{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T16:31:36Z","timestamp":1784737896999,"version":"3.55.0"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Assistive Augmentation Research Grant through the Entrepreneurial Universities (EU) initiative of New Zealand"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2020.3026823","type":"journal-article","created":{"date-parts":[[2020,9,25]],"date-time":"2020-09-25T20:47:53Z","timestamp":1601066873000},"page":"176274-176285","source":"Crossref","is-referenced-by-count":143,"title":["Multimodal Emotion Recognition With Transformer-Based Self Supervised Feature Fusion"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0688-7901","authenticated-orcid":false,"given":"Shamane","family":"Siriwardhana","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1777-231X","authenticated-orcid":false,"given":"Tharindu","family":"Kaluarachchi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mark","family":"Billinghurst","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7441-5493","authenticated-orcid":false,"given":"Suranga","family":"Nanayakkara","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2926751"},{"key":"ref38","article-title":"VoxCeleb2: Deep speaker recognition","author":"son chung","year":"2018","journal-title":"arXiv 1806 05622"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5446"},{"key":"ref32","article-title":"Language models are few-shot learners","author":"brown","year":"2020","journal-title":"arXiv 2005 14165"},{"key":"ref31","article-title":"Pretrained AI models: Performativity, mobility, and change","author":"varshney","year":"2019","journal-title":"arXiv 1909 03290"},{"key":"ref30","article-title":"Release strategies and the social impacts of language models","author":"solaiman","year":"2019","journal-title":"arXiv 1908 09203"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref36","article-title":"Representation learning with contrastive predictive coding","author":"van den oord","year":"2018","journal-title":"arXiv 1807 03748"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.11"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00973"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.167"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00202"},{"key":"ref2","author":"goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/1140.001.0001"},{"key":"ref20","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"arXiv 1810 04805"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-018-9491-z"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2010.09.020"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052937"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3758\/s13428-017-0996-1"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8462891"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-3307"},{"key":"ref50","article-title":"Convolutional neural networks pretrained on large face recognition datasets for emotion classification from video","author":"knyazev","year":"2017","journal-title":"arXiv 1711 04598"},{"key":"ref10","article-title":"Transfer learning from sound representations for anger detection in speech","author":"ezzeldin","year":"2019","journal-title":"arXiv 1902 02120"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3389\/fcomp.2020.00009"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"ref12","article-title":"Deep net features for complex emotion recognition","author":"nagarajan","year":"2018","journal-title":"arXiv 1811 00003"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2984368"},{"key":"ref14","article-title":"Learning relationships between text, audio, and video via deep canonical correlation for multimodal language analysis","author":"sun","year":"2019","journal-title":"arXiv 1911 05544"},{"key":"ref15","article-title":"Self-supervised visual feature learning with deep neural networks: A survey","author":"jing","year":"2019","journal-title":"arXiv 1902 06162"},{"key":"ref16","article-title":"Self-supervised learning of a facial attribute embedding from video","author":"wiles","year":"2018","journal-title":"arXiv 1808 06882"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref18","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref19","article-title":"RoBERTa: A robustly optimized BERT pretraining approach","author":"liu","year":"2019","journal-title":"arXiv 1907 11692"},{"key":"ref4","first-page":"2236","article-title":"Multimodal language analysis in the wild: CMU-MOSEI dataset and interpretable dynamic fusion graph","volume":"1","author":"zadeh","year":"2018","journal-title":"Proc Annual Meeting of the Assoc Computational Linguistics"},{"key":"ref3","article-title":"MELD: A multimodal multi-party dataset for emotion recognition in conversations","author":"poria","year":"2018","journal-title":"arXiv 1810 02508"},{"key":"ref6","author":"ekman","year":"1997","journal-title":"What the Face Reveals Basic and Applied Studies of Spontaneous Expression using the Facial Action Coding System (FACS)"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853739"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/2818346.2830593"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref49","article-title":"Self-supervised learning for ECG-based emotion recognition","author":"sarkar","year":"2019","journal-title":"arXiv 1910 07497"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/BigDataSecurity-HPSC-IDS.2019.00027"},{"key":"ref46","first-page":"5642","article-title":"Multi-attention recurrent network for human communication comprehension","author":"zadeh","year":"2018","journal-title":"Proc 32nd AAAI Conf Artif Intell"},{"key":"ref45","article-title":"MOSI: Multimodal corpus of sentiment intensity and subjectivity analysis in online opinion videos","author":"zadeh","year":"2016","journal-title":"arXiv 1606 06259"},{"key":"ref48","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","author":"lu","year":"2019","journal-title":"arXiv 1908 02265"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/755"},{"key":"ref42","article-title":"Retinaface: Single-stage dense face localisation in the wild","author":"deng","year":"2019","journal-title":"arXiv 1905 00641"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1015"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref43","article-title":"SQuAD: Integrating PCE and Non-PCE approaches","author":"sido","year":"2019"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/09206016.pdf?arnumber=9206016","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:56:12Z","timestamp":1639770972000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9206016\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/access.2020.3026823","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}