{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,6]],"date-time":"2026-11-06T01:20:31Z","timestamp":1793928031343,"version":"4.8.0"},"publisher-location":"New York, NY, USA","reference-count":62,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,10,12]],"date-time":"2020-10-12T00:00:00Z","timestamp":1602460800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001459","name":"Ministry of Education - Singapore","doi-asserted-by":"publisher","award":["MOE2018-T2-1-103"],"award-info":[{"award-number":["MOE2018-T2-1-103"]}],"id":[{"id":"10.13039\/501100001459","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001445","name":"DSO National Laboratories - Singapore","doi-asserted-by":"publisher","award":["RTDST190702"],"award-info":[{"award-number":["RTDST190702"]}],"id":[{"id":"10.13039\/501100001445","id-type":"DOI","asserted-by":"publisher"}]},{"name":"RIE 2020 Advanced Manufacturing and Engineering (AME) programmatic grant","award":["A19E2b0098"],"award-info":[{"award-number":["A19E2b0098"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,10,12]]},"DOI":"10.1145\/3394171.3413678","type":"proceedings-article","created":{"date-parts":[[2020,10,12]],"date-time":"2020-10-12T08:27:38Z","timestamp":1602491258000},"page":"1122-1131","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1096,"title":["MISA"],"prefix":"10.1145","author":[{"given":"Devamanyu","family":"Hazarika","sequence":"first","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Roger","family":"Zimmermann","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Soujanya","family":"Poria","sequence":"additional","affiliation":[{"name":"Singapore University of Technology and Design, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2020,10,12]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"Roee Aharoni and Yoav Goldberg. 2020. Unsupervised Domain Clusters in Pretrained Language Models. CoRR Vol. abs\/2004.02105 (2020). arxiv: 2004.02105 https:\/\/arxiv.org\/abs\/2004.02105 Roee Aharoni and Yoav Goldberg. 2020. Unsupervised Domain Clusters in Pretrained Language Models. CoRR Vol. abs\/2004.02105 (2020). arxiv: 2004.02105 https:\/\/arxiv.org\/abs\/2004.02105"},{"key":"e_1_3_2_2_2_1","first-page":"19","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019","volume":"1","author":"Shad Akhtar Md.","year":"2019"},{"key":"e_1_3_2_2_3_1","volume-title":"Proceedings of the 30th International Conference on Machine Learning, ICML 2013 (JMLR Workshop and Conference Proceedings","volume":"1255","author":"Andrew Galen","year":"2013"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2016.7477553"},{"key":"e_1_3_2_2_5_1","volume-title":"Advances in Neural Information Processing Systems 29. Curran Associates","author":"Bousmalis Konstantinos"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"crossref","unstructured":"Dushyant Singh Chauhan Md Shad Akhtar Asif Ekbal and Pushpak Bhattacharyya. 2019. Context-aware Interactive Attention for Multi-modal Sentiment and Emotion Analysis. 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). Association for Computational Linguistics Hong Kong China 5647--5657. https:\/\/doi.org\/10.18653\/v1\/D19-1566 Dushyant Singh Chauhan Md Shad Akhtar Asif Ekbal and Pushpak Bhattacharyya. 2019. Context-aware Interactive Attention for Multi-modal Sentiment and Emotion Analysis. 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). Association for Computational Linguistics Hong Kong China 5647--5657. https:\/\/doi.org\/10.18653\/v1\/D19-1566","DOI":"10.18653\/v1\/D19-1566"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3136755.3136801"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.5555\/2354409.2355082"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853739"},{"key":"e_1_3_2_2_11_1","first-page":"19","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","volume":"1","author":"Devlin Jacob","year":"2019"},{"key":"e_1_3_2_2_12_1","volume-title":"Joint Robust Voicing Detection and Pitch Estimation Based on Residual Harmonics. In INTERSPEECH 2011, 12th Annual Conference of the International Speech Communication Association. ISCA","author":"Drugman Thomas","year":"2011"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2170835"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"crossref","unstructured":"Rosenberg Ekman. 1997. What the face reveals: Basic and applied studies of spontaneous expression using the Facial Action Coding System (FACS). Oxford University Press USA. Rosenberg Ekman. 1997. What the face reveals: Basic and applied studies of spontaneous expression using the Facial Action Coding System (FACS). Oxford University Press USA.","DOI":"10.1093\/oso\/9780195104462.001.0001"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1044"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1382"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240714"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2916887"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"crossref","unstructured":"Md Kamrul Hasan Wasifur Rahman AmirAli Bagher Zadeh Jianyuan Zhong Md Iftekhar Tanveer Louis-Philippe Morency and Mohammed (Ehsan) Hoque. 2019. UR-FUNNY: A Multimodal Language Dataset for Understanding Humor. 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). Association for Computational Linguistics Hong Kong China 2046--2056. https:\/\/doi.org\/10.18653\/v1\/D19-1211 Md Kamrul Hasan Wasifur Rahman AmirAli Bagher Zadeh Jianyuan Zhong Md Iftekhar Tanveer Louis-Philippe Morency and Mohammed (Ehsan) Hoque. 2019. UR-FUNNY: A Multimodal Language Dataset for Understanding Humor. 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). Association for Computational Linguistics Hong Kong China 2046--2056. https:\/\/doi.org\/10.18653\/v1\/D19-1211","DOI":"10.18653\/v1\/D19-1211"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_2_2_21_1","volume-title":"Attribute-Enhanced Face Recognition with Neural Tensor Fusion Networks. In IEEE International Conference on Computer Vision, ICCV 2017","author":"Hu Guosheng","year":"2017"},{"key":"e_1_3_2_2_22_1","volume-title":"NeurIPS 2019 Workshop. Curran Associates, Inc.","author":"Kiela Douwe","year":"2019"},{"key":"e_1_3_2_2_23_1","unstructured":"Liunian Harold Li Mark Yatskar Da Yin Cho-Jui Hsieh and Kai-Wei Chang. 2019. VisualBERT: A Simple and Performant Baseline for Vision and Language. CoRR Vol. abs\/1908.03557 (2019). arxiv: 1908.03557 http:\/\/arxiv.org\/abs\/1908.03557 Liunian Harold Li Mark Yatskar Da Yin Cho-Jui Hsieh and Kai-Wei Chang. 2019. VisualBERT: A Simple and Performant Baseline for Vision and Language. CoRR Vol. abs\/1908.03557 (2019). arxiv: 1908.03557 http:\/\/arxiv.org\/abs\/1908.03557"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1014"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1001"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1209"},{"key":"e_1_3_2_2_27_1","volume-title":"Advances in Neural Information Processing Systems 32. Curran Associates","author":"Lu Jiasen"},{"key":"e_1_3_2_2_28_1","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der Maaten Laurens","year":"2008","journal-title":"Journal of machine learning research"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1046"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5347"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2925966"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2018.07.041"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.5555\/2392963.2392965"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"crossref","unstructured":"David Olson. 1977. From utterance to text: The bias of language in speech and writing. Harvard educational review Vol. 47 3 (1977) 257--281. David Olson. 1977. From utterance to text: The bias of language in speech and writing. Harvard educational review Vol. 47 3 (1977) 257--281.","DOI":"10.17763\/haer.47.3.8840364413869005"},{"key":"e_1_3_2_2_35_1","unstructured":"Gwangbeen Park and Woobin Im. 2016. Image-Text Multi-Modal Representation Learning by Adversarial Backpropagation. CoRR Vol. abs\/1612.08354 (2016). arxiv: 1612.08354 http:\/\/arxiv.org\/abs\/1612.08354 Gwangbeen Park and Woobin Im. 2016. Image-Text Multi-Modal Representation Learning by Adversarial Backpropagation. CoRR Vol. abs\/1612.08354 (2016). arxiv: 1612.08354 http:\/\/arxiv.org\/abs\/1612.08354"},{"key":"e_1_3_2_2_36_1","series-title":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, ACL","volume-title":"Long Papers","author":"Peng Minlong","year":"2018"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3284750"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016892"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-3308"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2017.02.003"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1303"},{"key":"e_1_3_2_2_43_1","volume-title":"Multi-level Multiple Attentions for Contextual Multimodal Sentiment Analysis. In 2017 IEEE International Conference on Data Mining, ICDM 2017","author":"Poria Soujanya","year":"2017"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1081"},{"key":"e_1_3_2_2_45_1","unstructured":"Soujanya Poria Devamanyu Hazarika Navonil Majumder and Rada Mihalcea. 2020. Beneath the Tip of the Iceberg: Current Challenges and New Directions in Sentiment Analysis Research. CoRR Vol. abs\/2005.00357 (2020). arxiv: 2005.00357 https:\/\/arxiv.org\/abs\/2005.00357 Soujanya Poria Devamanyu Hazarika Navonil Majumder and Rada Mihalcea. 2020. Beneath the Tip of the Iceberg: Current Challenges and New Directions in Sentiment Analysis Research. CoRR Vol. abs\/2005.00357 (2020). arxiv: 2005.00357 https:\/\/arxiv.org\/abs\/2005.00357"},{"key":"e_1_3_2_2_46_1","volume-title":"Proceedings, Part VII (Lecture Notes in Computer Science","volume":"353","author":"Rajagopalan Shyam Sundar","year":"2016"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1096"},{"key":"e_1_3_2_2_48_1","volume-title":"Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, AISTATS 2010 (JMLR Proceedings","volume":"708","author":"Salzmann Mathieu","year":"2010"},{"key":"e_1_3_2_2_49_1","unstructured":"Weijie Su Xizhou Zhu Yue Cao Bin Li Lewei Lu Furu Wei and Jifeng Dai. 2019. VL-BERT: Pre-training of Generic Visual-Linguistic Representations. CoRR Vol. abs\/1908.08530 (2019). arxiv: 1908.08530 http:\/\/arxiv.org\/abs\/1908.08530 Weijie Su Xizhou Zhu Yue Cao Bin Li Lewei Lu Furu Wei and Jifeng Dai. 2019. VL-BERT: Pre-training of Generic Visual-Linguistic Representations. CoRR Vol. abs\/1908.08530 (2019). arxiv: 1908.08530 http:\/\/arxiv.org\/abs\/1908.08530"},{"key":"e_1_3_2_2_50_1","unstructured":"Zhongkai Sun Prathusha K. Sarma William A. Sethares and Yingyu Liang. 2019. Learning Relationships between Text Audio and Video via Deep Canonical Correlation for Multimodal Language Analysis. CoRR Vol. abs\/1911.05544 (2019). arxiv: 1911.05544 http:\/\/arxiv.org\/abs\/1911.05544 Zhongkai Sun Prathusha K. Sarma William A. Sethares and Yingyu Liang. 2019. Learning Relationships between Text Audio and Video via Deep Canonical Correlation for Multimodal Language Analysis. CoRR Vol. abs\/1911.05544 (2019). arxiv: 1911.05544 http:\/\/arxiv.org\/abs\/1911.05544"},{"key":"e_1_3_2_2_51_1","volume-title":"Learning Factorized Multimodal Representations. In 7th International Conference on Learning Representations, ICLR","author":"Hubert Tsai Yao-Hung","year":"2019"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.463"},{"key":"e_1_3_2_2_54_1","volume-title":"Advances in Neural Information Processing Systems 30. Curran Associates","author":"Vaswani Ashish"},{"key":"e_1_3_2_2_55_1","unstructured":"Weiran Wang Honglak Lee and Karen Livescu. 2016. Deep Variational Canonical Correlation Analysis. CoRR Vol. abs\/1610.03454 (2016). arxiv: 1610.03454 http:\/\/arxiv.org\/abs\/1610.03454 Weiran Wang Honglak Lee and Karen Livescu. 2016. Deep Variational Canonical Correlation Analysis. CoRR Vol. abs\/1610.03454 (2016). arxiv: 1610.03454 http:\/\/arxiv.org\/abs\/1610.03454"},{"key":"e_1_3_2_2_56_1","volume-title":"Words Can Shift: Dynamically Adjusting Word Representations Using Nonverbal Behaviors. In The Thirty-Third AAAI Conference on Artificial Intelligence. AAAI Press","author":"Wang Yansen","year":"2019"},{"key":"e_1_3_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3380688.3380693"},{"key":"e_1_3_2_2_58_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1115"},{"key":"e_1_3_2_2_59_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12021"},{"key":"e_1_3_2_2_60_1","volume-title":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, ACL 2018","volume":"2246","author":"Zadeh Amir","year":"2018"},{"key":"e_1_3_2_2_61_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12024"},{"key":"e_1_3_2_2_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2016.94"},{"key":"e_1_3_2_2_63_1","volume-title":"Central Moment Discrepancy (CMD) for Domain-Invariant Representation Learning. In 5th International Conference on Learning Representations, ICLR","author":"Zellinger Werner","year":"2017"}],"event":{"name":"MM '20: The 28th ACM International Conference on Multimedia","location":"Seattle WA USA","acronym":"MM '20","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 28th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3394171.3413678","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3394171.3413678","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:47:16Z","timestamp":1750178836000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3394171.3413678"}},"subtitle":["Modality-Invariant and -Specific Representations for Multimodal Sentiment Analysis"],"short-title":[],"issued":{"date-parts":[[2020,10,12]]},"references-count":62,"alternative-id":["10.1145\/3394171.3413678","10.1145\/3394171"],"URL":"https:\/\/doi.org\/10.1145\/3394171.3413678","relation":{},"subject":[],"published":{"date-parts":[[2020,10,12]]},"assertion":[{"value":"2020-10-12","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}