IEEE transactions on biometrics, behavior, and identity science最新文献_第2页

Detecting LLM-Assisted Academic Dishonesty Using Keystroke Dynamics 使用击键动力学检测llm辅助学术不诚实

IF 4.4

IEEE transactions on biometrics, behavior, and identity science Pub Date : 2026-09-01 Epub Date: 2026-04-14 DOI: 10.1109/TBIOM.2026.3683979

Atharva Mehta;Rajesh Kumar;Aman Singla;Kartik Bisht;Yaman Kumar Singla;Rajiv Ratn Shah

{"title":"Detecting LLM-Assisted Academic Dishonesty Using Keystroke Dynamics","authors":"Atharva Mehta;Rajesh Kumar;Aman Singla;Kartik Bisht;Yaman Kumar Singla;Rajiv Ratn Shah","doi":"10.1109/TBIOM.2026.3683979","DOIUrl":"https://doi.org/10.1109/TBIOM.2026.3683979","url":null,"abstract":"The rapid adoption of generative AI tools has heightened concerns regarding academic integrity, as students increasingly engage in dishonest practices by copying or paraphrasing AI-generated content. Existing plagiarism detection systems, which rely primarily on text-intrinsic features, are ineffective at identifying AI-assisted or paraphrased submissions. Our prior conference work introduced a behavioral detection approach that leverages how text is produced, captured through keystroke dynamics, in addition to what is written, enabling discrimination between genuine and assisted writing. That study, conducted on keystroke data from 40 participants, demonstrated promising performance. This paper substantially extends and systemizes the prior work by: 1) expanding the dataset with 90 additional participants and introducing an explicit paraphrasing condition to model realistic plagiarism strategies; 2) formalizing a threat model and evaluating detection under adversarial and deception-oriented scenarios; and 3) performing a comprehensive empirical comparison against state-of-the-art text-only detectors and human evaluators. Experimental results demonstrate that keystroke-based models significantly outperform text-based approaches in practical deployment settings, while revealing limitations under more challenging adversarial conditions.","PeriodicalId":73307,"journal":{"name":"IEEE transactions on biometrics, behavior, and identity science","volume":"8 5","pages":"754-768"},"PeriodicalIF":4.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148961953","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Cancelable Iris Recognition Scheme Based on Positive–Negative Mapping and Negative Selection 基于正负映射和负选择的可取消虹膜识别方案

IF 4.4

IEEE transactions on biometrics, behavior, and identity science Pub Date : 2026-09-01 Epub Date: 2026-03-22 DOI: 10.1109/TBIOM.2026.3696143

Qianrong Zheng;Baotong Ren;Jianwen Xiang;Rui Hao;Songsong Liao;Dongdong Zhao

{"title":"Cancelable Iris Recognition Scheme Based on Positive–Negative Mapping and Negative Selection","authors":"Qianrong Zheng;Baotong Ren;Jianwen Xiang;Rui Hao;Songsong Liao;Dongdong Zhao","doi":"10.1109/TBIOM.2026.3696143","DOIUrl":"https://doi.org/10.1109/TBIOM.2026.3696143","url":null,"abstract":"Iris recognition technology is widely used in identity verification and other fields due to its high accuracy and strong security. However, with the popularization of the technology, the privacy protection of iris data has become increasingly prominent. Existing systems are often difficult to protect personal data privacy while guaranteeing recognition accuracy, especially when facing data leakage and attacks, iris features cannot be modified once leaked, which is extremely risky. Therefore, proposing an efficient and accurate protection scheme that can ensure the security of iris data has become an important issue that needs to be solved urgently. In this paper, we propose an iris template protection framework based on positive-negative mapping and the negative selective algorithm, called the IrisPN-NS. The framework effectively protects iris data by constructing a complex system of inequality equations and combining it with the negative selection algorithm, thus increasing the difficulty for attackers to crack. Based on this framework, we propose two iris template protection methods, IrisPNM-NS and IrisPNS-NS. We conducted experiments on the CASIA-IrisV3-Interval, CASIA-IrisV4-Lamp, and IIT Delhi Iris datasets. The experimental results show that the scheme achieves high performance and effectively resists the attack of the greedy algorithm, while satisfying the requirements of irreversibility, revocability, and unlinkability.","PeriodicalId":73307,"journal":{"name":"IEEE transactions on biometrics, behavior, and identity science","volume":"8 5","pages":"960-978"},"PeriodicalIF":4.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148961860","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Lightweight Cross-Spectral Face Recognition via Contrastive Alignment and Distillation 基于对比对准和蒸馏的轻型交叉光谱人脸识别

IF 4.4

IEEE transactions on biometrics, behavior, and identity science Pub Date : 2026-09-01 Epub Date: 2026-03-08 DOI: 10.1109/TBIOM.2026.3691473

Anjith George;Sébastien Marcel

引用次数: 0

FaceLiVTv2: An Improved Hybrid Architecture for Efficient Mobile Face Recognition FaceLiVTv2：一种用于高效移动人脸识别的改进混合架构

IF 4.4

IEEE transactions on biometrics, behavior, and identity science Pub Date : 2026-09-01 Epub Date: 2026-03-05 DOI: 10.1109/TBIOM.2026.3690540

Novendra Setyawan;Chi-Chia Sun;Mao-Hsiu Hsu;Wen-Kai Kuo;Jun-Wei Hsieh

{"title":"FaceLiVTv2: An Improved Hybrid Architecture for Efficient Mobile Face Recognition","authors":"Novendra Setyawan;Chi-Chia Sun;Mao-Hsiu Hsu;Wen-Kai Kuo;Jun-Wei Hsieh","doi":"10.1109/TBIOM.2026.3690540","DOIUrl":"https://doi.org/10.1109/TBIOM.2026.3690540","url":null,"abstract":"Lightweight face recognition is increasingly important for deployment on edge and mobile devices, where strict constraints on latency, memory, and energy consumption must be met alongside reliable accuracy. Although recent hybrid CNN-Transformer architectures have advanced global context modeling, striking an effective balance between recognition performance and computational efficiency remains an open challenge. In this work, we present FaceLiVTv2, an improved version of our FaceLiVT hybrid architecture designed for efficient global–local feature interaction in mobile face recognition. At its core is Lite MHLA, a lightweight global token interaction module that replaces the original multi-layer attention design with multi-head linear token projections and affine rescale transformations, reducing redundancy while preserving representational diversity across heads. We further integrate Lite MHLA into a unified RepMix block that coordinates local and global feature interactions and adopts global deepthwise convolution for adaptive spatial aggregation in the embedding stage. Under our experimental setup, results on LFW, CA-LFW, CP-LFW, CFP-FP, AgeDB-30, and IJB show that FaceLiVTv2 consistently improves the accuracy-efficiency trade-off over existing lightweight methods. Notably, FaceLiVTv2 reduces mobile inference latency by 22% relative to FaceLiVTv1, achieves speedups of up to 30.8% over GhostFaceNets on mobile devices, and delivers 20-41% latency improvements over EdgeFace and KANFace across platforms while maintaining higher recognition accuracy. These results demonstrate that FaceLiVTv2 offers a practical and deployable solution for real-time face recognition. Code is available at <uri>https://github.com/novendrastywn/FaceLiVT</uri>","PeriodicalId":73307,"journal":{"name":"IEEE transactions on biometrics, behavior, and identity science","volume":"8 5","pages":"905-918"},"PeriodicalIF":4.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148961884","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Morph Detection as Anomalies in the Compressed Frequency Domain 作为压缩频域异常的形态检测

IF 4.4

IEEE transactions on biometrics, behavior, and identity science Pub Date : 2026-09-01 Epub Date: 2026-03-15 DOI: 10.1109/TBIOM.2026.3692617

Roberto Leyva;Carsten Maple;Victor Sanchez

{"title":"Morph Detection as Anomalies in the Compressed Frequency Domain","authors":"Roberto Leyva;Carsten Maple;Victor Sanchez","doi":"10.1109/TBIOM.2026.3692617","DOIUrl":"https://doi.org/10.1109/TBIOM.2026.3692617","url":null,"abstract":"Among the severe threats to Face Recognition Systems (FRS), morphs attacks remain challenging and difficult to mitigate. This difficulty stems from the high realism in morphed images, which can deceive both human operators and standard FRS. In this paper, we propose to detect morphed face images as anomalies. Specifically, instead of training a binary classifier with bona fide and morphed images, our method only requires learning the data distribution of those samples that are deemed to be <italic>normal</i>; i.e. a set of bona fide images. Once trained, morphs are detected as outliers or <italic>abnormal</i> samples. Our method relies on the analysis of the frequency power spectrum to generate a descriptive latent space, which is then reduced via autoencoders into compact and descriptive embeddings. These embeddings are used to generate probability distributions of the observed data. Our method manages to detect morphs generated by several common techniques without prior knowledge of their generation process and without relying on any training morphed images. It achieves state-of-the-art performance on the FRLL dataset and very competitive performance on the SMDD dataset and the Morphed Flick Faces High Quality (MFFHQ), which is a new dataset of morphs generated from the FFHQ dataset. Our evaluation results confirm the strength and practicality of the anomaly detection framework in the <italic>compressed</i> frequency domain for the morph attack detection task.","PeriodicalId":73307,"journal":{"name":"IEEE transactions on biometrics, behavior, and identity science","volume":"8 5","pages":"919-930"},"PeriodicalIF":4.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148961893","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Aerial-Ground Video-Based Person Re-Identification With Neural ODE-Enhanced Fusion 基于神经ode增强融合的地空视频人物再识别

IF 4.4

IEEE transactions on biometrics, behavior, and identity science Pub Date : 2026-09-01 Epub Date: 2026-03-28 DOI: 10.1109/TBIOM.2026.3697779

Huy Nguyen;Kien Nguyen;Akila Pemasiri;Clinton Fookes;Sridha Sridharan

{"title":"Aerial-Ground Video-Based Person Re-Identification With Neural ODE-Enhanced Fusion","authors":"Huy Nguyen;Kien Nguyen;Akila Pemasiri;Clinton Fookes;Sridha Sridharan","doi":"10.1109/TBIOM.2026.3697779","DOIUrl":"https://doi.org/10.1109/TBIOM.2026.3697779","url":null,"abstract":"Person re-identification (Re-ID) across visible and infrared modalities is crucial for 24-hour surveillance systems, but existing datasets primarily focus on ground-level perspectives. While ground-based IR systems offer nighttime capabilities, they suffer from occlusions, limited coverage, and vulnerability to obstructions—problems that aerial perspectives uniquely solve. To address these limitations, we introduce AG-VPReID.VIR, the first aerial-ground cross-modality video-based person Re-ID dataset. This dataset captures 1,837 identities across 4,861 tracklets (124,855 frames) using both UAV-mounted and fixed CCTV cameras in RGB and infrared modalities. AG-VPReID.VIR presents unique challenges including cross-viewpoint variations, modality discrepancies, and temporal dynamics. We propose TCC-VPReID, a novel three-stream architecture designed to address the joint challenges of cross-platform and cross-modality person Re-ID. We enhance this with ODE-Fusion, a neural ODE framework for fusing paired RGB-IR captures from the same platform, facilitating effective cross-modal feature fusion through continuous state evolution. Our approach bridges the domain gaps through style-robust feature learning, memory-based cross-view adaptation, intermediary-guided temporal modeling, and ODE-based fusion. Experiments show that AG-VPReID.VIR presents distinctive challenges compared to existing datasets, with our enhanced TCC-VPReID framework achieving significant performance gains across multiple evaluation protocols. Dataset and code will be made available.","PeriodicalId":73307,"journal":{"name":"IEEE transactions on biometrics, behavior, and identity science","volume":"8 5","pages":"780-791"},"PeriodicalIF":4.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148961935","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Spatiotemporal Graph Latent Diffusion Models for Human Action Synthesis 人类行为综合的时空图潜在扩散模型

IF 4.4

IEEE transactions on biometrics, behavior, and identity science Pub Date : 2026-09-01 Epub Date: 2026-04-03 DOI: 10.1109/TBIOM.2026.3680677

Bruno Degardin;Vasco Lopes;João Neves;Hugo Proença

{"title":"Spatiotemporal Graph Latent Diffusion Models for Human Action Synthesis","authors":"Bruno Degardin;Vasco Lopes;João Neves;Hugo Proença","doi":"10.1109/TBIOM.2026.3680677","DOIUrl":"https://doi.org/10.1109/TBIOM.2026.3680677","url":null,"abstract":"Generating natural human actions and behaviours remains a complex task, encompassing first, the refinement of generated forms; second, the enrichment of their diversity; and third, achieving temporal flexibility. This complexity is especially evident in the task of synthesising lifelike body movements tailored to specific actions, often referred to as action conditioning. This paper introduces GLDM, a new architecture that builds on Latent Diffusion Models (DMs) and Graph Convolutional Networks (GCNs) to synthesise human motions effectively. By decomposing the process of motion formation into a sequence of denoising graph autoencoders (GAEs) within a graph latent space, it is possible to generate unconstrained body movements while improving sample quality, diversity, conditioning and temporal flexibility. The experiments carried out in three well-known datasets show that GLDM notably outperforms state-of-the-art approaches in terms of distribution quality metrics while having the ability to generate over 120 distinct actions and behaviours, including text prompt conditioning. Furthermore, it is demonstrated that the improvements attained in the generation of synthetic behaviours allow the increase of the accuracy of action recognition methods when trained on these data.","PeriodicalId":73307,"journal":{"name":"IEEE transactions on biometrics, behavior, and identity science","volume":"8 5","pages":"847-856"},"PeriodicalIF":4.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148961939","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Longitudinal Evaluation of Child Fingerprint Recognition: Time Interval Up to Eight Years 儿童指纹识别的纵向评价：时间间隔长达8年

IF 4.4

IEEE transactions on biometrics, behavior, and identity science Pub Date : 2026-09-01 Epub Date: 2026-03-04 DOI: 10.1109/TBIOM.2026.3690014

Mst Rumana Sumi;Stephanie Schuckers

{"title":"Longitudinal Evaluation of Child Fingerprint Recognition: Time Interval Up to Eight Years","authors":"Mst Rumana Sumi;Stephanie Schuckers","doi":"10.1109/TBIOM.2026.3690014","DOIUrl":"https://doi.org/10.1109/TBIOM.2026.3690014","url":null,"abstract":"Child fingerprint recognition systems face unique challenges due to the rapid physiological changes associated with growth, making long-term recognition difficult. This study is focused on a comprehensive evaluation of fingerprint recognition performance over time, utilizing a longitudinal dataset comprising approximately 40K fingerprint images collected every six months over 8 years from 267 children aged 4 to 18 years. With the dataset, this study focused on the impact of aging, i.e., the variations in accuracy due to the increasing time gap between reference and probe samples. Additionally, the study assessed the effectiveness of customized Preciozzi’s scaling and VeriFinger’s fingerprint scaling methods, designed to adjust a fingerprint to compensate for changes related to the growth of a fingerprint. Despite significant aging effects in the 4–8-year age group, our findings reveal that a 4-year-old child remains recognizable for up to 48 months with a TAR of 97.4% at 0.1% FAR and up to 60 months with a TAR of 90.9% at 0.1% FAR without any scaling due to growth. Scaling techniques effectively mitigated decreases in performance, maintaining a TAR of 99.3% at 0.1% FAR for up to 90 months. Additionally, the study highlights that scaling is not strictly essential for children over 8 years of age up to 96 months but remains beneficial for achieving near-perfect accuracy (99–100%) over extended periods, especially for the 9–11-year age group. Linear Mixed-Effects Models revealed key predictors of comparison score variability, including time gap, enrollment age, and image quality, while accounting for their interactions and contributions to recognition performance. This study offers valuable insights into the longitudinal performance of child fingerprint recognition systems, bridging gaps in biometric research and paving the way for policy development and advanced technical solutions to enhance child safety and identification worldwide.","PeriodicalId":73307,"journal":{"name":"IEEE transactions on biometrics, behavior, and identity science","volume":"8 5","pages":"892-904"},"PeriodicalIF":4.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148961843","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

HiPo-Gait: Hierarchical Pose Model Decoupling for Gait Recognition hipo -步态：用于步态识别的分层姿态模型解耦

IF 4.4

IEEE transactions on biometrics, behavior, and identity science Pub Date : 2026-09-01 Epub Date: 2026-04-17 DOI: 10.1109/TBIOM.2026.3684931

Nicolas Cubero;Francisco M. Castro;Nicolas Guil;Manuel J. Marin-Jimenez

{"title":"HiPo-Gait: Hierarchical Pose Model Decoupling for Gait Recognition","authors":"Nicolas Cubero;Francisco M. Castro;Nicolas Guil;Manuel J. Marin-Jimenez","doi":"10.1109/TBIOM.2026.3684931","DOIUrl":"https://doi.org/10.1109/TBIOM.2026.3684931","url":null,"abstract":"Gait recognition has traditionally relied on silhouette- or appearance-based representations to analyze walking patterns. While silhouettes capture rich movement information, they are highly dependent on body shape and contours, which are potentially irrelevant to gait analysis. The human pose emerges as a more robust and semantically meaningful alternative. However, pose-based models have typically underperformed compared to silhouette-based approaches. To enhance gait feature extraction from pose representations, this paper proposes HiPo-Gait, a novel hierarchical architecture that analyzes isolated limbs of the body pose and groups them at different levels using a new local attention-based fusion module (LAF) to produce a robust hierarchical descriptor of the walking pattern. Moreover, instead of using point coordinates as input, we use heatmaps, a richer representation of the body pose. Our experimental results indicate that: 1) the hierarchical decoupling extracts richer features from every individual limb and 2) the fusion approach optimally aggregates the limbs, outperforming the classical fusion operations. Finally, our approach achieves a percentage point increase of 3.3% over the top pose-based state-of-the-art model in CASIA-B, 21.9%, and 25.6%, respectively, in CCPG and SUSTech1K, and 1.7% improvement over the top model in the FVG-B dataset. Source code is available at <uri>https://github.com/Nico-Cubero/HiPo-Gait</uri>","PeriodicalId":73307,"journal":{"name":"IEEE transactions on biometrics, behavior, and identity science","volume":"8 5","pages":"870-879"},"PeriodicalIF":4.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11483236","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148961847","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Robust 3-D Feature Extraction and Graph Pose-Invariant Matching for Contactless Fingerprint 非接触式指纹的鲁棒三维特征提取与图位不变匹配

IF 4.4

IEEE transactions on biometrics, behavior, and identity science Pub Date : 2026-09-01 Epub Date: 2026-04-20 DOI: 10.1109/TBIOM.2026.3685624

Yuwei Jia;Siyang Zheng;Fei Feng;Haoran Ma;Zhe Cui;Fei Su

{"title":"Robust 3-D Feature Extraction and Graph Pose-Invariant Matching for Contactless Fingerprint","authors":"Yuwei Jia;Siyang Zheng;Fei Feng;Haoran Ma;Zhe Cui;Fei Su","doi":"10.1109/TBIOM.2026.3685624","DOIUrl":"https://doi.org/10.1109/TBIOM.2026.3685624","url":null,"abstract":"Contactless fingerprint has gained lots of attention in recent fingerprint studies. However, most existing contactless fingerprint algorithms treat contactless fingerprints as 2D plain fingerprints, which lack consideration of the modality difference between contactless and contact fingerprints, especially the intrinsic 3D features in contactless fingerprints. This paper proposes a novel contactless fingerprint recognition algorithm that captures the revealed 3D feature of contactless fingerprints rather than the plain 2D feature. The proposed method first recovers 3D features from the monocular input contactless fingerprint, including the 3D shape model and 3D fingerprint feature (minutiae, orientation, etc.). Then, a novel pose estimation and matching method based on 3D graph network is proposed according to the extracted 3D feature. The proposed method is able to perform robust 3D feature extractions on various contactless fingerprints across multiple finger poses and correcting the pose of contactless fingerprints in 3D space. The results of the experiments on contactless fingerprint databases show that the proposed method successfully improves the matching accuracy of contactless fingerprints. Exceptionally, our method performs stably across multiple poses of contactless fingerprints due to 3D pose regression and embeddings, which is a great advantage compared to 2D-based previous contactless fingerprint recognition algorithms.","PeriodicalId":73307,"journal":{"name":"IEEE transactions on biometrics, behavior, and identity science","volume":"8 5","pages":"718-729"},"PeriodicalIF":4.4,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148961871","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0