IEEE transactions on biometrics, behavior, and identity science最新文献

{"title":"MDL-Net: Multi-Task Learning Network for Face Forgery Detection and Localization Using Dual-Stream Feature Extraction and Reconstruction","authors":"Huasong Yi;Qian Jiang;Hongyue Huang;Li Tang;Shaowen Yao;Shin-Jye Lee;Xin Jin","doi":"10.1109/TBIOM.2026.3656922","DOIUrl":"https://doi.org/10.1109/TBIOM.2026.3656922","url":null,"abstract":"Advancement in face forgery technologies has led to the generation of increasingly realistic images, making them difficult for the human eye to distinguish. These technologies pose risks in areas such as face recognition and identity verification, including fraud and social engineering attacks. While face forgery detection algorithms achieve high accuracy within a single dataset, their generalization performance in cross-dataset scenarios remains insufficient. To address this issue, this study introduces the Multi-task Face Forgery Detection and Localization Network (MDL-Net), which improves cross-dataset detection performance through dual-stream feature extraction and reconstructed feature enhancement. First, the face forgery reconstruction module restores and reconstructs images, amplifying subtle features in the tampered regions. Second, leveraging pixel-level residual information, the reconstruction attention module enhances feature representation by comparing input images with their reconstructed counterparts. Finally, the localization module precisely identifies forged regions through pixel-level segmentation. This approach encourages the model to extract forgery-specific features and learn more generalized and robust representations, achieving high detection and localization accuracy. Experiments conducted on the FaceForensics++ and WildDeepfake datasets demonstrate the superior performance and robustness of the proposed framework. Comparative experiments on other benchmark datasets validate the enhanced generalization ability of the method while maintaining high detection accuracy. The code is available at <uri>https://github.com/jinxinhuo/MDL-Net</uri>","PeriodicalId":73307,"journal":{"name":"IEEE transactions on biometrics, behavior, and identity science","volume":"8 3","pages":"398-411"},"PeriodicalIF":5.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147685342","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}

{"title":"IEEE Transactions on Biometrics, Behavior, and Identity Science Information for Authors","authors":"","doi":"10.1109/TBIOM.2026.3678354","DOIUrl":"https://doi.org/10.1109/TBIOM.2026.3678354","url":null,"abstract":"","PeriodicalId":73307,"journal":{"name":"IEEE transactions on biometrics, behavior, and identity science","volume":"8 3","pages":"C3-C3"},"PeriodicalIF":5.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11481992","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147685532","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}

{"title":"IEEE Transactions on Biometrics, Behavior, and Identity Science Publication Information","authors":"","doi":"10.1109/TBIOM.2026.3678355","DOIUrl":"https://doi.org/10.1109/TBIOM.2026.3678355","url":null,"abstract":"","PeriodicalId":73307,"journal":{"name":"IEEE transactions on biometrics, behavior, and identity science","volume":"8 3","pages":"C2-C2"},"PeriodicalIF":5.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11481990","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147685556","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}

{"title":"Impact of Sunglasses on One-to-Many Facial Identification Accuracy","authors":"Sicong Tian;Haiyu Wu;Michael C. King;Kevin W. Bowyer","doi":"10.1109/TBIOM.2026.3666896","DOIUrl":"https://doi.org/10.1109/TBIOM.2026.3666896","url":null,"abstract":"Probe images used in one-to-many facial identification often deviate from ‘mugshot quality’ in various ways. This paper explores how the accuracy of one-to-many facial identification is degraded by the person in the probe image wearing sunglasses, and how this accuracy degradation can be ameliorated. We show that sunglasses degrade accuracy for mugshot-quality images by an amount similar to strong blur or noticeably lower resolution. Further, we demonstrate that the combination of sunglasses with blur or lower resolution has an additive effect in degrading accuracy. These results have important implications for developing criteria to qualify a probe image for the accuracy that can be expected if it is used for facial identification. We explore two approaches to reduce the accuracy loss. First, we show that by adding synthetic sunglasses to all gallery images, we can recover approximately 27% of the accuracy loss with no change to the face-matching model. Second, we demonstrate that training a sunglasses-aware model using augmented training data can achieve up to 33% higher accuracy for sunglasses-wearing probes while maintaining baseline accuracy for non-sunglasses probes. Moreover, combining both approaches achieves even greater accuracy recovery (up to 43% for males and 35% for females). Additionally, our results show that increasing the representation of sunglasses-wearing images evenly across all identities in training data is more effective than concentrating them on fewer identities. The effectiveness of our sunglasses-aware model is validated through t-SNE visualization and a 16% increase in feature similarity between sunglasses and no-sunglasses images of a given identity. Our investigation further reveals that baseball caps play a role similar to sunglasses in degrading facial identification accuracy. To support replication and further research, info to obtain the face image datasets used is available at <uri>https://cvrl.nd.edu/projects/data/</uri>","PeriodicalId":73307,"journal":{"name":"IEEE transactions on biometrics, behavior, and identity science","volume":"8 3","pages":"461-476"},"PeriodicalIF":5.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147685321","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}

{"title":"Point-Supervised Facial Expression Spotting With Gaussian-Based Instance-Adaptive Intensity Modeling","authors":"Yicheng Deng;Hideaki Hayashi;Hajime Nagahara","doi":"10.1109/TBIOM.2026.3651893","DOIUrl":"https://doi.org/10.1109/TBIOM.2026.3651893","url":null,"abstract":"Automatic facial expression spotting, which aims to identify facial expression instances in untrimmed videos, is crucial for facial expression analysis. Existing methods primarily focus on fully-supervised learning and rely on costly, time-consuming temporal boundary annotations. In this paper, we investigate point-supervised facial expression spotting (P-FES), where only a single timestamp annotation per instance is required for training. We propose a unique two-branch framework for P-FES. First, to mitigate the limitation of hard pseudo-labeling, which often confuses neutral and expression frames with various intensities, we propose a Gaussian-based instance-adaptive intensity modeling (GIM) module to model instance-level expression intensity distribution for soft pseudo-labeling. By detecting the pseudo-apex frame around each point label, estimating the duration, and constructing an instance-level Gaussian distribution, GIM assigns soft pseudo-labels to expression frames for more reliable intensity supervision. The GIM module is incorporated into our framework to optimize the class-agnostic expression intensity branch. Second, we design a class-aware apex classification branch that distinguishes macro- and micro-expressions solely based on their pseudo-apex frames. During inference, the two branches work independently: the class-agnostic expression intensity branch generates expression proposals, while the class-aware apex-classification branch is responsible for macro- and micro-expression classification. Furthermore, we introduce an intensity-aware contrastive loss to enhance discriminative feature learning and suppress neutral noise by contrasting neutral frames with expression frames with various intensities. Extensive experiments on the SAMM-LV, CAS(ME)2, and CAS(ME)3 datasets demonstrate the effectiveness of our proposed framework. Code is available at <uri>https://github.com/KinopioIsAllIn/GIM</uri>","PeriodicalId":73307,"journal":{"name":"IEEE transactions on biometrics, behavior, and identity science","volume":"8 3","pages":"378-391"},"PeriodicalIF":5.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11339514","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147685468","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}

{"title":"Identity Reflections: Hyperspectral Skin Analysis via Reflectance Distance Learning With Context-Aware Contrastive Transformers","authors":"Emanuela Marasco;Bhargavi Janga;Gautham Gali;Raghavendra Ramachandra","doi":"10.1109/TBIOM.2026.3657642","DOIUrl":"https://doi.org/10.1109/TBIOM.2026.3657642","url":null,"abstract":"Hyperspectral Imaging (HSI) enables real-time analysis with rich spectral detail, offering a promising path to spoof-resistant AI-based identity verification. Leveraging this spectral information, we present a novel biometric approach that extracts and analyzes skin reflectance patterns from hyperspectral fingertip images. In prior work, hyperspectral analysis has primarily been applied to facial biometrics; however, the associated lighting requirements are often impractical or inconvenient for users in real-world scenarios. From a computational perspective, while deep learning has significantly advanced recognition using conventional imaging, effectively applying these frameworks to the rich and complex signals captured by HSI remains a critical open challenge. Convolutional Neural Networks (CNNs) often have difficulty preserving the sequential structure of spectral information. Vision transformers effectively capture global context through self-attention but often face challenges in modeling fine-grained local features due to the lack of convolutional inductive biases. To address existing limitations, this work introduces a novel integration of Context-Enriched Contrastive Loss (CECL) into two architectures: SpectralFormer, a ViT-based model that employs decoupled spatial–spectral processing to handle spectral signatures extracted from carefully selected spatial regions; and the Swin Transformer, which leverages a unified 3D joint representation. For the first time, SpectralFormer is employed for identity verification, leveraging group-wise spectral embeddings, inspired by ViT’s patch-based processing, across adjacent bands, along with intermediate skip connections to enhance the analysis of complex spectral data. The proposed approach was evaluated on three biometric databases, including the Mason FHSD-2022 hyperspectral fingertip dataset collected at George Mason University with 100 subjects. The code will be publicly available on GitHub.","PeriodicalId":73307,"journal":{"name":"IEEE transactions on biometrics, behavior, and identity science","volume":"8 3","pages":"431-444"},"PeriodicalIF":5.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147685524","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}

{"title":"MoGA-ETA: Generalized Face Anti-Spoofing With Enhanced Text Guidance and Alignment","authors":"Liepiao Zhang;Kun Liu;Tianming Xie;Junduan Huang;Zitong Yu;Wenxiong Kang","doi":"10.1109/TBIOM.2026.3657113","DOIUrl":"https://doi.org/10.1109/TBIOM.2026.3657113","url":null,"abstract":"Face anti-spoofing (FAS) methods struggle with cross-domain generalization due to variations in attack types and imaging conditions. While recent vision-language approaches leverage image-text contrastive learning, they face three critical limitations: 1) simplistic text prompts fail to capture nuanced spoofing artifacts like moiré patterns or 3D mask boundaries, 2) suboptimal visual encoder fine-tuning leads to either inadequate adaptation or overfitting, and 3) substantial semantic gaps between image and text features undermine cross-modal alignment. To address these limitations, we propose the Enhanced Text Guidance and Alignment (MoGA-ETA) to enhance language-guided face anti-spoofing. First, we introduce an in-context text prompt enhancement strategy to generate detailed descriptions with fine-grained textual descriptions, capturing both global attributes (e.g., illumination anomalies) and local cues (e.g., Moiré patterns) through the large vision-language model. Second, we design and embed a mixture of gradient adapters into the language-image contrastive pretrained visual encoder during the post-training period. Third, we investigate image-text alignment via a hard positive and negative mining strategy to improve the efficacy of cross-modal contrastive learning. Extensive experiments on leave-one-out cross-domain benchmarks demonstrate that our method can achieve state-of-the-art performance, and ablation studies confirm the necessity of each component. The code is released at <uri>https://github.com/zlpiao/MoGA-ETA</uri>","PeriodicalId":73307,"journal":{"name":"IEEE transactions on biometrics, behavior, and identity science","volume":"8 3","pages":"340-353"},"PeriodicalIF":5.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147685353","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}

{"title":"FaceXBench: Evaluating Multimodal LLMs on Face Understanding","authors":"Kartik Narayan;V. S. Vibashan;Vishal M. Patel","doi":"10.1109/TBIOM.2026.3655668","DOIUrl":"https://doi.org/10.1109/TBIOM.2026.3655668","url":null,"abstract":"Multimodal Large Language Models (MLLMs) demonstrate impressive problem-solving abilities across a wide range of tasks and domains. However, their capacity for face understanding has not been systematically studied. To address this gap, we introduce FaceXBench, a comprehensive benchmark designed to evaluate MLLMs on complex face understanding tasks. FaceXBench includes 5,000 multimodal multiple-choice questions derived from 25 public datasets and a newly created dataset, FaceXAPI. These questions cover 14 tasks across 6 broad categories, assessing MLLMs’ face understanding abilities in bias and fairness, face authentication, recognition, analysis, localization and tool retrieval. Using FaceXBench, we conduct an extensive evaluation of 26 open-source MLLMs alongside 2 proprietary models, revealing the unique challenges in complex face understanding tasks. We analyze the models across three evaluation settings: zero-shot, in-context task description, and chain-of-thought prompting. Our detailed analysis reveals that current MLLMs, including advanced models like GPT-4o, and GeminiPro 1.5, show significant room for improvement. We believe FaceXBench will be a crucial resource for developing MLLMs equipped to perform sophisticated face understanding.","PeriodicalId":73307,"journal":{"name":"IEEE transactions on biometrics, behavior, and identity science","volume":"8 3","pages":"354-364"},"PeriodicalIF":5.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147685546","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}

{"title":"Face Morphing Attack Generation and Detection: A State-of-the-Art Review","authors":"Davide Antonutti;Justin Ilyes;Laurenz Ruzicka;Silvia Poletti;Marcel Hasenbalg;Martin Boyer;David Fischinger","doi":"10.1109/TBIOM.2026.3655515","DOIUrl":"https://doi.org/10.1109/TBIOM.2026.3655515","url":null,"abstract":"Face morphing attacks pose a significant threat to the security and reliability of biometric identity verification systems, particularly in real-world applications such as passport issuance and border control. In a morphing attack, facial features from two or more individuals are blended into a single image that can deceive face recognition systems, allowing multiple individuals to share a biometric identity. This survey provides a comprehensive overview of the literature on face morphing attack detection (MAD). It begins by introducing the practical implications of morphing attacks and their relevance in operational contexts. The paper then explores a wide range of morphing generation techniques, including both classical landmark-based approaches and modern deep learning-based methods such as GANs and diffusion models. The work proceeds with an extensive review and categorization of existing MAD techniques, grouped into meaningful categories based on their underlying principles, ranging from texture-based and quality-based methods to deep learning and hybrid approaches. By organizing the literature and identifying current trends, strengths, and limitations, this survey offers valuable insight for researchers and practitioners seeking to understand, evaluate, or develop robust solutions against face morphing attacks.","PeriodicalId":73307,"journal":{"name":"IEEE transactions on biometrics, behavior, and identity science","volume":"8 3","pages":"412-430"},"PeriodicalIF":5.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11357967","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147685343","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}

{"title":"Advancing Brainwave-Based Biometrics: A Large-Scale, Multi-Session Evaluation","authors":"Matin Fallahi;Patricia Arias Cabarcos;Thorsten Strufe","doi":"10.1109/TBIOM.2026.3666044","DOIUrl":"https://doi.org/10.1109/TBIOM.2026.3666044","url":null,"abstract":"The field of brainwave-based biometrics has gained attention for its potential to revolutionize user authentication through hands-free interaction, resistance to shoulder surfing, continuous authentication, and revocability. However, current research often relies on single-session or limited-session datasets with fewer than 55 subjects, raising concerns about the generalizability of the findings. To address this gap, we conducted a large-scale study using a public brainwave dataset comprising 345 subjects and over 6,007 sessions (an average of 17 per subject) recorded over five years using three headsets. Our results reveal that deep learning approaches significantly outperform hand-crafted feature extraction methods. We also observe Equal Error Rates (EER) increases over time (e.g., from 6.7% after 1 day to 14.3% after a year). Therefore, it is necessary to reinforce the enrollment set after successful login attempts. Moreover, we demonstrate that fewer brainwave measurement sensors can be used, with an acceptable increase in EER, which is necessary for transitioning from medical-grade to affordable consumer-grade devices. Finally, we compared our results to prior work and existing biometric standards. While our performance is on par with or exceeds previous approaches, it still falls short of industrial benchmarks. Based on the results, we hypothesize that further improvements are possible with larger training sets. To support future research, we have open-sourced our analysis code.","PeriodicalId":73307,"journal":{"name":"IEEE transactions on biometrics, behavior, and identity science","volume":"8 3","pages":"445-460"},"PeriodicalIF":5.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11407492","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147685352","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}