{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T14:49:03Z","timestamp":1743000543143,"version":"3.40.3"},"publisher-location":"Cham","reference-count":23,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031301049"},{"type":"electronic","value":"9783031301056"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-30105-6_36","type":"book-chapter","created":{"date-parts":[[2023,4,12]],"date-time":"2023-04-12T20:31:55Z","timestamp":1681331515000},"page":"431-442","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Synesthesia Transformer with\u00a0Contrastive Multimodal Learning"],"prefix":"10.1007","author":[{"given":"Zhengxiao","family":"Sun","sequence":"first","affiliation":[]},{"given":"Feiyu","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Jie","family":"Shao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,4,13]]},"reference":[{"key":"36_CR1","unstructured":"Fedotov, D.: Contextual time-continuous emotion recognition based on multimodal data, Ph. D. thesis, University of Ulm, Germany (2022)"},{"key":"36_CR2","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.B.: Momentum contrast for unsupervised visual representation learning. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020, pp. 9726\u20139735 (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"36_CR3","doi-asserted-by":"crossref","unstructured":"Heo, S., Lee, W., Lee, J.: mcBERT: momentum contrastive learning with BERT for zero-shot slot filling. CoRR abs\/2203.12940 (2022)","DOI":"10.21437\/Interspeech.2022-839"},{"issue":"6","key":"36_CR4","first-page":"112","volume":"6","author":"MG Huddar","year":"2021","unstructured":"Huddar, M.G., Sannakki, S.S., Rajpurohit, V.S.: Attention-based multi-modal sentiment analysis and emotion detection in conversation using RNN. Int. J. Interact. Multim. Artif. Intell. 6(6), 112\u2013121 (2021)","journal-title":"Int. J. Interact. Multim. Artif. Intell."},{"key":"36_CR5","doi-asserted-by":"crossref","unstructured":"Jang, H., Choi, H., Yi, Y., Shin, J.: Adiabatic persistent contrastive divergence learning. In: 2017 IEEE International Symposium on Information Theory, ISIT 2017, pp. 3005\u20133009 (2017)","DOI":"10.1109\/ISIT.2017.8007081"},{"key":"36_CR6","unstructured":"Jenckel, M.: Sequence learning for ocr in unsupervised training cases, Ph. D. thesis, Kaiserslautern University of Technology, Germany (2022)"},{"key":"36_CR7","unstructured":"Ji, X.: Unsupervised learning and continual learning in neural networks, Ph. D. thesis, University of Oxford, UK (2021)"},{"key":"36_CR8","doi-asserted-by":"crossref","unstructured":"Kann, K., Monsalve-Mercado, M.M.: Coloring the black box: what synesthesia tells us about character embeddings. In: Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, EACL 2021, pp. 2673\u20132685 (2021)","DOI":"10.18653\/v1\/2021.eacl-main.230"},{"key":"36_CR9","doi-asserted-by":"crossref","unstructured":"Liu, Z., Shen, Y., Lakshminarasimhan, V.B., Liang, P.P., Zadeh, A., Morency, L.: Efficient low-rank multimodal fusion with modality-specific factors. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, ACL 2018, Volume 1: Long Papers, pp. 2247\u20132256 (2018)","DOI":"10.18653\/v1\/P18-1209"},{"key":"36_CR10","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3172360","author":"S Mai","year":"2022","unstructured":"Mai, S., Zeng, Y., Zheng, S., Hu, H.: Hybrid contrastive learning of tri-modal representation for multimodal sentiment analysis. IEEE Trans. Affect. Comput. (2022). https:\/\/doi.org\/10.1109\/TAFFC.2022.3172360","journal-title":"IEEE Trans. Affect. Comput."},{"key":"36_CR11","first-page":"69","volume":"67","author":"DM Melanchthon","year":"2021","unstructured":"Melanchthon, D.M.: Unimodal feature-level improvement on multimodal CMU-MOSEI dataset: uncorrelated and convolved feature sets. Proces. del Leng. Natural 67, 69\u201381 (2021)","journal-title":"Proces. del Leng. Natural"},{"key":"36_CR12","doi-asserted-by":"crossref","unstructured":"Pham, H., Liang, P.P., Manzini, T., Morency, L., P\u00f3czos, B.: Found in translation: learning robust joint representations by cyclic translations between modalities. In: The Thirty-Third AAAI Conference on Artificial Intelligence, AAAI 2019, pp. 6892\u20136899 (2019)","DOI":"10.1609\/aaai.v33i01.33016892"},{"key":"36_CR13","doi-asserted-by":"publisher","first-page":"28750","DOI":"10.1109\/ACCESS.2022.3157712","volume":"10","author":"Q Qi","year":"2022","unstructured":"Qi, Q., Lin, L., Zhang, R., Xue, C.: MEDT: using multimodal encoding-decoding network as in transformer for multimodal sentiment analysis. IEEE Access 10, 28750\u201328759 (2022)","journal-title":"IEEE Access"},{"key":"36_CR14","doi-asserted-by":"crossref","unstructured":"Stappen, L., et al.: The muse 2021 multimodal sentiment analysis challenge: Sentiment, emotion, physiological-emotion, and stress. In: MuSe 2021: Proceedings of the 2nd on Multimodal Sentiment Analysis Challenge, pp. 5\u201314 (2021)","DOI":"10.1145\/3475957.3484450"},{"key":"36_CR15","doi-asserted-by":"crossref","unstructured":"Tsai, Y.H., Bai, S., Liang, P.P., Kolter, J.Z., Morency, L., Salakhutdinov, R.: Multimodal transformer for unaligned multimodal language sequences. In: Proceedings of the 57th Conference of the Association for Computational Linguistics, ACL 2019, Volume 1: Long Papers, pp. 6558\u20136569 (2019)","DOI":"10.18653\/v1\/P19-1656"},{"key":"36_CR16","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, pp. 5998\u20136008 (2017)"},{"key":"36_CR17","doi-asserted-by":"crossref","unstructured":"Wang, Y., Shen, Y., Liu, Z., Liang, P.P., Zadeh, A., Morency, L.: Words can shift: dynamically adjusting word representations using nonverbal behaviors. In: The Thirty-Third AAAI Conference on Artificial Intelligence, AAAI 2019, pp. 7216\u20137223 (2019)","DOI":"10.1609\/aaai.v33i01.33017216"},{"key":"36_CR18","doi-asserted-by":"publisher","first-page":"130","DOI":"10.1016\/j.neucom.2021.09.041","volume":"467","author":"B Yang","year":"2022","unstructured":"Yang, B., Shao, B., Wu, L., Lin, X.: Multimodal sentiment analysis with unidirectional modality translation. Neurocomputing 467, 130\u2013137 (2022)","journal-title":"Neurocomputing"},{"key":"36_CR19","doi-asserted-by":"crossref","unstructured":"Yang, N., Wei, F., Jiao, B., Jiang, D., Yang, L.: xMoCo: cross momentum contrastive learning for open-domain question answering. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL\/IJCNLP 2021, (Volume 1: Long Papers), pp. 6120\u20136129 (2021)","DOI":"10.18653\/v1\/2021.acl-long.477"},{"key":"36_CR20","doi-asserted-by":"crossref","unstructured":"Zadeh, A., Chen, M., Poria, S., Cambria, E., Morency, L.: Tensor fusion network for multimodal sentiment analysis. In: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, EMNLP 2017, pp. 1103\u20131114 (2017)","DOI":"10.18653\/v1\/D17-1115"},{"key":"36_CR21","doi-asserted-by":"crossref","unstructured":"Zadeh, A., Liang, P.P., Mazumder, N., Poria, S., Cambria, E., Morency, L.: Memory fusion network for multi-view sequential learning. In: Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, (AAAI-18), pp. 5634\u20135641 (2018)","DOI":"10.1609\/aaai.v32i1.12021"},{"key":"36_CR22","unstructured":"Zadeh, A., Zellers, R., Pincus, E., Morency, L.: MOSI: multimodal corpus of sentiment intensity and subjectivity analysis in online opinion videos. CoRR abs\/1606.06259 (2016)"},{"key":"36_CR23","unstructured":"Zheng, J., Zhang, S., Wang, X., Zeng, Z.: Multimodal representations learning based on mutual information maximization and minimization and identity embedding for multimodal sentiment analysis. CoRR abs\/2201.03969 (2022)"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-30105-6_36","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,12]],"date-time":"2023-04-12T20:36:58Z","timestamp":1681331818000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-30105-6_36"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031301049","9783031301056"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-30105-6_36","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"13 April 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New Delhi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 November 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 November 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iconip2022.apnns.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Easy Chair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"810","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"359","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"44% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2.65","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"ICONIP 2022 consists of a two-volume set, LNCS & CCIS, which includes 146 and 213 papers","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}