{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T19:58:29Z","timestamp":1775505509745,"version":"3.50.1"},"reference-count":73,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Portuguese FCT\/MCTES through National Funds and co-funded by EU Funds","award":["UIDB\/50008\/2020"],"award-info":[{"award-number":["UIDB\/50008\/2020"]}]},{"DOI":"10.13039\/501100001871","name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia (FCT) Doctoral","doi-asserted-by":"publisher","award":["2020.09847.BD"],"award-info":[{"award-number":["2020.09847.BD"]}],"id":[{"id":"10.13039\/501100001871","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001871","name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia (FCT) Doctoral","doi-asserted-by":"publisher","award":["2021.04905.BD"],"award-info":[{"award-number":["2021.04905.BD"]}],"id":[{"id":"10.13039\/501100001871","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Biom. Behav. Identity Sci."],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1109\/tbiom.2024.3520030","type":"journal-article","created":{"date-parts":[[2024,12,18]],"date-time":"2024-12-18T14:53:10Z","timestamp":1734533590000},"page":"410-421","source":"Crossref","is-referenced-by-count":3,"title":["BIAS: A Body-Based Interpretable Active Speaker Approach"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9563-8039","authenticated-orcid":false,"given":"Tiago","family":"Roxo","sequence":"first","affiliation":[{"name":"Instituto de Telecomunicações, University of Beira Interior, Covilhã, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3995-4621","authenticated-orcid":false,"given":"Joana Cabral","family":"Costa","sequence":"additional","affiliation":[{"name":"Instituto de Telecomunicações, University of Beira Interior, Covilhã, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8221-0666","authenticated-orcid":false,"given":"Pedro R. M.","family":"In\u00e1cio","sequence":"additional","affiliation":[{"name":"Instituto de Telecomunicações, University of Beira Interior, Covilhã, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2551-8570","authenticated-orcid":false,"given":"Hugo","family":"Proen\u00e7a","sequence":"additional","affiliation":[{"name":"Instituto de Telecomunicações, University of Beira Interior, Covilhã, Portugal"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053900"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-2041"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/tbiom.2024.3412821"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_18"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00033"},{"key":"ref7","article-title":"EasyCom: An augmented reality dataset to support algorithms for easy communication in noisy environments","author":"Donley","year":"2021","journal-title":"arXiv:2107.04174"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/WIFS58808.2023.10374734"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2337"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3426670"},{"key":"ref11","article-title":"Naver at ActivityNet challenge 2019\u2014Task B active speaker detection (AVA)","author":"Chung","year":"2019","journal-title":"arXiv:1906.10555"},{"key":"ref12","first-page":"1","article-title":"Multi-task learning for audio-visual active speaker detection","volume-title":"Proc. Activ.Net Large-Scale Activ. Recognit. Chall.","author":"Zhang"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682524"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_13"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413869"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01248"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00123"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475275"},{"key":"ref22","first-page":"1","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"Proc. ICLR","author":"Welling"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_22"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_8"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475587"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02196"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654966"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.46"},{"key":"ref29","article-title":"A richly annotated dataset for pedestrian attribute recognition","author":"Li","year":"2016","journal-title":"arXiv:1603.07054"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3157857"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/441"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00510"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_42"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00082"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ACPR.2015.7486476"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.06.006"},{"key":"ref37","article-title":"Rethinking of pedestrian attribute recognition: Realistic datasets with efficient method","author":"Jia","year":"2020","journal-title":"arXiv:2005.11909"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref39","article-title":"Not just a black box: Learning important features through propagating activation differences","author":"Shrikumar","year":"2016","journal-title":"arXiv:1605.01713"},{"key":"ref40","first-page":"1","article-title":"Full-gradient representation for neural network visualization","volume-title":"Proc. 33rd Conf. Neural Inf. Process. Syst.","volume":"32","author":"Srinivas"},{"key":"ref41","article-title":"SmoothGrad: Removing noise by adding noise","author":"Smilkov","year":"2017","journal-title":"arXiv:1706.03825"},{"key":"ref42","first-page":"3319","article-title":"Axiomatic attribution for deep networks","volume-title":"Proc. ICML","author":"Sundararajan"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0130140"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20893-6_8"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00513"},{"key":"ref46","first-page":"4768","article-title":"A unified approach to interpreting model predictions","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Lundberg"},{"key":"ref47","first-page":"3145","article-title":"Learning important features through propagating activation differences","volume-title":"Proc. ICML","author":"Shrikumar"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858759"},{"key":"ref49","first-page":"6970","article-title":"Real time image saliency for black box classifiers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Dabkowski"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-017-1059-x"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00304"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.371"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00084"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00944"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/EUVIP53989.2022.9922905"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3137023"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00268"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TBIOM.2021.3100926"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref61","article-title":"Visual transformers: Token-based image representation and processing for computer vision","author":"Wu","year":"2020","journal-title":"arXiv:2006.03677"},{"issue":"8","key":"ref62","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref64","article-title":"Microsoft COCO captions: Data collection and evaluation server","author":"Chen","year":"2015","journal-title":"arXiv:1504.00325"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00633"},{"key":"ref67","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","volume-title":"Proc. Text Summ. Branches Out","author":"Lin"},{"key":"ref68","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proc. ACL Workshop Intrinsic Extrinsic Eval. Meas. Mach. Transl. Summ.","author":"Banerjee"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref70","article-title":"LoCoNet: Long-short context network for active speaker detection","author":"Wang","year":"2023","journal-title":"arXiv:2301.08237"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00428"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3395118"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3013834"}],"container-title":["IEEE Transactions on Biometrics, Behavior, and Identity Science"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8423754\/11052638\/10806889.pdf?arnumber=10806889","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,4]],"date-time":"2025-09-04T18:24:06Z","timestamp":1757010246000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10806889\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":73,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tbiom.2024.3520030","relation":{},"ISSN":["2637-6407"],"issn-type":[{"value":"2637-6407","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7]]}}}