IEEE transactions on biometrics, behavior, and identity science最新文献_第4页

Beyond the Voice: Inertial Sensing of Mouth Motion for High-Security Speech Verification 超越声音：用于高安全性语音验证的口腔运动惯性感应

IF 4.4

IEEE transactions on biometrics, behavior, and identity science Pub Date : 2026-07-01 Epub Date: 2026-03-27 DOI: 10.1109/TBIOM.2026.3678247

Ynes Ineza;Muhammad Aziz Ullah;Abdul Serwadda;Aurore Nicole Munyaneza

{"title":"Beyond the Voice: Inertial Sensing of Mouth Motion for High-Security Speech Verification","authors":"Ynes Ineza;Muhammad Aziz Ullah;Abdul Serwadda;Aurore Nicole Munyaneza","doi":"10.1109/TBIOM.2026.3678247","DOIUrl":"https://doi.org/10.1109/TBIOM.2026.3678247","url":null,"abstract":"Voice interfaces are increasingly used in high-stakes domains such as mobile banking, smart-home security, and hands-free healthcare. Meanwhile, modern generative models have made high-quality voice forgeries inexpensive and easy to create, eroding confidence in voice authentication alone. To strengthen protection against such attacks, we present a second authentication factor that combines acoustic evidence with the unique motion patterns of a speaker’s lower face. By placing lightweight inertial sensors around the mouth to capture mouth opening and evolving lower-facial geometry, our system records a distinct motion signature with strong discriminative power across individuals.We built a prototype and recruited 43 participants to evaluate the system under four conditions: seated, walking on level ground, walking on stairs, and speaking with different language backgrounds (native vs. non-native English). Across all scenarios, our approach consistently achieved a median equal-error rate (EER) of 0.01 or lower, indicating that mouth-movement data remain robust under variations in gait, posture, and spoken language. We discuss specific use cases where this second line of defense could provide tangible security benefits to voice authentication systems.","PeriodicalId":73307,"journal":{"name":"IEEE transactions on biometrics, behavior, and identity science","volume":"8 4","pages":"600-611"},"PeriodicalIF":4.4,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148433200","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

MMHAR-28: Human Action Recognition Across RGB, Thermal, Depth, and Event Modalities MMHAR-28：跨越RGB、热、深度和事件模式的人类行为识别

IF 4.4

IEEE transactions on biometrics, behavior, and identity science Pub Date : 2026-07-01 Epub Date: 2026-03-19 DOI: 10.1109/TBIOM.2026.3675639

Tomiris Rakhimzhanova;Askat Kuzdeuov;Artur Muratov;Huseyin Atakan Varol

{"title":"MMHAR-28: Human Action Recognition Across RGB, Thermal, Depth, and Event Modalities","authors":"Tomiris Rakhimzhanova;Askat Kuzdeuov;Artur Muratov;Huseyin Atakan Varol","doi":"10.1109/TBIOM.2026.3675639","DOIUrl":"https://doi.org/10.1109/TBIOM.2026.3675639","url":null,"abstract":"Currently, the majority of human action recognition (HAR) models are trained on RGB video datasets. However, RGB cameras have limitations such as motion blur, low illumination, privacy concerns, and the lack of 3D spatial details. Existing HAR datasets are often unimodal or lack consistent protocols across different modalities, hindering robust multimodal learning. To bridge this gap, we present MMHAR-28, an extensive multimodal HAR dataset featuring 10,298 videos representing 28 actions captured across four camera types: RGB, depth, thermal, and event-based sensors. It includes various daily activities, sports exercises, and multi-person interactions, providing a unified benchmark for multimodal learning. To show the efficacy of MMHAR-28, we trained various HAR models such as VideoMamba, UniFormerV2, and TSM, examining the effects of increased temporal context, modality-specific performance, and the benefits of multimodal feature generalization. Notably, the multimodal Uniformerv2-MM-32 model achieved a top-1 accuracy of 97.86% on RGB, 90.71% on depth, 86.58% on event, and 98.57% on thermal modalities. We have made our dataset, source code, and models publicly available at <uri>https://github.com/IS2AI/MMHA-28</uri> to support research in this area.","PeriodicalId":73307,"journal":{"name":"IEEE transactions on biometrics, behavior, and identity science","volume":"8 4","pages":"575-586"},"PeriodicalIF":4.4,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148433291","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

Enhancing Crowd Counting With Synthetic Retrieval 利用合成检索增强人群计数

IF 4.4

IEEE transactions on biometrics, behavior, and identity science Pub Date : 2026-07-01 Epub Date: 2026-02-24 DOI: 10.1109/TBIOM.2026.3667751

Yasiru Ranasinghe;Vishal M. Patel

{"title":"Enhancing Crowd Counting With Synthetic Retrieval","authors":"Yasiru Ranasinghe;Vishal M. Patel","doi":"10.1109/TBIOM.2026.3667751","DOIUrl":"https://doi.org/10.1109/TBIOM.2026.3667751","url":null,"abstract":"Existing crowd-counting methods rely on the manual localization of each person in the image. While recent efforts have attempted to circumvent the annotation burden through vision-language models or crowd image generation, these approaches rely on pseudo-labels to perform crowd-counting. Simulated datasets provide an alternative to the annotation cost associated with real datasets. However, the use of large-scale simulated data often results in a distribution gap between real and simulated domains. To address the latter, we introduce knowledge retrieval inspired by knowledge-enhanced models in natural language processing. With knowledge retrieval, we extract simulated crowd images and their text descriptions to augment the image embeddings of real crowd images to improve generalized crowd-counting. Knowledge retrieval enables to use a vast amount of non-parameterized knowledge during testing, enhancing a model’s inference capability. Our work is the first to actively use text information to regress the crowd count in any supervised manner. Moreover, to address the domain gap, we propose a retrieval mechanism that uses unlabeled real crowd images along with simulated data. We report state-of-the-art results for zero-shot counting on five public datasets, surpassing existing multi-model crowd-counting methods. The project is available at: <uri>https://dylran.github.io/regecount.github.io</uri>","PeriodicalId":73307,"journal":{"name":"IEEE transactions on biometrics, behavior, and identity science","volume":"8 4","pages":"564-574"},"PeriodicalIF":4.4,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148433378","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

Beyond Global Perturbations: Focused Adversarial Attacks for Face Deepfake 超越全局扰动：针对人脸深度造假的集中对抗性攻击

IF 4.4

IEEE transactions on biometrics, behavior, and identity science Pub Date : 2026-07-01 Epub Date: 2026-03-02 DOI: 10.1109/TBIOM.2026.3669723

Zhi Cao;Zhongyuan Wang;Run Wang;Haojun Ai;Gang Wu

{"title":"Beyond Global Perturbations: Focused Adversarial Attacks for Face Deepfake","authors":"Zhi Cao;Zhongyuan Wang;Run Wang;Haojun Ai;Gang Wu","doi":"10.1109/TBIOM.2026.3669723","DOIUrl":"https://doi.org/10.1109/TBIOM.2026.3669723","url":null,"abstract":"As deepfake generation models continue to evolve in complexity, they pose increasing security threats, necessitating more effective and robust adversarial defense mechanisms. In this paper, we first propose a foreground-aware robustness evaluation strategy for assessing robust adversarial perturbations that exploits the intrinsic foreground-background separation in deepfake, offering a more realistic assessment aligned with practical forgery scenarios. We further propose Focused Iterative-FGSM (FIM), a novel adversarial attack framework tailored for deepfake models. Specifically, motivated by the unequal adversarial sensitivity across different regions, we quantify pixel-level importance from three complementary perspectives: static saliency via Grad-CAM, dynamic gradient magnitude, and semantic foreground masking. Based on the resulting composite importance scores, we propose an importance-guided perturbation threshold reallocation scheme to concentrate adversarial efforts on high-impact areas. Extensive experiments on two benchmark datasets (CelebA and LFW) and multiple face editing GANs demonstrate that FIM consistently outperforms state-of-the-art baselines in both adversarial effectiveness and robustness.","PeriodicalId":73307,"journal":{"name":"IEEE transactions on biometrics, behavior, and identity science","volume":"8 4","pages":"518-528"},"PeriodicalIF":4.4,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148433298","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

Toward Generalized and Explainable Face Anti-Spoofing via Decomposition-Fusion Networks 基于分解融合网络的广义可解释人脸反欺骗研究

IF 4.4

IEEE transactions on biometrics, behavior, and identity science Pub Date : 2026-07-01 Epub Date: 2026-03-31 DOI: 10.1109/TBIOM.2026.3679390

Dhimas Arief Dharmawan;Anto Satriyo Nugroho;Seviko Attalarik Pramayudha Handoko

{"title":"Toward Generalized and Explainable Face Anti-Spoofing via Decomposition-Fusion Networks","authors":"Dhimas Arief Dharmawan;Anto Satriyo Nugroho;Seviko Attalarik Pramayudha Handoko","doi":"10.1109/TBIOM.2026.3679390","DOIUrl":"https://doi.org/10.1109/TBIOM.2026.3679390","url":null,"abstract":"This paper presents DFNet, a decomposition-fusion network for generalized and interpretable face anti-spoofing. DFNet comprises two explicitly designed branches—a decomposition branch and a fusion branch—that jointly enhance robustness and interpretability in presentation attack detection. The decomposition branch extracts multi-level representations through a two-stage process, where coarse features and saliency maps are first computed to emphasize prominent regions, followed by the suppression of these regions to facilitate fine-grained feature extraction from less dominant areas. The fusion branch integrates the coarse and fine-grained streams using a residual architecture augmented with convolutional block attention modules, while a dynamic weighting mechanism adaptively balances their contributions during feature fusion. DFNet is extensively evaluated on multiple public benchmarks under both intra- and cross-dataset protocols, and its robustness is further assessed under strong Projected Gradient Descent (PGD) adversarial attacks. Experimental results demonstrate that DFNet achieves competitive or superior performance across diverse datasets and attack scenarios, while maintaining improved resilience to adversarial perturbations. Moreover, the modular, attention-driven design of DFNet provides saliency-based insights into the learned spoof traces, supporting its interpretability. Overall, this work highlights the effectiveness of explicitly incorporating generalization, robustness, and interpretability into architectural design for real-world face anti-spoofing, with DFNet offering a concrete step toward this goal. For reproducibility, the source code is publicly available at <uri>https://github.com/dhimasarief/DFNet</uri>","PeriodicalId":73307,"journal":{"name":"IEEE transactions on biometrics, behavior, and identity science","volume":"8 4","pages":"640-651"},"PeriodicalIF":4.4,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148433226","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

Restricted Receptive Fields for Face Verification 人脸验证的受限制接受域

IF 4.4

IEEE transactions on biometrics, behavior, and identity science Pub Date : 2026-07-01 Epub Date: 2026-02-11 DOI: 10.1109/TBIOM.2026.3663919

Kagan Ozturk;Aman Bhatta;Haiyu Wu;Patrick J. Flynn;Kevin W. Bowyer

{"title":"Restricted Receptive Fields for Face Verification","authors":"Kagan Ozturk;Aman Bhatta;Haiyu Wu;Patrick J. Flynn;Kevin W. Bowyer","doi":"10.1109/TBIOM.2026.3663919","DOIUrl":"https://doi.org/10.1109/TBIOM.2026.3663919","url":null,"abstract":"Understanding how deep neural networks make decisions is crucial for analyzing their behavior and diagnosing failure cases. In computer vision, a common approach to improve interpretability is to assign importance to individual pixels using post-hoc methods. Although they are widely used to explain black-box models, their fidelity to the model’s actual reasoning is uncertain due to the lack of reliable evaluation metrics. This limitation motivates an alternative approach, which is to design models whose decision processes are inherently interpretable. To this end, we propose a face similarity metric that breaks down global similarity into contributions from restricted receptive fields. Our method defines the similarity between two face images as the sum of patch-level similarity scores, providing a locally additive explanation without relying on post-hoc analysis. We show that the proposed approach achieves competitive verification performance even with patches as small as <inline-formula> <tex-math>$28 times 28$ </tex-math></inline-formula> within <inline-formula> <tex-math>$112 times 112$ </tex-math></inline-formula> face images, and surpasses state-of-the-art methods when using <inline-formula> <tex-math>$56 times 56$ </tex-math></inline-formula> patches.","PeriodicalId":73307,"journal":{"name":"IEEE transactions on biometrics, behavior, and identity science","volume":"8 4","pages":"529-539"},"PeriodicalIF":4.4,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148433297","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

Attention-Based Parameter-Efficient Contrastive Learning Network for Finger Vein Recognition 基于注意力的参数高效对比学习网络用于手指静脉识别

IF 4.4

IEEE transactions on biometrics, behavior, and identity science Pub Date : 2026-07-01 Epub Date: 2026-04-23 DOI: 10.1109/TBIOM.2026.3686848

Zijun Ke;Lu Yang;Xinlong Zhao;Chenglong Li;Yilong Yin

{"title":"Attention-Based Parameter-Efficient Contrastive Learning Network for Finger Vein Recognition","authors":"Zijun Ke;Lu Yang;Xinlong Zhao;Chenglong Li;Yilong Yin","doi":"10.1109/TBIOM.2026.3686848","DOIUrl":"https://doi.org/10.1109/TBIOM.2026.3686848","url":null,"abstract":"As a highly secure biometric modality, finger vein recognition holds significant value in personal identification applications. However, some recognition modules have a large number of parameters and a habit of dependency on large-scale training images. To deal with above problems, this paper proposes a dual convolutional fusion Attention Based parameter-efficient Contrastive learning Network (ABCNet) for finger vein recognition, which achieves a low computational cost and a high recognition accuracy by the compact network architecture and supervised contrastive learning. In detail, we design a parameter-efficient backbone network, which effectively reduces parameters by optimizing residual layers and bottleneck blocks. Additionally, a dual convolution fusion attention (DCFAtt) is proposed to enhance feature representation, in which the attention weight is computed by a depthwise separable convolution path and a pointwise convolution path. Moreover, the supervised contrastive learning strategy makes use of class labels to build positive and negative image pairs for training our network, which reduces the dependency on large-scale training images. The effectiveness of our ABCNet is proved on SDU, HKPU and USM datasets with the recognition accuracies of 99.84%, 99.15%, 99.80% respectively. Compared with the state-of-the-art models, our ABCNet has fewer parameters and higher recognition accuracy.","PeriodicalId":73307,"journal":{"name":"IEEE transactions on biometrics, behavior, and identity science","volume":"8 4","pages":"487-496"},"PeriodicalIF":4.4,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148433305","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

Beyond Real Versus Fake: Towards Intent-Aware Video Analysis 超越真假：走向意图感知视频分析

IF 4.4

IEEE transactions on biometrics, behavior, and identity science Pub Date : 2026-07-01 Epub Date: 2026-02-11 DOI: 10.1109/TBIOM.2026.3663642

Saurabh Atreya;Nabyl Quignon;Baptiste Chopin;Abhijit Das;Antitza Dantcheva

{"title":"Beyond Real Versus Fake: Towards Intent-Aware Video Analysis","authors":"Saurabh Atreya;Nabyl Quignon;Baptiste Chopin;Abhijit Das;Antitza Dantcheva","doi":"10.1109/TBIOM.2026.3663642","DOIUrl":"https://doi.org/10.1109/TBIOM.2026.3663642","url":null,"abstract":"The rapid advancement of generative models has led to increasingly realistic deepfake videos, posing significant societal and security risks. While existing detection methods have focused on distinguishing real from fake videos, such approaches fail to address a fundamental question: What is the intent behind a manipulated video? Towards addressing this question, we introduce IntentHQ: the first benchmark for human-centered intent analysis, shifting the paradigm from authenticity verification to contextual understanding of videos. IntentHQ consists of 5168 videos that have been meticulously collected and annotated with 23 fine-grained intent-categories, including ‘Financial fraud’, ‘Indirect marketing’, ‘Political propaganda’, as well as ‘Fear mongering’. We perform intent recognition with supervised and self-supervised multi-modality models that integrate spatio-temporal video features, audio processing, and text analysis to infer underlying motivation and goals behind videos. Our proposed model is streamlined to differentiate between a wide range of intent-categories. This work establishes intent recognition as a new research direction beyond authenticity verification, enabling richer contextual understanding of video. The IntentHQ dataset is available under <uri>https://github.com/atrey-a/intent-hq</uri>","PeriodicalId":73307,"journal":{"name":"IEEE transactions on biometrics, behavior, and identity science","volume":"8 4","pages":"540-551"},"PeriodicalIF":4.4,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148433216","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

Machine Vision-Oriented Image Quality Evaluation for Face Super-Resolution 面向机器视觉的人脸超分辨率图像质量评价

IF 4.4

IEEE transactions on biometrics, behavior, and identity science Pub Date : 2026-07-01 Epub Date: 2026-01-28 DOI: 10.1109/TBIOM.2026.3658611

Weiling Chen;Ranwen Zhuang;Weitao Lin;Keke Zhang;Xuejin Wang;Tiesong Zhao

{"title":"Machine Vision-Oriented Image Quality Evaluation for Face Super-Resolution","authors":"Weiling Chen;Ranwen Zhuang;Weitao Lin;Keke Zhang;Xuejin Wang;Tiesong Zhao","doi":"10.1109/TBIOM.2026.3658611","DOIUrl":"https://doi.org/10.1109/TBIOM.2026.3658611","url":null,"abstract":"Super-resolution technology can improve recognition accuracy of low-resolution face images. However, existing face super-resolution techniques often suffer from identity change and recognizability reduction, limiting their effectiveness in automated face recognition systems. These shortcomings stem from the semantic gap and the lack of high-resolution reference images, leading to suboptimal performance in real-world applications. To reasonably evaluate the performance of face super-resolution, we propose a machine recognition-oriented image quality evaluation method. Firstly, we establish a Machine vision-oriented Face Super-resolution Quality Dataset (M-FSQD) annotated by multiple face recognition algorithms. The dataset is specifically designed to account for machine vision requirements and provides a variety of super-resolution face images for quality assessment. To our knowledge, this is the first face super-resolution image quality dataset tailored for machine vision applications. On this basis, a Siamese network architecture is designed to assess the quality of face super-resolution images quality from a machine vision perspective. Our semi-supervised method effectively extracts the identity-preserving features from low-resolution images while eliminating dependency on high-resolution References. Experimental results demonstrate that our method successfully captures machine-vision-aligned features and outperforms existing image quality assessment methods.","PeriodicalId":73307,"journal":{"name":"IEEE transactions on biometrics, behavior, and identity science","volume":"8 4","pages":"477-486"},"PeriodicalIF":4.4,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148433280","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

IEEE Transactions on Biometrics, Behavior, and Identity Science Publication Information IEEE生物计量学、行为与身份科学学报

IF 4.4

IEEE transactions on biometrics, behavior, and identity science Pub Date : 2026-07-01 Epub Date: 2026-06-17 DOI: 10.1109/TBIOM.2026.3688369

引用次数: 0