{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T15:53:11Z","timestamp":1780501991018,"version":"3.54.1"},"reference-count":91,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"YUTP-FRG","award":["015LC0-395"],"award-info":[{"award-number":["015LC0-395"]}]},{"DOI":"10.13039\/501100003093","name":"Ministry of Higher Education, Malaysia","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003093","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Higher Institutional Centre of Excellence (HICoE) Scheme"},{"name":"Centre for Intelligent Signal and Imaging Research"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Affective Comput."],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1109\/taffc.2025.3566773","type":"journal-article","created":{"date-parts":[[2025,5,2]],"date-time":"2025-05-02T13:17:07Z","timestamp":1746191827000},"page":"2721-2734","source":"Crossref","is-referenced-by-count":4,"title":["Lightweight Spatio-Temporal Convolutional Neural Network for Audio-Visual Emotion Recognition"],"prefix":"10.1109","volume":"16","author":[{"given":"Su Yen","family":"Ding","sequence":"first","affiliation":[{"name":"Centre of Intelligent Signal and Imaging Research (CISIR), Universiti Teknologi PETRONAS, Bandar Seri Iskandar, Malaysia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5721-6828","authenticated-orcid":false,"given":"Tong Boon","family":"Tang","sequence":"additional","affiliation":[{"name":"Centre of Intelligent Signal and Imaging Research (CISIR), Universiti Teknologi PETRONAS, Bandar Seri Iskandar, Malaysia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5819-0754","authenticated-orcid":false,"given":"Cheng-Kai","family":"Lu","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, National Taiwan Normal University, Taipei, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2020.532279"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3188390"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3188730"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3263585"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3390\/electronics12122704"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.38094\/jastt20291"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ETFA46521.2020.9212098"},{"key":"ref8","first-page":"8093","article-title":"Overfitting in adversarially robust deep learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rice"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOMWKSHPS57453.2023.10226045"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3084827"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.micpro.2022.104711"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.ymssp.2020.107398"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.3390\/s19163579"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/mosicom59118.2023.10458797"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2020.2981446"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3310428"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.4018\/978-1-61520-919-4.ch017"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.1188976"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_42"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1017\/ATSIP.2014.11"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.101847"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2017.02.003"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2019.8851942"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.52547\/jist.16499.10.38.89"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2020.115831"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.121692"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CAC51589.2020.9327178"},{"issue":"4","key":"ref28","first-page":"529","article-title":"Audio-visual emotion recognition based on a deep convolutional neural network","volume":"10","author":"Aghajani","year":"2022","journal-title":"J. AI Data Min."},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ATSIP55956.2022.9805959"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.108580"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICRAMET.2017.8253139"},{"key":"ref32","first-page":"802","article-title":"Convolutional LSTM Network: A machine learning approach for precipitation nowcasting","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Shi"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.3390\/e25101440"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2022.106646"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.3390\/s23167092"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.02.028"},{"key":"ref37","first-page":"987","article-title":"Not all ops are created equal!","volume-title":"Proc. Annu. Conf. Mach. Learn. Syst.","author":"Lai"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.643"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-739"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.3390\/s17071694"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.3390\/s21155097"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1121\/1.1781620"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2023.101538"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.5120\/8529-2061"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.07.050"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.128177"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2024.101713"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.3390\/app122312151"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2023.05.008"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2017.08.015"},{"key":"ref51","article-title":"pydub: Manipulate audio with an simple and easy high level interface","author":"Robert","year":"2018"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2001.990517"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1142\/s0218001420560030"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-11173-0"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01104"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.87"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-39940-9_1033"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/s12559-021-09865-2"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2008.01.004"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1980.1163420"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.25080\/Majora-7b98e3ed-003"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3223444"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/EAIS48028.2020.9122698"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO55093.2022.9909674"},{"key":"ref65","article-title":"An overview of gradient descent optimization algorithms","author":"Ruder","year":"2016"},{"key":"ref66","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representation","author":"Kingma"},{"key":"ref67","volume-title":"TIMIT Acoustic-Phonetic Continuous Speech Corpus","author":"Garofolo","year":"2015"},{"key":"ref68","article-title":"OpenCV library","year":"2019"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-56431-4_7"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1371\/joumal.pone.0177239"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0197160"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1111\/exsy.13759"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1002\/ejp.1691"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1037\/0894-4105.14.4.526"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1080\/17470211003721642"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/AFGR.1998.670976"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2015.08.011"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.109271"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1145\/3469661"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.20"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2022.103970"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/IPRIA59240.2023.10147192"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3116530"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2003.10057"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2336244"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.107708"},{"key":"ref87","first-page":"3319","article-title":"Axiomatic attribution for deep networks","volume-title":"Proc. Int. Conf. Mach Learn.","author":"Sundararajan"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1037\/a0022758"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1057\/9781137345868_6"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3358455"},{"key":"ref91","article-title":"Quantization aware training | TensorFlow model optimization"}],"container-title":["IEEE Transactions on Affective Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5165369\/11269911\/10982434.pdf?arnumber=10982434","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:58:42Z","timestamp":1764269922000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10982434\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":91,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/taffc.2025.3566773","relation":{},"ISSN":["1949-3045","2371-9850"],"issn-type":[{"value":"1949-3045","type":"electronic"},{"value":"2371-9850","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10]]}}}