡恢复。 评估标准包括处理速度（FPS 和内存使用）、追踪准确性（成功率和框稳定性）以及鲁棒性（遮挡恢复能力和身份一致性）。实验结果显示，在足球视频序列上，所提出的方法实现了7.6-7.7 FPS的速度，并且在各种情况下的内存使用量保持稳定（约1880 MB）。该方法在轻度遮挡情况下实现了100%的跟踪成功率，在包含5名或更多球员的拥挤点球区场景中也能达到90%的成功率。基于外观特征重识别技术恢复了50%的重大遮挡情况，这表明领域特定线索的重要性。 分析揭示了一些关键的权衡：SAM+CSRT组合在不同人群密度下表现出稳定的性能，但在长时间遮挡的情况下（当球员离开画面时），重新获取成功率仅为8.66%，显示出该方法在此类情况下的局限性。这些结果为在资源受限条件下部署足球追踪系统提供了实用指导，表明经典跟踪器方法适用于持续可见的情况，但对于长期缺席的场景，则需要更强大的重识别机制。 综上所述，所提出的方法通过结合领域特定线索和轻量级模型，在处理复杂且多变的比赛环境中展现出良好的性能和实用性。
URL
https://arxiv.org/abs/2512.08467
PDF
-
Towards Visual Re-Identification of Fish using Fine-Grained Classification for Electronic Monitoring in Fisheries
2025-12-09 09:33:53Samitha Nuwan Thilakarathna, Ercan Avsar, Martin Mathias Nielsen, Malte PedersenAbstract
Accurate fisheries data are crucial for effective and sustainable marine resource management. With the recent adoption of Electronic Monitoring (EM) systems, more video data is now being collected than can be feasibly reviewed manually. This paper addresses this challenge by developing an optimized deep learning pipeline for automated fish re-identification (Re-ID) using the novel AutoFish dataset, which simulates EM systems with conveyor belts with six similarly looking fish species. We demonstrate that key Re-ID metrics (R1 and mAP@k) are substantially improved by using hard triplet mining in conjunction with a custom image transformation pipeline that includes dataset-specific normalization. By employing these strategies, we demonstrate that the Vision Transformer-based Swin-T architecture consistently outperforms the Convolutional Neural Network-based ResNet-50, achieving peak performance of 41.65% mAP@k and 90.43% Rank-1 accuracy. An in-depth analysis reveals that the primary challenge is distinguishing visually similar individuals of the same species (Intra-species errors), where viewpoint inconsistency proves significantly more detrimental than partial occlusion. The source code and documentation are available at: this https URL
Abstract (translated)
精确的渔业数据对于有效和可持续的海洋资源管理至关重要。随着最近采用电子监控（EM）系统的广泛应用，现在收集到的视频数据量已超出人工审查的能力范围。本文通过开发一种优化的深度学习流水线来应对这一挑战，该管道用于使用新型AutoFish数据集自动识别鱼类，该数据集模拟了具有六种外观相似鱼种传送带的电子监控系统。我们展示了通过结合硬三元组挖掘和定制的图像转换流程（包括特定于数据集的标准化）可以显著提高关键再识别指标（R1 和 mAP@k）。通过采用这些策略，基于视觉变压器的Swin-T架构在实验中始终优于基于卷积神经网络的ResNet-50，达到了41.65% 的mAP@k和90.43% 的Rank-1精度。深入分析表明，主要挑战在于区分同一物种中的外观相似个体（种内错误），其中视角不一致比部分遮挡更具破坏性。源代码和文档可在以下网址获得：[此URL]
URL
https://arxiv.org/abs/2512.08400
PDF
-
Animal Re-Identification on Microcontrollers
2025-12-09 03:09:22Yubo Chen, Di Zhao, Yun Sing Koh, Talia XuAbstract
Camera-based animal re-identification (Animal Re-ID) can support wildlife monitoring and precision livestock management in large outdoor environments with limited wireless connectivity. In these settings, inference must run directly on collar tags or low-power edge nodes built around microcontrollers (MCUs), yet most Animal Re-ID models are designed for workstations or servers and are too large for devices with small memory and low-resolution inputs. We propose an on-device framework. First, we characterise the gap between state-of-the-art Animal Re-ID models and MCU-class hardware, showing that straightforward knowledge distillation from large teachers offers limited benefit once memory and input resolution are constrained. Second, guided by this analysis, we design a high-accuracy Animal Re-ID architecture by systematically scaling a CNN-based MobileNetV2 backbone for low-resolution inputs. Third, we evaluate the framework with a real-world dataset and introduce a data-efficient fine-tuning strategy to enable fast adaptation with just three images per animal identity at a new site. Across six public Animal Re-ID datasets, our compact model achieves competitive retrieval accuracy while reducing model size by over two orders of magnitude. On a self-collected cattle dataset, the deployed model performs fully on-device inference with only a small accuracy drop and unchanged Top-1 accuracy relative to its cluster version. We demonstrate that practical, adaptable Animal Re-ID is achievable on MCU-class devices, paving the way for scalable deployment in real field environments.
Abstract (translated)
基于摄像头的动物再识别（Animal Re-ID）可以支持野生动物监测和大型户外环境中的精准畜牧业管理，这些环境中无线连接有限。在这种情况下，推理必须直接在项圈标签或围绕微控制器（MCU）构建的低功耗边缘节点上运行。然而，大多数动物再识别模型都是为工作站或服务器设计的，并且对于内存小、输入分辨率低的设备来说太大了。 为此，我们提出了一种端到端框架。首先，我们描述了最先进的Animal Re-ID模型与MCU类硬件之间的差距，表明在受到内存和输入分辨率限制的情况下，从大型教师进行直接的知识蒸馏提供的收益有限。其次，根据这一分析，我们设计了一个高精度的动物再识别架构，通过系统地缩放基于CNN的MobileNetV2骨干网以适应低分辨率输入来实现。第三，我们在一个真实世界的数据集上评估了该框架，并引入了一种数据高效微调策略，使得仅用每只动物三个新地点的新图像即可快速适应环境。 在六个公开的Animal Re-ID数据集中，我们的紧凑型模型实现了具有竞争力的检索准确率，同时将模型大小减少了两个数量级。在一个自收集的牛数据集上，部署的模型能够完全进行设备端推理，并且仅出现了较小的准确性下降，相对于集群版本来说Top-1精度没有变化。 我们证明了在MCU类设备上实现实用、可适应的动物再识别是可行的，为大规模部署到实际野外环境铺平了道路。
URL
https://arxiv.org/abs/2512.08198
PDF
-
GorillaWatch: An Automated System for In-the-Wild Gorilla Re-Identification and Population Monitoring
2025-12-08 17:58:20Maximilian Schall, Felix Leonard Kn\"ofel, Noah Elias K\"onig, Jan Jonas Kubeler, Maximilian von Klinski, Joan Wilhelm Linnemann, Xiaoshi Liu, Iven Jelle Schlegelmilch, Ole Woyciniuk, Alexandra Schild, Dante Wasmuht, Magdalena Bermejo Espinet, German Illera Basas, Gerard de MeloAbstract
Monitoring critically endangered western lowland gorillas is currently hampered by the immense manual effort required to re-identify individuals from vast archives of camera trap footage. The primary obstacle to automating this process has been the lack of large-scale, "in-the-wild" video datasets suitable for training robust deep learning models. To address this gap, we introduce a comprehensive benchmark with three novel datasets: Gorilla-SPAC-Wild, the largest video dataset for wild primate re-identification to date; Gorilla-Berlin-Zoo, for assessing cross-domain re-identification generalization; and Gorilla-SPAC-MoT, for evaluating multi-object tracking in camera trap footage. Building on these datasets, we present GorillaWatch, an end-to-end pipeline integrating detection, tracking, and re-identification. To exploit temporal information, we introduce a multi-frame self-supervised pretraining strategy that leverages consistency in tracklets to learn domain-specific features without manual labels. To ensure scientific validity, a differentiable adaptation of AttnLRP verifies that our model relies on discriminative biometric traits rather than background correlations. Extensive benchmarking subsequently demonstrates that aggregating features from large-scale image backbones outperforms specialized video architectures. Finally, we address unsupervised population counting by integrating spatiotemporal constraints into standard clustering to mitigate over-segmentation. We publicly release all code and datasets to facilitate scalable, non-invasive monitoring of endangered species
Abstract (translated)
监测极度濒危的西部低地大猩猩目前受到大量手工劳动的影响，这些工作是为了从大量的相机陷阱视频资料中重新识别个体。自动处理这一过程的主要障碍是缺乏适合训练稳健深度学习模型的大规模、真实环境下的视频数据集。为了填补这一空白，我们引入了一个全面的基准，并提供了三个新的数据集：Gorilla-SPAC-Wild 是迄今为止最大的用于野外灵长类动物再识别的视频数据集；Gorilla-Berlin-Zoo 用于评估跨域再识别泛化能力；以及 Gorilla-SPAC-MoT，用于评估相机陷阱视频中的多目标跟踪性能。基于这些数据集，我们提出了 GorillaWatch，一个端到端的工作流程，整合了检测、追踪和再识别功能。 为了利用时间信息，我们引入了一种跨多个帧的自监督预训练策略，该策略利用轨迹的一致性来学习领域特定特征，而无需手动标签。为确保科学有效性，我们采用可微分的 AttnLRP 来验证我们的模型是否依赖于有鉴别性的生物标志特征而非背景相关因素。 广泛的基准测试随后证明，从大规模图像骨干网络中聚合特征优于专门针对视频架构的方法。最后，为了处理无监督的人口计数问题，我们将时空约束整合到标准聚类中以减少过度分割现象。 我们公开发布所有代码和数据集，以便为濒危物种提供可扩展、非侵入性的监测手段。
URL
https://arxiv.org/abs/2512.07776
PDF
-
Modality-Aware Bias Mitigation and Invariance Learning for Unsupervised Visible-Infrared Person Re-Identification
2025-12-08 17:42:28Menglin Wang, Xiaojin Gong, Jiachen Li, Genlin JiAbstract
Unsupervised visible-infrared person re-identification (USVI-ReID) aims to match individuals across visible and infrared cameras without relying on any annotation. Given the significant gap across visible and infrared modality, estimating reliable cross-modality association becomes a major challenge in USVI-ReID. Existing methods usually adopt optimal transport to associate the intra-modality clusters, which is prone to propagating the local cluster errors, and also overlooks global instance-level relations. By mining and attending to the visible-infrared modality bias, this paper focuses on addressing cross-modality learning from two aspects: bias-mitigated global association and modality-invariant representation learning. Motivated by the camera-aware distance rectification in single-modality re-ID, we propose modality-aware Jaccard distance to mitigate the distance bias caused by modality discrepancy, so that more reliable cross-modality associations can be estimated through global clustering. To further improve cross-modality representation learning, a `split-and-contrast' strategy is designed to obtain modality-specific global prototypes. By explicitly aligning these prototypes under global association guidance, modality-invariant yet ID-discriminative representation learning can be achieved. While conceptually simple, our method obtains state-of-the-art performance on benchmark VI-ReID datasets and outperforms existing methods by a significant margin, validating its effectiveness.
Abstract (translated)
无监督可见光-红外重识别（USVI-ReID）旨在不依赖任何标注的情况下，在可见光和红外摄像机之间匹配个体。鉴于可见光与红外模态之间的显著差异，估计可靠的跨模态关联成为USVI-ReID的主要挑战之一。现有方法通常采用最优传输来关联单个模态下的聚类，这种做法容易传播局部集群误差，并且忽视了全局实例级关系。 本文通过挖掘和关注可见光-红外模态偏差，从两个方面解决了跨模态学习问题：减少偏差的全局关联与模态不变表示学习。受单一模态重识别中摄像机感知距离校正的启发，我们提出了一种模态感知的雅克距离（modality-aware Jaccard distance），用于缓解由模态差异引起的距离偏差，从而通过全局聚类估计出更可靠的跨模态关联。 为了进一步改进跨模态表示学习，设计了一种“分离并对比”策略来获取特定于每个模态的全局原型。通过在全局关联引导下明确对齐这些原型，可以实现既模态不变又具有身份区分能力的表示学习。尽管概念简单，本文提出的方法在基准VI-ReID数据集上取得了最先进的性能，并且显著优于现有方法，验证了其有效性。
URL
https://arxiv.org/abs/2512.07760
PDF
-
Training-free Clothing Region of Interest Self-correction for Virtual Try-On
2025-12-08 03:22:43Shengjie Lu, Zhibin Wan, Jiejie Liu, Quan Zhang, Mingjie SunAbstract
VTON (Virtual Try-ON) aims at synthesizing the target clothing on a certain person, preserving the details of the target clothing while keeping the rest of the person unchanged. Existing methods suffer from the discrepancies between the generated clothing results and the target ones, in terms of the patterns, textures and boundaries. Therefore, we propose to use an energy function to impose constraints on the attention map extracted through the generation process. Thus, at each generation step, the attention can be more focused on the clothing region of interest, thereby influencing the generation results to be more consistent with the target clothing details. Furthermore, to address the limitation that existing evaluation metrics concentrate solely on image realism and overlook the alignment with target elements, we design a new metric, Virtual Try-on Inception Distance (VTID), to bridge this gap and ensure a more comprehensive assessment. On the VITON-HD and DressCode datasets, our approach has outperformed the previous state-of-the-art (SOTA) methods by 1.4%, 2.3%, 12.3%, and 5.8% in the traditional metrics of LPIPS, FID, KID, and the new VTID metrics, respectively. Additionally, by applying the generated data to downstream Clothing-Change Re-identification (CC-Reid) methods, we have achieved performance improvements of 2.5%, 1.1%, and 1.6% on the LTCC, PRCC, VC-Clothes datasets in the metrics of Rank-1. The code of our method is public at this https URL.
Abstract (translated)
VTON（虚拟试穿）旨在将目标衣物合成为特定人物身上的效果，同时保留目标衣物的细节而不改变人体其他部分。现有方法在生成衣物结果与目标衣物之间的模式、纹理和边界方面存在不一致的问题。因此，我们提出使用能量函数来对通过生成过程提取的关注图施加约束条件。这样，在每次生成步骤中，注意力可以更集中于感兴趣的服装区域，从而影响生成的结果更加符合目标衣物的细节。 此外，为了解决现有评估指标仅关注图像现实性而忽视与目标元素对齐的问题，我们设计了一个新的度量标准——虚拟试穿Inception距离（VTID），以此来弥合这一差距，并确保更全面的评估。在VITON-HD和DressCode数据集上，我们的方法分别在传统的LPIPS、FID、KID指标以及新推出的VTID指标上优于之前的最先进（SOTA）方法1.4%、2.3%、12.3%和5.8%。此外，在下游的服装变化再识别（CC-Reid）方法中应用生成的数据，我们在LTCC、PRCC、VC-Clothes数据集上的Rank-1指标分别取得了2.5%、1.1%和1.6%的性能提升。 我们的方法代码可在[此处](https://example.com)获得。
URL
https://arxiv.org/abs/2512.07126
PDF
-
When Gender is Hard to See: Multi-Attribute Support for Long-Range Recognition
2025-12-06 13:12:07Nzakiese Mbongo, Kailash A. Hambarde, Hugo Proen\c{c}aAbstract
Accurate gender recognition from extreme long-range imagery remains a challenging problem due to limited spatial resolution, viewpoint variability, and loss of facial cues. For such purpose, we present a dual-path transformer framework that leverages CLIP to jointly model visual and attribute-driven cues for gender recognition at a distance. The framework integrates two complementary streams: (1) a direct visual path that refines a pre-trained CLIP image encoder through selective fine-tuning of its upper layers, and (2) an attribute-mediated path that infers gender from a set of soft-biometric prompts (e.g., hairstyle, clothing, accessories) aligned in the CLIP text-image space. Spatial channel attention modules further enhance discriminative localization under occlusion and low resolution. To support large-scale evaluation, we construct U-DetAGReID, a unified long-range gender dataset derived from DetReIDx and AG-ReID.v2, harmonized under a consistent ternary labeling scheme (Male, Female, Unknown). Extensive experiments suggest that the proposed solution surpasses state-of-the-art person-attribute and re-identification baselines across multiple metrics (macro-F1, accuracy, AUC), with consistent robustness to distance, angle, and height variations. Qualitative attention visualizations confirm interpretable attribute localization and responsible abstention behavior. Our results show that language-guided dual-path learning offers a principled, extensible foundation for responsible gender recognition in unconstrained long-range scenarios.
Abstract (translated)
从极端远距离图像中进行准确的性别识别仍然是一个挑战，原因在于空间分辨率有限、视角变化以及面部线索丢失。为此，我们提出了一种双路径Transformer框架，该框架利用CLIP（对比语言-图像预训练模型）来同时建模视觉和属性驱动的提示，以实现远程性别识别。此框架整合了两条互补的数据流：(1) 一条直接视觉路径，通过选择性微调其上层结构来优化预训练的CLIP图像编码器；(2) 一个由属性中介的路径，从一组软生物特征提示（如发型、服装和配饰）中推断性别，这些提示在CLIP文本-图像空间中进行了对齐。此外，空间通道注意模块进一步增强了遮挡和低分辨率条件下的区分性定位。 为了支持大规模评估，我们构建了U-DetAGReID数据集，该数据集是从DetReIDx和AG-ReID.v2派生而来的统一远距离性别识别数据集，并在一致的三元标签体系（男性、女性、未知）下进行了调和。广泛的实验表明，所提出的解决方案在多种度量标准（宏F1分数、准确率、AUC）上超越了现有的人员属性和重识别基准方法，在不同距离、角度和高度变化的情况下均表现出稳健性。定性的注意可视化确认了可解释的属性定位及合理的放弃行为。 我们的研究结果表明，语言引导的双路径学习为在无约束远距离场景中进行负责任的性别识别提供了一个合理且可扩展的基础。
URL
https://arxiv.org/abs/2512.06426
PDF
-
Identity Clue Refinement and Enhancement for Visible-Infrared Person Re-Identification
2025-12-04 07:13:38Guoqing Zhang, Zhun Wang, Hairui Wang, Zhonglin Ye, Yuhui ZhengAbstract
Visible-Infrared Person Re-Identification (VI-ReID) is a challenging cross-modal matching task due to significant modality discrepancies. While current methods mainly focus on learning modality-invariant features through unified embedding spaces, they often focus solely on the common discriminative semantics across modalities while disregarding the critical role of modality-specific identity-aware knowledge in discriminative feature learning. To bridge this gap, we propose a novel Identity Clue Refinement and Enhancement (ICRE) network to mine and utilize the implicit discriminative knowledge inherent in modality-specific attributes. Initially, we design a Multi-Perception Feature Refinement (MPFR) module that aggregates shallow features from shared branches, aiming to capture modality-specific attributes that are easily overlooked. Then, we propose a Semantic Distillation Cascade Enhancement (SDCE) module, which distills identity-aware knowledge from the aggregated shallow features and guide the learning of modality-invariant features. Finally, an Identity Clues Guided (ICG) Loss is proposed to alleviate the modality discrepancies within the enhanced features and promote the learning of a diverse representation space. Extensive experiments across multiple public datasets clearly show that our proposed ICRE outperforms existing SOTA methods.
Abstract (translated)
可见光-红外人物重新识别（VI-ReID）是一项具有挑战性的跨模态匹配任务，由于存在显著的模态差异性。虽然当前的方法主要集中在通过统一嵌入空间学习模态不变特征上，但它们往往只关注各模态之间共同判别语义的同时忽略了特定模态身份感知知识在判别特征学习中的关键作用。为了填补这一空白，我们提出了一种新颖的身份线索精炼与增强（ICRE）网络来挖掘并利用特定模态属性中蕴含的隐性判别知识。 首先，我们设计了一个多感知特征精炼（MPFR）模块，该模块聚合了来自共享分支的浅层特征，旨在捕捉容易被忽视的特定于模态的属性。然后，我们提出了一个语义蒸馏级联增强（SDCE）模块，该模块从聚合的浅层特征中蒸馏出身份感知知识，并指导模态不变特征的学习过程。最后，提出了一种由身份线索引导（ICG）损失函数，以减轻增强后的特征中的模态差异，并促进多样表示空间的学习。 通过多个公共数据集进行的广泛实验清楚地表明，我们提出的ICRE方法优于现有的最先进的方法。
URL
https://arxiv.org/abs/2512.04522
PDF
-
Dual-level Modality Debiasing Learning for Unsupervised Visible-Infrared Person Re-Identification
2025-12-03 12:43:16Jiaze Li, Yan Lu, Bin Liu, Guojun Yin, Mang YeAbstract
Two-stage learning pipeline has achieved promising results in unsupervised visible-infrared person re-identification (USL-VI-ReID). It first performs single-modality learning and then operates cross-modality learning to tackle the modality discrepancy. Although promising, this pipeline inevitably introduces modality bias: modality-specific cues learned in the single-modality training naturally propagate into the following cross-modality learning, impairing identity discrimination and generalization. To address this issue, we propose a Dual-level Modality Debiasing Learning (DMDL) framework that implements debiasing at both the model and optimization levels. At the model level, we propose a Causality-inspired Adjustment Intervention (CAI) module that replaces likelihood-based modeling with causal modeling, preventing modality-induced spurious patterns from being introduced, leading to a low-biased model. At the optimization level, a Collaborative Bias-free Training (CBT) strategy is introduced to interrupt the propagation of modality bias across data, labels, and features by integrating modality-specific augmentation, label refinement, and feature alignment. Extensive experiments on benchmark datasets demonstrate that DMDL could enable modality-invariant feature learning and a more generalized model.
Abstract (translated)
在无监督的可见光-红外行人重识别（USL-VI-ReID）中，两阶段学习管道已经取得了显著成果。它首先进行单模态学习，然后执行跨模态学习以解决模态差异问题。尽管这一流程显示出前景，但不可避免地引入了模态偏见：在单一模态训练中学到的特定于某一模态的线索自然会传递到随后的跨模态学习中，从而损害身份鉴别能力和泛化能力。 为了解决这个问题，我们提出了一种双层级消偏学习（DMDL）框架，在模型和优化两个层面实施了消偏策略。在模型层面上，我们提出了一个因果启发调整干预（CAI）模块，该模块用因果建模替代基于似然性的建模方法，防止由特定模态导致的虚假模式被引入系统中，从而生成低偏见的模型。在优化层面上，则引入了一种协作无偏训练（CBT）策略，通过整合特定于某一模态的数据增强、标签精炼和特征对齐来中断数据、标签及特征之间的模态偏见传播。 广泛的基准数据集实验表明，DMDL框架能够实现模态不变的特征学习，并提高模型的泛化能力。
URL
https://arxiv.org/abs/2512.03745
PDF
-
MOS: Mitigating Optical-SAR Modality Gap for Cross-Modal Ship Re-Identification
2025-12-03 03:23:19Yujian Zhao, Hankun Liu, Guanglin NiuAbstract
Cross-modal ship re-identification (ReID) between optical and synthetic aperture radar (SAR) imagery has recently emerged as a critical yet underexplored task in maritime intelligence and surveillance. However, the substantial modality gap between optical and SAR images poses a major challenge for robust identification. To address this issue, we propose MOS, a novel framework designed to mitigate the optical-SAR modality gap and achieve modality-consistent feature learning for optical-SAR cross-modal ship ReID. MOS consists of two core components: (1) Modality-Consistent Representation Learning (MCRL) applies denoise SAR image procession and a class-wise modality alignment loss to align intra-identity feature distributions across modalities. (2) Cross-modal Data Generation and Feature fusion (CDGF) leverages a brownian bridge diffusion model to synthesize cross-modal samples, which are subsequently fused with original features during inference to enhance alignment and discriminability. Extensive experiments on the HOSS ReID dataset demonstrate that MOS significantly surpasses state-of-the-art methods across all evaluation protocols, achieving notable improvements of +3.0%, +6.2%, and +16.4% in R1 accuracy under the ALL to ALL, Optical to SAR, and SAR to Optical settings, respectively. The code and trained models will be released upon publication.
Abstract (translated)
光学和合成孔径雷达（SAR）图像之间的跨模态船舶再识别（ReID）最近已成为海事智能与监视领域中的一个关键但研究较少的任务。然而，光学图像和SAR图像之间显著的模态差异对稳健的身份识别构成了重大挑战。为了解决这个问题，我们提出了MOS框架，这是一种旨在减少光-SAR模态差距并实现光-SAR跨模态船舶ReID的一致性特征学习的新方法。 MOS包含两个核心组件： 1. **一致性表示学习（MCRL）**：应用去噪SAR图像处理技术和类别的模态对齐损失来调整同一身份在不同模态下的特征分布，从而实现跨模态内的特征一致。 2. **跨模态数据生成与特性融合（CDGF）**：采用布朗桥扩散模型合成跨模态样本，并在其推理过程中将这些样本与其原始特性相结合以提高一致性与可区分性。 在HOSS ReID数据集上进行的大量实验表明，MOS方法显著超越了所有评估协议下的现有最佳方法，在ALL to ALL、光学到SAR和SAR到光学设置下分别实现了+3.0%、+6.2% 和 +16.4% 的R1准确率提升。发布后的代码与训练好的模型将会公开提供。 该描述展示了MOS框架在解决跨模态船舶再识别挑战方面的创新性和有效性，特别是在填补光学和SAR图像之间差距方面具有显著优势。
URL
https://arxiv.org/abs/2512.03404
PDF
-
OmniPerson: Unified Identity-Preserving Pedestrian Generation
2025-12-02 09:24:34Changxiao Ma, Chao Yuan, Xincheng Shi, Yuzhuo Ma, Yongfei Zhang, Longkun Zhou, Yujia Zhang, Shangze Li, Yifan XuAbstract
Person re-identification (ReID) suffers from a lack of large-scale high-quality training data due to challenges in data privacy and annotation costs. While previous approaches have explored pedestrian generation for data augmentation, they often fail to ensure identity consistency and suffer from insufficient controllability, thereby limiting their effectiveness in dataset augmentation. To address this, We introduce OmniPerson, the first unified identity-preserving pedestrian generation pipeline for visible/infrared image/video ReID tasks. Our contributions are threefold: 1) We proposed OmniPerson, a unified generation model, offering holistic and fine-grained control over all key pedestrian attributes. Supporting RGB/IR modality image/video generation with any number of reference images, two kinds of person poses, and text. Also including RGB-to-IR transfer and image super-resolution abilities.2) We designed Multi-Refer Fuser for robust identity preservation with any number of reference images as input, making OmniPerson could distill a unified identity from a set of multi-view reference images, ensuring our generated pedestrians achieve high-fidelity pedestrian generation.3) We introduce PersonSyn, the first large-scale dataset for multi-reference, controllable pedestrian generation, and present its automated curation pipeline which transforms public, ID-only ReID benchmarks into a richly annotated resource with the dense, multi-modal supervision required for this task. Experimental results demonstrate that OmniPerson achieves SoTA in pedestrian generation, excelling in both visual fidelity and identity consistency. Furthermore, augmenting existing datasets with our generated data consistently improves the performance of ReID models. We will open-source the full codebase, pretrained model, and the PersonSyn dataset.
Abstract (translated)
人员重识别（ReID）面临缺乏大规模高质量训练数据的问题，这主要是由于数据隐私和标注成本的挑战。虽然之前的方法探索了行人生成以进行数据增强，但它们往往无法确保身份一致性，并且控制力不足，从而限制了在数据集扩充中的有效性。为解决这一问题，我们引入了OmniPerson，这是第一个统一的身份保持型行人生成管道，适用于可见光/红外图像和视频ReID任务。 我们的贡献有三点： 1. 我们提出了OmniPerson，一个统一的生成模型，提供对所有关键行人属性的整体性和细致控制。支持RGB/IR模态图像/视频生成，并可以使用任意数量的参考图片、两种类型的人体姿态以及文本作为输入。此外还具备从RGB到IR转换和图像超分辨率能力。 2. 我们设计了多参照融合器（Multi-Refer Fuser），用于在输入任意数量的参考图片时进行稳健的身份保持，使OmniPerson能够从一组多视角参考图集中提取统一身份，并确保我们生成的行人具有高保真度的人行者生成效果。 3. 我们引入了PersonSyn，这是第一个大规模数据集，专门针对可引用的可控性行人生成。还介绍了其自动编目管道，该管道可以将仅凭ID的公共ReID基准转换为完成密集且多模态监督所需的任务丰富注释资源。 实验结果表明，OmniPerson在行人的生成方面达到了最新的技术水平，在视觉保真度和身份一致性上都表现出色。此外，通过使用我们生成的数据增强现有数据集，能够持续提升ReID模型的性能。我们将开源完整的代码库、预训练模型以及PersonSyn数据集。
URL
https://arxiv.org/abs/2512.02554
PDF
-
MANTA: Physics-Informed Generalized Underwater Object Tracking
2025-11-28 17:59:06Suhas Srinath, Hemang Jamadagni, Aditya Chadrasekar, Prathosh APAbstract
Underwater object tracking is challenging due to wavelength dependent attenuation and scattering, which severely distort appearance across depths and water conditions. Existing trackers trained on terrestrial data fail to generalize to these physics-driven degradations. We present MANTA, a physics-informed framework integrating representation learning with tracking design for underwater scenarios. We propose a dual-positive contrastive learning strategy coupling temporal consistency with Beer-Lambert augmentations to yield features robust to both temporal and underwater distortions. We further introduce a multi-stage pipeline augmenting motion-based tracking with a physics-informed secondary association algorithm that integrates geometric consistency and appearance similarity for re-identification under occlusion and drift. To complement standard IoU metrics, we propose Center-Scale Consistency (CSC) and Geometric Alignment Score (GAS) to assess geometric fidelity. Experiments on four underwater benchmarks (WebUOT-1M, UOT32, UTB180, UWCOT220) show that MANTA achieves state-of-the-art performance, improving Success AUC by up to 6 percent, while ensuring stable long-term generalized underwater tracking and efficient runtime.
Abstract (translated)
URL
https://arxiv.org/abs/2511.23405
PDF
