{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,25]],"date-time":"2026-10-25T14:07:56Z","timestamp":1792937276236,"version":"4.5.0"},"reference-count":48,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2022,11,14]],"date-time":"2022-11-14T00:00:00Z","timestamp":1668384000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,11,14]],"date-time":"2022-11-14T00:00:00Z","timestamp":1668384000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61962057"],"award-info":[{"award-number":["61962057"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U2003208"],"award-info":[{"award-number":["U2003208"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Autonomous Region Key R&D Project","award":["2021B01002"],"award-info":[{"award-number":["2021B01002"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Cogn Comput"],"published-print":{"date-parts":[[2023,1]]},"DOI":"10.1007\/s12559-022-10073-9","type":"journal-article","created":{"date-parts":[[2022,11,14]],"date-time":"2022-11-14T02:02:46Z","timestamp":1668391366000},"page":"289-303","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":54,"title":["TEDT: Transformer-Based Encoding\u2013Decoding Translation Network for Multimodal Sentiment Analysis"],"prefix":"10.1007","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0953-1276","authenticated-orcid":false,"given":"Fan","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shengwei","family":"Tian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Long","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junwen","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kun","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongtao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,11,14]]},"reference":[{"key":"10073_CR1","doi-asserted-by":"publisher","first-page":"271","DOI":"10.3115\/1218955.1218990","volume-title":"A sentimental education: sentiment analysis using subjectivity summarization based on minimum cuts","author":"P Bo","year":"2004","unstructured":"Bo P, Lillian L. A sentimental education: sentiment analysis using subjectivity summarization based on minimum cuts. Proceedings of the Association for Computational Linguistics; 2004. p. 271\u20138. https:\/\/doi.org\/10.3115\/1218955.1218990."},{"issue":"6","key":"10073_CR2","doi-asserted-by":"publisher","first-page":"282","DOI":"10.1007\/978-1-4899-7502-7","volume":"2","author":"G Vinodhini","year":"2012","unstructured":"Vinodhini G, Chandrasekaran RM. Sentiment analysis and opinion mining: a survey. Int J. 2012;2(6):282\u201392. https:\/\/doi.org\/10.1007\/978-1-4899-7502-7.","journal-title":"Int J"},{"key":"10073_CR3","doi-asserted-by":"publisher","first-page":"55","DOI":"10.3115\/v1\/P14-5010","volume-title":"The Stanford CoreNLP natural language processing toolkit","author":"C Manning","year":"2014","unstructured":"Manning C, Surdeanu M, Bauer J. The Stanford CoreNLP natural language processing toolkit. Proceedings of the Association for Computational Linguistics; 2014. p. 55\u201360. https:\/\/doi.org\/10.3115\/v1\/P14-5010."},{"key":"10073_CR4","doi-asserted-by":"publisher","first-page":"873","DOI":"10.18653\/v1\/P17-1081","volume-title":"Context-dependent sentiment analysis in user-generated videos","author":"S Poria","year":"2017","unstructured":"Poria S, Cambria E, Hazarika D. Context-dependent sentiment analysis in user-generated videos, vol. 1. Proceedings of the Association for Computational Linguistics; 2017. p. 873\u201383. https:\/\/doi.org\/10.18653\/v1\/P17-1081."},{"issue":"2","key":"10073_CR5","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1109\/TPAMI.2018.2798607","volume":"41","author":"T Baltru\u0161aitis","year":"2019","unstructured":"Baltru\u0161aitis T, Ahuja C, Morency L-P. Multimodal machine learning: a survey and taxonomy. IEEE Trans Pattern Anal Mach Intell. 2019;41(2):423\u201343. https:\/\/doi.org\/10.1109\/TPAMI.2018.2798607.","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"10073_CR6","doi-asserted-by":"publisher","first-page":"124","DOI":"10.1016\/j.knosys.2018.07.041","volume":"161","author":"N Majumder","year":"2018","unstructured":"Majumder N, Hazarika D, Gelbukh A, Cambria E, Poria S. Multimodal sentiment analysis using hierarchical fusion with context modeling. Knowl Based Syst. 2018;161:124\u201333. https:\/\/doi.org\/10.1016\/j.knosys.2018.07.041.","journal-title":"Knowl Based Syst"},{"key":"10073_CR7","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1145\/3219819.3219853","volume-title":"Multimodal sentiment analysis to explore the structure of emotions","author":"A Hu","year":"2018","unstructured":"Hu A, Flaxman S. Multimodal sentiment analysis to explore the structure of emotions, vol. 9. New York, NY, USA: Proceedings of the Association for Computing Machinery; 2018. p. 350\u20138. https:\/\/doi.org\/10.1145\/3219819.3219853."},{"key":"10073_CR8","doi-asserted-by":"publisher","first-page":"2507","DOI":"10.1007\/s11042-015-2646-x","volume":"75","author":"C Baecchi","year":"2016","unstructured":"Baecchi C, Uricchio T, Bertini M, et al. A multimodal feature learning approach for sentiment analysis of social network multimedia. Multimed Tools Appl. 2016;75:2507\u201325. https:\/\/doi.org\/10.1007\/s11042-015-2646-x.","journal-title":"Multimed Tools Appl"},{"key":"10073_CR9","doi-asserted-by":"publisher","first-page":"2887","DOI":"10.1007\/s11042-020-08836-3","volume":"80","author":"YR Pandeya","year":"2021","unstructured":"Pandeya YR, Lee J. Deep learning-based late fusion of multimodal information for emotion classification of music video. Multimed Tools Appl. 2021;80:2887\u2013905. https:\/\/doi.org\/10.1007\/s11042-020-08836-3.","journal-title":"Multimed Tools Appl"},{"key":"10073_CR10","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1016\/j.inffus.2017.02.003","volume":"37","author":"S Poria","year":"2017","unstructured":"Poria S, Cambria E, Bajpai R, Hussain A. A review of affective computing: from unimodal analysis to multimodal fusion. Inform Fusion. 2017;37:98\u2013125.","journal-title":"Inform Fusion"},{"key":"10073_CR11","first-page":"19","volume-title":"Multilogue-Net: A context-aware RNN for multi-modal emotion detection and sentiment analysis in conversation","author":"A Shenoy","year":"2020","unstructured":"Shenoy A, Sardana A. Multilogue-Net: A context-aware RNN for multi-modal emotion detection and sentiment analysis in conversation. Proceedings of the Second Grand Challenge and Workshop on Multimodal Language; 2020. p. 19\u201328."},{"key":"10073_CR12","doi-asserted-by":"publisher","first-page":"1103","DOI":"10.18653\/v1\/d17-1115","volume-title":"Tensor fusion network for multimodal sentiment analysis","author":"A Zadeh","year":"2017","unstructured":"Zadeh A, Chen M, Poria S. Tensor fusion network for multimodal sentiment analysis. Proceedings of the Association for Computational Linguistics; 2017. p. 1103\u201314. https:\/\/doi.org\/10.18653\/v1\/d17-1115."},{"issue":"1","key":"10073_CR13","first-page":"5634","volume":"32","author":"A Zadeh","year":"2018","unstructured":"Zadeh A, Liang P, Mazumder N, Poria S. Memory fusion network for multi-view sequential learning. Proc AAAI Conf Artif Intell. 2018;32(1):5634\u201341.","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"10073_CR14","doi-asserted-by":"publisher","first-page":"150","DOI":"10.18653\/v1\/D18-1014","volume-title":"Multimodal language analysis with recurrent multistage fusion","author":"P Liang","year":"2018","unstructured":"Liang P, Liu Z, Zadeh A, Morency L. Multimodal language analysis with recurrent multistage fusion. Proceedings of the Association for Computational Linguistics; 2018. p. 150\u201361. https:\/\/doi.org\/10.18653\/v1\/D18-1014."},{"key":"10073_CR15","doi-asserted-by":"publisher","first-page":"3454","DOI":"10.18653\/v1\/D18-1382","volume-title":"Contextual intermodal attention for multi-modal sentiment analysis","author":"D Ghosal","year":"2018","unstructured":"Ghosal D, Akhtar MS, Chauhan D, Poria S. Contextual intermodal attention for multi-modal sentiment analysis. Proceedings of the Association for Computational Linguistics; 2018. p. 3454\u201366. https:\/\/doi.org\/10.18653\/v1\/D18-1382."},{"key":"10073_CR16","first-page":"4171","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019, Minneapolis, MN, USA, vol 1, June 2\u20137, 2019, (Long and Short Papers)","author":"J Devlin","year":"2019","unstructured":"Devlin J, Chang M, Lee K, Toutanova K. BERT: pre-training of deep bidirectional transformers for language understanding. In: Burstein J, Doran C, Solorio T, editors. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019, Minneapolis, MN, USA, vol 1, June 2\u20137, 2019\u00a0(Long and Short Papers). Association for Computational Linguistics; 2019. p. 4171\u201386."},{"key":"10073_CR17","first-page":"2247","volume-title":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, ACL 2018, Melbourne, Australia, July 15\u201320, 2018, Volume 1: Long Papers","author":"Z Liu","year":"2018","unstructured":"Liu Z, Shen Y, Lakshminarasimhan VB, Liang PP, Zadeh A, Morency L. Efficient low-rank multimodal fusion with modality-specific factors. In: Gurevych I, Miyao Y, editors. Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, ACL 2018, Melbourne, Australia, July 15\u201320, 2018, Volume 1: Long Papers. Association for Computational Linguistics; 2018. p. 2247\u201356."},{"issue":"1","key":"10073_CR18","first-page":"5634","volume":"32","author":"A Zadeh","year":"2018","unstructured":"Zadeh A, Liang PP, Mazumder N, Poria S, Cambria E, Morency L-P. Memory fusion network for multi-view sequential learning. Proc AAAI Conf Artif Intell. 2018;32(1):5634\u201341.","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"10073_CR19","doi-asserted-by":"publisher","first-page":"3454","DOI":"10.18653\/v1\/D18-1382","volume-title":"Contextual intermodal attention for multi-modal sentiment analysis","author":"D Ghosal","year":"2018","unstructured":"Ghosal D, Akhtar MS, Chauhan D, Poria S. Contextual intermodal attention for multi-modal sentiment analysis. Proceedings of the Association for Computational Linguistics; 2018. p. 3454\u201366. https:\/\/doi.org\/10.18653\/v1\/D18-1382."},{"key":"10073_CR20","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1145\/3462244.3479919","volume-title":"Bi-bimodal modality fusion for correlation-controlled multimodal sentiment analysis","author":"W Han","year":"2021","unstructured":"Han W, Chen H, Gelbukh A, Zadeh A, et al. Bi-bimodal modality fusion for correlation-controlled multimodal sentiment analysis. ICMI \u201921: Proceedings of the 2021 International Conference on Multimodal Interaction; 2021. p. 6\u201315. https:\/\/doi.org\/10.1145\/3462244.3479919."},{"issue":"12","key":"10073_CR21","doi-asserted-by":"publisher","first-page":"10790","DOI":"10.18653\/v1\/D18-1382","volume":"35","author":"W Yu","year":"2021","unstructured":"Yu W, Xu H, Yuan Z, Wu J. Learning modality-specific representations with self-supervised multi-task learning for multimodal sentiment analysis. Proc AAAI Conf Artif Intell. 2021;35(12):10790\u20137. https:\/\/doi.org\/10.18653\/v1\/D18-1382.","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"10073_CR22","first-page":"9180","volume-title":"Improving multimodal fusion with hierarchical mutual information maximization for multimodal sentiment analysis","author":"W Han","year":"2021","unstructured":"Han W, Chen H, Poria S. Improving multimodal fusion with hierarchical mutual information maximization for multimodal sentiment analysis. Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing; 2021. p. 9180\u201392."},{"key":"10073_CR23","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1016\/j.inffus.2020.08.006","volume":"65","author":"Q Li","year":"2021","unstructured":"Li Q, Gkoumas D, Lioma C, Melucci M. Quantum-inspired multimodal fusion for video sentiment analysis. Inf Fusion. 2021;65:58\u201371.","journal-title":"Inf Fusion"},{"key":"10073_CR24","doi-asserted-by":"publisher","first-page":"454","DOI":"10.1109\/LSP.2021.3139856","volume":"29","author":"J He","year":"2022","unstructured":"He J, Hu H. MF-BERT: Multimodal fusion in pre-trained BERT for sentiment analysis. IEEE Signal Process Lett. 2022;29:454\u20138.","journal-title":"IEEE Signal Process Lett"},{"key":"10073_CR25","doi-asserted-by":"publisher","first-page":"4730","DOI":"10.18653\/v1\/2021.findings-acl.417","volume-title":"Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021","author":"Y Wu","year":"2021","unstructured":"Wu Y, Lin Z, Zhao Y, Qin B, Zhu L-N. A text-centered shared-private framework via cross-modal prediction for multimodal sentiment analysis. In: Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021. Association for Computational Linguistics; 2021. p. 4730\u20138."},{"key":"10073_CR26","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1109\/ICDMW53433.2021.00025","volume-title":"2021 International Conference on Data Mining Workshops (ICDMW)","author":"D Jiang","year":"2021","unstructured":"Jiang D, Wei R, Liu H, Wen J, Tu G, Zheng L, Cambria E. A multitask learning framework for multimodal sentiment analysis. In: 2021 International Conference on Data Mining Workshops (ICDMW). IEEE; 2021. p. 151\u20137."},{"key":"10073_CR27","doi-asserted-by":"publisher","first-page":"2015","DOI":"10.1109\/TASLP.2022.3178204","volume":"30","author":"B Yang","year":"2022","unstructured":"Yang B, Wu L, Zhu J, Shao B, Lin X, Liu TY. Multimodal sentiment analysis with two-phase multi-task learning. IEEE\/ACM Trans Audio Speech Language Process. 2022;30:2015\u201324.","journal-title":"IEEE\/ACM Trans Audio Speech Language Process"},{"issue":"1","key":"10073_CR28","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1109\/TAFFC.2019.2926724","volume":"13","author":"S Akhtar","year":"2019","unstructured":"Akhtar S, Ghosal D, Ekbal A, Bhattacharyya P, Kurohashi S. All-in-one: Emotion, sentiment and intensity prediction using a multi-task ensemble framework. IEEE Trans Affect Comput. 2019;13(1):285\u201397. https:\/\/doi.org\/10.1109\/TAFFC.2019.2926724.","journal-title":"IEEE Trans Affect Comput"},{"key":"10073_CR29","volume-title":"Artificial Neural Networks and Machine Learning \u2013 ICANN 2022. ICANN 2022. Lecture Notes in Computer Science","author":"Y Wang","year":"2022","unstructured":"Wang Y, Chen Z, Chen S, Zhu Y. Multi-task Learning for Multimodal Emotion Recognition. In: Pimenidis E, Angelov P, Jayne C, Papaleonidas A, Aydin ML, editors. Artificial Neural Networks and Machine Learning \u2013 ICANN 2022. ICANN 2022. Lecture Notes in Computer Science, vol. 13531. Cham: Springer; 2022."},{"key":"10073_CR30","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1016\/j.knosys.2022.109924","volume-title":"Artificial Intelligence in China. Lecture Notes in Electrical Engineering","author":"Y Song","year":"2022","unstructured":"Song Y, Fan X, Yang Y, Ren G, Pan W. A Cross-Modal Attention and Multi-task Learning Based Approach for Multi-modal Sentiment Analysis. In: Liang Q, Wang W, Mu J, Liu X, Na Z, editors. Artificial Intelligence in China. Lecture Notes in Electrical Engineering, vol. 854. Singapore: Springer; 2022. p. 159\u201366. https:\/\/doi.org\/10.1016\/j.knosys.2022.109924."},{"issue":"5","key":"10073_CR31","doi-asserted-by":"publisher","first-page":"103038","DOI":"10.1016\/j.ipm.2022.103038","volume":"59","author":"L Yang","year":"2022","unstructured":"Yang L, Na J-C, Yu J. Cross-Modal Multitask Transformer for End-to-End Multimodal Aspect-Based Sentiment Analysis. Inf Process Manag. 2022;59(5):103038 ISSN 0306\u20134573.","journal-title":"Inf Process Manag"},{"key":"10073_CR32","doi-asserted-by":"publisher","first-page":"109924","DOI":"10.1016\/j.knosys.2022.109924","volume":"257","author":"DS Chauhan","year":"2022","unstructured":"Chauhan DS, Singh GV, Arora A, Ekbal A, Bhattacharyya P. An emoji-aware multitask framework for multimodal sarcasm detection. Knowl Based Syst. 2022;257:109924. https:\/\/doi.org\/10.1016\/j.knosys.2022.109924 ISSN 0950\u20137051.","journal-title":"Knowl Based Syst"},{"key":"10073_CR33","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.106172","volume":"204","author":"H Li","year":"2020","unstructured":"Li H, Xu H. Deep reinforcement learning for robust emotional classification in facial expression recognition. Knowl Based Syst. 2020;204: 106172. https:\/\/doi.org\/10.1016\/j.knosys.2020.106172.","journal-title":"Knowl Based Syst"},{"key":"10073_CR34","first-page":"121","volume-title":"The Pacific Rim International Conference On Artificial Intelligence 2019","author":"Y Shu","year":"2019","unstructured":"Shu Y, Xu G. Emotion recognition from music enhanced by domain knowledge. In: The Pacific Rim International Conference On Artificial Intelligence 2019. Trends In Artificial Intelligence; 2019. p. 121\u201334."},{"issue":"3","key":"10073_CR35","doi-asserted-by":"publisher","first-page":"1034","DOI":"10.1109\/TCSVT.2021.3072412","volume":"32","author":"K Zhang","year":"2021","unstructured":"Zhang K, Li Y, Wang J, Cambria E, Li X. Real-time video emotion recognition based on reinforcement learning and domain knowledge. IEEE Trans Circuits Syst Video Technol. 2021;32(3):1034\u201347.","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"10073_CR36","first-page":"6892","volume":"33","author":"H Pham","year":"2019","unstructured":"Pham H, Liang PP, Manzini T, Morency L-P, P\u00f3czos B. Found in translation: learning robust joint representations by cyclic translations between modalities. Proc AAAI Conf Artif Intell. 2019;33:6892\u20139.","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"10073_CR37","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1109\/CIHLI.2013.6613272","volume-title":"2013 IEEE Symposium on Computational Intelligence for Human-Like Intelligence (CIHLI)","author":"E Cambria","year":"2013","unstructured":"Cambria E, Howard N, Hsu J, Hussain A. Sentic blending: Scalable multimodal fusion for the continuous interpretation of semantics and sentics. In: 2013 IEEE Symposium on Computational Intelligence for Human-Like Intelligence (CIHLI). Singapore, Singapore: IEEE; 2013. p. 108\u201317. https:\/\/doi.org\/10.1109\/CIHLI.2013.6613272."},{"key":"10073_CR38","first-page":"5998","volume":"30","author":"A Vaswani","year":"2017","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser \u0141, Polosukhin I. Attention is all you need. Adv Neural Inf Process Syst. 2017;30:5998\u20136008.","journal-title":"Adv Neural Inf Process Syst"},{"key":"10073_CR39","unstructured":"Wu Y, Schuster M, Chen Z, Le QV, Norouzi M, Macherey W, Krikun M, Cao Y, Gao Q, Macherey K, Klingner J, Shah A, Johnson M, Liu X, Kaiser L, Gouws S, Kato Y, Kudo T, Kazawa H, Stevens K, Kurian G, Patil N, Wang W, Young C, Smith J, Riesa J, Rudnick A, Vinyals O, Corrado G, Hughes M, Dean J. Google\u2019s neural machine translation system: Bridging the gap between human and machine translation. http:\/\/arxiv.org\/abs\/1609.08144. Accessed 18 Oct 2016."},{"key":"10073_CR40","doi-asserted-by":"publisher","first-page":"1724","DOI":"10.3115\/v1\/d14-1179","volume-title":"Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, EMNLP 2014, October 25\u201329, 2014, Doha, Qatar, A meeting of SIGDAT, a Special Interest Group of the ACL","author":"K Cho","year":"2014","unstructured":"Cho K, van Merrienboer B, G\u00fcl\u00e7ehre \u00c7, Bahdanau D, Bougares F, Schwenk H, Bengio Y. Learning phrase representations using RNN encoder-decoder for statistical machine translation. In: Moschitti A, Pang B, Daelemans W, editors. Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, EMNLP 2014, October 25\u201329, 2014, Doha, Qatar, A meeting of SIGDAT, a Special Interest Group of the ACL. ACL; 2014. p. 1724\u201334. https:\/\/doi.org\/10.3115\/v1\/d14-1179."},{"key":"10073_CR41","doi-asserted-by":"crossref","unstructured":"Zadeh A, Zellers R, Pincus E, Morency L. MOSI: multimodal corpus of sentiment intensity and subjectivity analysis in online opinion videos. IEEE Intell Syst. 2016;31(6):82\u20138. http:\/\/arxiv.org\/abs\/1606.06259. Accessed 12 Aug 2016.","DOI":"10.1109\/MIS.2016.94"},{"key":"10073_CR42","first-page":"2236","volume-title":"Multimodal language analysis in the wild: Cmu-mosei dataset and interpretable dynamic fusion graph","author":"AB Zadeh","year":"2018","unstructured":"Zadeh AB, Liang PP, Poria S, Cambria E, Morency L-P. Multimodal language analysis in the wild: Cmu-mosei dataset and interpretable dynamic fusion graph. Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers); 2018. p. 2236\u201346."},{"key":"10073_CR43","doi-asserted-by":"publisher","first-page":"960","DOI":"10.1109\/ICASSP.2014.6853739","volume-title":"2014 IEEE international conference on acoustics, speech and signal processing (icassp)","author":"G Degottex","year":"2014","unstructured":"Degottex G, Kane J, Drugman T, Raitio T, Scherer S. COVAREP\u2013a collaborative voice analysis- repository for speech technologies. In: 2014 IEEE international conference on acoustics, speech and signal processing\n(icassp). IEEE; 2014. p. 960\u20134."},{"key":"10073_CR44","first-page":"7216","volume":"33","author":"Y Wang","year":"2019","unstructured":"Wang Y, Shen Y, Liu Z, Liang PP, Zadeh A, Morency L-P. Words can shift: Dynamically adjusting word representations using nonverbal behaviors. Proc AAAI Conf Artif Intell. 2019;33:7216\u201323.","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"10073_CR45","doi-asserted-by":"publisher","first-page":"6558","DOI":"10.18653\/v1\/P19-1656","volume-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, Florence, Italy","author":"YHH Tsai","year":"2019","unstructured":"Tsai YHH, Bai S, Liang PP, Kolter JZ, Morency LP, Salakhutdinov R. Multimodal transformer for unaligned multimodal language sequences. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, Florence, Italy. Association for Computational Linguistics; 2019. p. 6558\u201369."},{"key":"10073_CR46","unstructured":"Tsai YH, P Liang P, Zadeh A, Morency L, Salakhutdinov R. Learning factorized multimodal representations. In: 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, May 6\u20139, 2019. OpenReview.net;\u00a02019. https:\/\/openreview.net\/forum?id=rygqqsA9KX. Accessed 14 May 2019."},{"issue":"5","key":"10073_CR47","doi-asserted-by":"publisher","first-page":"8992","DOI":"10.1609\/aaai.v34i05.6431","volume":"34","author":"Z Sun","year":"2020","unstructured":"Sun Z, Sarma P, Sethares W, Liang Y. Learning Relationships between Text, Audio, and Video via Deep Canonical Correlation for Multimodal Language Analysis. Proc AAAI Conf Artif Intell. 2020;34(5):8992\u20139. https:\/\/doi.org\/10.1609\/aaai.v34i05.6431.","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"10073_CR48","first-page":"2359","volume-title":"Integrating multimodal information in large pretrained transformers","author":"W Rahman","year":"2020","unstructured":"Rahman W, Hasan MK, Lee S, Zadeh A, Mao C, Morency L-P, Hoque E. Integrating multimodal information in large pretrained transformers. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics; 2020. p. 2359\u201369."}],"container-title":["Cognitive Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12559-022-10073-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s12559-022-10073-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12559-022-10073-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,9]],"date-time":"2023-03-09T10:44:32Z","timestamp":1678358672000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s12559-022-10073-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,14]]},"references-count":48,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2023,1]]}},"alternative-id":["10073"],"URL":"https:\/\/doi.org\/10.1007\/s12559-022-10073-9","relation":{},"ISSN":["1866-9956","1866-9964"],"issn-type":[{"value":"1866-9956","type":"print"},{"value":"1866-9964","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,11,14]]},"assertion":[{"value":"29 June 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 November 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 November 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This article does not contain any studies with human participants or animals performed by any of the authors.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Approval"}},{"value":"The authors declare no competing interests.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of Interest"}}]}}