{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T09:23:24Z","timestamp":1780392204016,"version":"3.54.1"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"24","license":[{"start":{"date-parts":[[2023,5,16]],"date-time":"2023-05-16T00:00:00Z","timestamp":1684195200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,5,16]],"date-time":"2023-05-16T00:00:00Z","timestamp":1684195200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2019YFB1405803"],"award-info":[{"award-number":["2019YFB1405803"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61772125"],"award-info":[{"award-number":["61772125"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2023,8]]},"DOI":"10.1007\/s00521-023-08638-2","type":"journal-article","created":{"date-parts":[[2023,5,16]],"date-time":"2023-05-16T10:04:53Z","timestamp":1684231493000},"page":"17619-17632","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["HAAN-ERC: hierarchical adaptive attention network for multimodal emotion recognition in conversation"],"prefix":"10.1007","volume":"35","author":[{"given":"Tao","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9870-8925","authenticated-orcid":false,"given":"Zhenhua","family":"Tan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoer","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,5,16]]},"reference":[{"key":"8638_CR1","first-page":"1064","volume-title":"Learning what and when to drop: adaptive multimodal and contextual dynamics for emotion recognition in conversation","author":"F Chen","year":"2021","unstructured":"Chen F, Sun Z, Ouyang D, Liu X, Shao J (2021) Learning what and when to drop: adaptive multimodal and contextual dynamics for emotion recognition in conversation. Association for Computing Machinery, New York, pp 1064\u20131073"},{"key":"8638_CR2","doi-asserted-by":"crossref","unstructured":"Hazarika D, Poria S, Mihalcea R, Cambria E, Zimmermann R (2018) ICON: interactive conversational memory network for multimodal emotion detection. In: Proceedings of the 2018 conference on empirical methods in natural language processing, Association for Computational Linguistics, Brussels, pp 2594\u20132604","DOI":"10.18653\/v1\/D18-1280"},{"key":"8638_CR3","doi-asserted-by":"crossref","unstructured":"Hazarika D, Poria S, Zadeh A, Cambria E, Morency L-P, Zimmermann R (2018) Conversational memory network for emotion recognition in dyadic dialogue videos. In: Proceedings of the 2018 Conference of the North American chapter of the association for computational linguistics: human language technologies, vol 1 (Long Papers), Association for Computational Linguistics, New Orleans, pp 2122\u20132132","DOI":"10.18653\/v1\/N18-1193"},{"key":"8638_CR4","doi-asserted-by":"crossref","unstructured":"Majumder N, Poria S, Hazarika D, Mihalcea R, Gelbukh AF, Cambria E (2019) Dialoguernn: an attentive RNN for emotion detection in conversations. In: The thirty-third AAAI conference on artificial intelligence, AAAI 2019, The thirty-first innovative applications of artificial intelligence conference, IAAI 2019, The ninth AAAI symposium on educational advances in artificial intelligence, EAAI 2019, Honolulu, January 27\u2013February 1, 2019, pp 6818\u20136825","DOI":"10.1609\/aaai.v33i01.33016818"},{"key":"8638_CR5","unstructured":"Hsu C-C, Chen S-Y, Kuo C-C, Huang T-H, Ku L-W (2018) Emotionlines: an emotion corpus of multi-party conversations. In: Proceedings of the eleventh international conference on language resources and evaluation (LREC 2018). European Language Resources Association (ELRA), Miyazaki"},{"key":"8638_CR6","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser \u0141, Polosukhin I (2017) Attention is all you need. Adv Neural Inf Process Syst 30"},{"key":"8638_CR7","doi-asserted-by":"crossref","unstructured":"Han K, Wang Y, Chen H, Chen X, Guo J, Liu Z, Tang Y, Xiao A, Xu C, Xu Y, Yang Z, Zhang Y, Tao D (2022) A survey on vision transformer. IEEE Trans Pattern Anal Mach Intell 1\u20131","DOI":"10.1109\/TPAMI.2022.3152247"},{"key":"8638_CR8","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2021.103982","volume":"126","author":"KS Kalyan","year":"2022","unstructured":"Kalyan KS, Rajasekharan A, Sangeetha S (2022) AMMU: a survey of transformer-based biomedical pretrained language models. J Biomed Inf 126:103982","journal-title":"J Biomed Inf"},{"issue":"4","key":"8638_CR9","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1007\/s10579-008-9076-6","volume":"42","author":"C Busso","year":"2008","unstructured":"Busso C, Bulut M, Lee C-C, Kazemzadeh A, Mower E, Kim S, Chang JN, Lee S, Narayanan SS (2008) IEMOCAP: interactive emotional dyadic motion capture database. Lang Resour Eval 42(4):335\u2013359","journal-title":"Lang Resour Eval"},{"key":"8638_CR10","doi-asserted-by":"crossref","unstructured":"Poria S, Hazarika D, Majumder N, Naik G, Cambria E, Mihalcea R (2019) MELD: a multimodal multi-party dataset for emotion recognition in conversations. In: Korhonen A, Traum DR, M\u00e0rquez L (eds) Proceedings of the 57th conference of the association for computational linguistics, ACL 2019, Florence, July 28\u2013August 2, 2019, vol 1 (Long Papers), pp 527\u2013536","DOI":"10.18653\/v1\/P19-1050"},{"key":"8638_CR11","doi-asserted-by":"crossref","unstructured":"Ghosal D, Majumder N, Poria S, Chhaya N, Gelbukh A (2019) Dialoguegcn: a graph convolutional neural network for emotion recognition in conversation. In: Proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing (EMNLP-IJCNLP)","DOI":"10.18653\/v1\/D19-1015"},{"key":"#cr-split#-8638_CR12.1","doi-asserted-by":"crossref","unstructured":"Zhang D, Wu L, Sun C, Li S, Zhu Q, Zhou G (2019) Modeling both context- and speaker-sensitive dependence for emotion detection in multi-speaker conversations. In: Kraus S","DOI":"10.24963\/ijcai.2019\/752"},{"key":"#cr-split#-8638_CR12.2","unstructured":"(ed) Proceedings of the twenty-eighth international joint conference on artificial intelligence, IJCAI 2019, Macao, August 10-16, 2019, pp 5415-5421"},{"key":"8638_CR13","doi-asserted-by":"crossref","unstructured":"Shen W, Chen J, Quan X, Xie Z (2021) Dialogxl: All-in-one xlnet for multi-party conversation emotion recognition. In: Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI 2021, Thirty-third conference on innovative applications of artificial intelligence, IAAI 2021, The eleventh symposium on educational advances in artificial intelligence, EAAI 2021, Virtual Event, February 2\u20139, 2021, pp 13789\u201313797","DOI":"10.1609\/aaai.v35i15.17625"},{"key":"8638_CR14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.inffus.2020.06.005","volume":"65","author":"D Hazarika","year":"2021","unstructured":"Hazarika D, Poria S, Zimmermann R, Mihalcea R (2021) Conversational transfer learning for emotion recognition. Inf Fusion 65:1\u201312","journal-title":"Inf Fusion"},{"key":"8638_CR15","doi-asserted-by":"crossref","unstructured":"Ghosal D, Majumder N, Gelbukh AF, Mihalcea R, Poria S (2020) COSMIC: commonsense knowledge for emotion identification in conversations. In: Findings of the association for computational linguistics: EMNLP 2020, Online Event, 16\u201320 November 2020, pp 2470\u20132481","DOI":"10.18653\/v1\/2020.findings-emnlp.224"},{"key":"8638_CR16","doi-asserted-by":"crossref","unstructured":"Jiao W, Lyu MR, King I (2020) Real-time emotion recognition via attention gated hierarchical memory network. In: The thirty-fourth AAAI conference on artificial intelligence, AAAI 2020, The thirty-second innovative applications of artificial intelligence conference, IAAI 2020, The tenth AAAI symposium on educational advances in artificial intelligence, EAAI 2020, New York, February 7\u201312, 2020, pp 8002\u20138009","DOI":"10.1609\/aaai.v34i05.6309"},{"key":"8638_CR17","doi-asserted-by":"crossref","unstructured":"Guo Y, Shi H, Kumar A, Grauman K, Feris R (2019) Spottune: Transfer learning through adaptive fine-tuning. In: 2019 IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR.2019.00494"},{"key":"8638_CR18","doi-asserted-by":"crossref","unstructured":"Ahn C, Kim E, Oh S (2019) Deep elastic networks with model selection for multi-task learning. In: 2019 IEEE\/CVF international conference on computer vision (ICCV)","DOI":"10.1109\/ICCV.2019.00663"},{"key":"8638_CR19","unstructured":"Rosenbaum C, Klinger T, Riemer M (2017) Routing networks: adaptive selection of non-linear functions for multi-task learning. Preprint arXiv:1711.01239"},{"key":"8638_CR20","first-page":"8728","volume":"33","author":"X Sun","year":"2020","unstructured":"Sun X, Panda R, Feris R, Saenko K (2020) Adashare: learning what to share for efficient deep multi-task learning. Adv Neural Inf Process Syst 33:8728\u20138740","journal-title":"Adv Neural Inf Process Syst"},{"key":"8638_CR21","doi-asserted-by":"crossref","unstructured":"Zhang T, Huang M, Zhao L (2018) Learning structured representation for text classification via reinforcement learning. In: Proceedings of the AAAI conference on artificial intelligence, vol 32","DOI":"10.1609\/aaai.v32i1.12047"},{"key":"8638_CR22","doi-asserted-by":"crossref","unstructured":"Veit A, Belongie S (2018) Convolutional networks with adaptive inference graphs. In: Proceedings of the European conference on computer vision (ECCV), pp 3\u201318","DOI":"10.1007\/978-3-030-01246-5_1"},{"key":"8638_CR23","doi-asserted-by":"crossref","unstructured":"Wu Z, Nagarajan T, Kumar A, Rennie S, Davis LS, Grauman K, Feris R (2018) Blockdrop: dynamic inference paths in residual networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 8817\u20138826","DOI":"10.1109\/CVPR.2018.00919"},{"key":"8638_CR24","doi-asserted-by":"crossref","unstructured":"Zhang D, Li S, Zhu Q, Zhou G (2019) Effective sentiment-relevant word selection for multi-modal sentiment analysis in spoken language. In: Proceedings of the 27th ACM international conference on multimedia, pp 148\u2013156","DOI":"10.1145\/3343031.3350987"},{"key":"8638_CR25","doi-asserted-by":"crossref","unstructured":"Panda R, Chen C-FR, Fan Q, Sun X, Saenko K, Oliva A, Feris R (2021) Adamml: adaptive multi-modal learning for efficient video recognition. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 7576\u20137585","DOI":"10.1109\/ICCV48922.2021.00748"},{"key":"8638_CR26","unstructured":"Liu Y, Ott M, Goyal N, Du J, Joshi M, Chen D, Levy O, Lewis M, Zettlemoyer L, Stoyanov V (2019) Roberta: a robustly optimized bert pretraining approach. Preprint arXiv:1907.11692"},{"key":"8638_CR27","doi-asserted-by":"crossref","unstructured":"Eyben F, W\u00f6llmer M, Schuller B (2010) Opensmile: the Munich versatile and fast open-source audio feature extractor. In: Proceedings of the 18th ACM international conference on multimedia, pp 1459\u20131462","DOI":"10.1145\/1873951.1874246"},{"key":"8638_CR28","unstructured":"Jang E, Gu S, Poole B (2016) Categorical reparameterization with gumbel-softmax. Preprint arXiv:1611.01144"},{"key":"8638_CR29","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR), pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"8638_CR30","unstructured":"Ba JL, Kiros JR, Hinton GE (2016) Layer normalization"},{"key":"8638_CR31","doi-asserted-by":"crossref","unstructured":"Ghosal D, Majumder N, Poria S, Chhaya N, Gelbukh A (2019) Dialoguegcn: a graph convolutional neural network for emotion recognition in conversation. Preprint arXiv:1908.11540","DOI":"10.18653\/v1\/D19-1015"},{"key":"8638_CR32","unstructured":"Kingma D, Ba J (2014) Adam: a method for stochastic optimization. Computer Science"},{"key":"8638_CR33","unstructured":"Loshchilov I, Hutter F (2017) Decoupled weight decay regularization. Preprint arXiv:1711.05101"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-023-08638-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-023-08638-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-023-08638-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,26]],"date-time":"2023-07-26T17:49:43Z","timestamp":1690393783000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-023-08638-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,16]]},"references-count":34,"journal-issue":{"issue":"24","published-print":{"date-parts":[[2023,8]]}},"alternative-id":["8638"],"URL":"https:\/\/doi.org\/10.1007\/s00521-023-08638-2","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,5,16]]},"assertion":[{"value":"7 October 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 May 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 May 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to participate"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"Not applicable.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval"}}]}}