{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T05:30:34Z","timestamp":1769923834954,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":24,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,9,23]],"date-time":"2022-09-23T00:00:00Z","timestamp":1663891200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,9,23]]},"DOI":"10.1145\/3573942.3573968","type":"proceedings-article","created":{"date-parts":[[2023,5,16]],"date-time":"2023-05-16T23:45:42Z","timestamp":1684280742000},"page":"167-172","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["A Method with Universal Transformer for Multimodal Sentiment Analysis"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6893-9098","authenticated-orcid":false,"given":"Hao","family":"Ai","sequence":"first","affiliation":[{"name":"Center for Image and Information Processing, Xi'an University of Posts and Telecommunications, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9037-7818","authenticated-orcid":false,"given":"Ying","family":"Liu","sequence":"additional","affiliation":[{"name":"Center for Image and Information Processing, Xi'an University of Posts and Telecommunications, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8325-3905","authenticated-orcid":false,"given":"Jie","family":"Fang","sequence":"additional","affiliation":[{"name":"Center for Image and Information Processing, Xi'an University of Posts and Telecommunications, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1551-8884","authenticated-orcid":false,"given":"Sheikh Faisal","family":"Rashid","sequence":"additional","affiliation":[{"name":"Al-Khwarizmi Institute of Computer Science (KICS), University of Engineering & Technology (UET), Pakistan"}]}],"member":"320","published-online":{"date-parts":[[2023,5,16]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3186015"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683163"},{"key":"e_1_3_2_1_3_1","first-page":"141","article-title":"Local occlusion facial expression recognition based on improved GAN","volume":"56","author":"Wang Haiyong","year":"2020","unstructured":"Haiyong Wang and Hongzhu Liang. 2020. Local occlusion facial expression recognition based on improved GAN. Computer Engineering and Application 56, 5 (2020), 141-146.","journal-title":"Computer Engineering and Application"},{"key":"e_1_3_2_1_4_1","first-page":"865","article-title":"Robust facial expression recognition based on Generative adversary Network","volume":"44","author":"Yao Naiming","year":"2018","unstructured":"Naiming Yao, Qingpei Guo and Fengchun Qiao. 2018. Robust facial expression recognition based on Generative adversary Network. Acta Automatica Sinica 44, 5 (2018), 865-877.","journal-title":"Acta Automatica Sinica"},{"key":"e_1_3_2_1_5_1","volume-title":"Jakob Uszkoreit and Lukasz Kaiser","author":"Dehghani Mostafa","year":"2018","unstructured":"Mostafa Dehghani, Stephan Gouws, Oriol Vinyals, Jakob Uszkoreit and Lukasz Kaiser. 2018. Universal transformers[J]. arXiv preprint arXiv:1807.03819, 2018."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.3390\/a9020041"},{"key":"e_1_3_2_1_8_1","volume-title":"Erik Cambria and Louis-Philippe Analysis","author":"Zadeh Amir","year":"2017","unstructured":"Amir Zadeh, Minghai Chen, Soujanya Poria, Erik Cambria and Louis-Philippe Analysis. 2017. Tensor fusion network for multimodal sentiment analysis. arXiv preprint arXiv:1707.07250(2017)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1081"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016818"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3049898"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"e_1_3_2_1_13_1","volume-title":"Ming Yang and Kai Yu","author":"Ji Shuiwang","year":"2012","unstructured":"Shuiwang Ji, Wei Xu, Ming Yang and Kai Yu. 2012. 3D convolutional neural networks for human action recognition. IEEE transactions on pattern analysis and machine intelligence 35, 1 (March 2012), 221-231."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853739"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2016.94"},{"key":"e_1_3_2_1_16_1","volume-title":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics. 2236-2246","author":"Zadeh Amir","year":"2018","unstructured":"Amir Zadeh, Paul Pu Liang, Jonathan Vanbriesen, Soujanya Poria, Edmund Tong, Erik Cambria, Minghai Chen, 2018. 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. 2236-2246."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1382"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1081"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2017.134"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3136755.3136801"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12024"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12021"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380000"},{"key":"e_1_3_2_1_24_1","article-title":"Attention-based Multi-modal Sentiment Analysis and Emotion Detection in Conversation using RNN","volume":"6","author":"Huddar Mahesh G.","year":"2021","unstructured":"Mahesh G. Huddar, Sanjeev S. Sannakki and Vijay S. Rajpurohit. 2021. Attention-based Multi-modal Sentiment Analysis and Emotion Detection in Conversation using RNN. International Journal of Interactive Multimedia & Artificial Intelligence 6, 6(December 2021), 112-121.","journal-title":"International Journal of Interactive Multimedia & Artificial Intelligence"}],"event":{"name":"AIPR 2022: 2022 5th International Conference on Artificial Intelligence and Pattern Recognition","location":"Xiamen China","acronym":"AIPR 2022"},"container-title":["Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3573942.3573968","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3573942.3573968","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:49:22Z","timestamp":1750182562000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3573942.3573968"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,23]]},"references-count":24,"alternative-id":["10.1145\/3573942.3573968","10.1145\/3573942"],"URL":"https:\/\/doi.org\/10.1145\/3573942.3573968","relation":{},"subject":[],"published":{"date-parts":[[2022,9,23]]},"assertion":[{"value":"2023-05-16","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}