{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T15:12:19Z","timestamp":1781622739589,"version":"3.54.5"},"reference-count":71,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"European Union's Horizon Europe Research and Innovation Programme","award":["101061303"],"award-info":[{"award-number":["101061303"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/taslp.2024.3496316","type":"journal-article","created":{"date-parts":[[2024,11,11]],"date-time":"2024-11-11T18:44:10Z","timestamp":1731350650000},"page":"5010-5023","source":"Crossref","is-referenced-by-count":1,"title":["$\\mathcal {P}$owMix: A Versatile Regularizer for Multimodal Sentiment Analysis"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6042-9584","authenticated-orcid":false,"given":"Efthymios","family":"Georgiou","sequence":"first","affiliation":[{"name":"School of ECE, National Technical University of Athens, Athens, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7476-4482","authenticated-orcid":false,"given":"Yannis","family":"Avrithis","sequence":"additional","affiliation":[{"name":"Institute of Advanced Research on Artificial Intelligence (IARAI), Vienna, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1532-5288","authenticated-orcid":false,"given":"Alexandros","family":"Potamianos","sequence":"additional","affiliation":[{"name":"School of ECE, National Technical University of Athens, Athens, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2012.2236291"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2930434"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2017.02.003"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2021.3097002"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.compedu.2019.103649"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2011.40"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2017.08.003"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1115"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413678"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17289"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3178231"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.62"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3656580"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01271"},{"key":"ref16","first-page":"24043","article-title":"Characterizing and overcoming the greedy nature of learning in multi-modal deep neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wu","year":"2022"},{"key":"ref17","first-page":"10944","article-title":"What makes multi-modal learning better than single (provably)","volume-title":"Proc. 35th Int. Conf. Neural Inf. Process. Syst.","author":"Huang","year":"2021"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2020.09.005"},{"key":"ref19","first-page":"9226","article-title":"Modality competition: What makes joint training of multi-modal network fail in deep learning? (Provably)","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","volume":"162","author":"Huang","year":"2022"},{"key":"ref20","first-page":"8632","article-title":"On uni-modal feature learning in supervised multi-modal learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Du","year":"2023"},{"key":"ref21","first-page":"4385","article-title":"Learning multimodal data augmentation in feature space","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Liu","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1739"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3536221.3556630"},{"key":"ref24","first-page":"1","article-title":"mixup: Beyond empirical risk management","volume-title":"Proc. 6th Int. Conf. Learn. Representations","author":"Zhang","year":"2018"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01182"},{"key":"ref26","first-page":"61923","article-title":"Embedding space interpolation beyond mini-batch, beyond pairs and beyond examples","volume-title":"Proc. 37th Int. Conf. Neural Inf. Process. Syst.","author":"Venkataramanan","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2016.94"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1208"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.343"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2017.134"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1207"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3243"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.143"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.306"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.214"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548137"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.109259"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.49"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3183830"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016892"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547754"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.723"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2023.3274829"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3267882"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.534"},{"issue":"140","key":"ref47","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref48","volume-title":"Deep Learning","author":"Goodfellow","year":"2016"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_26"},{"key":"ref51","article-title":"Openmixup: Open mixup toolbox and benchmark for visual representation learning","author":"Li","year":"2022"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.285"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-103"},{"key":"ref54","first-page":"6438","article-title":"Manifold mixup: Better representations by interpolating hidden states","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Verma","year":"2019"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5822"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-65414-6_9"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3147"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.305"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW58289.2023.00042"},{"key":"ref60","first-page":"22680","article-title":"VLMixer: Unpaired vision-language pre-training via cross-modal CutMix","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","author":"Wang","year":"2022"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-demo.20"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2014.6853739"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.25080\/Majora-7b98e3ed-003"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00019"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3282953"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-77116-8_13"},{"key":"ref68","first-page":"8026","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Paszke","year":"2019"},{"key":"ref69","first-page":"1","article-title":"Adam: A method for stochastic gradient descent","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2992393"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.50"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6570655\/10304349\/10750299.pdf?arnumber=10750299","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T09:10:37Z","timestamp":1732698637000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10750299\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":71,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3496316","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}