{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T08:43:56Z","timestamp":1743151436814,"version":"3.40.3"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031189067"},{"type":"electronic","value":"9783031189074"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-18907-4_33","type":"book-chapter","created":{"date-parts":[[2022,10,26]],"date-time":"2022-10-26T23:03:53Z","timestamp":1666825433000},"page":"423-435","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Momentum Distillation Improves Multimodal Sentiment Analysis"],"prefix":"10.1007","author":[{"given":"Siqi","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weihong","family":"Deng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiani","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,10,27]]},"reference":[{"key":"33_CR1","unstructured":"Ba, J.L., Kiros, J.R., Hinton, G.E.: Layer normalization. arXiv preprint arXiv:1607.06450 (2016)"},{"key":"33_CR2","doi-asserted-by":"crossref","unstructured":"Cai, Y., Cai, H., Wan, X.: Multi-modal sarcasm detection in twitter with hierarchical fusion model. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 2506\u20132515 (2019)","DOI":"10.18653\/v1\/P19-1239"},{"key":"33_CR3","doi-asserted-by":"crossref","unstructured":"Castro, S., Hazarika, D., P\u00e9rez-Rosas, V., Zimmermann, R., Mihalcea, R., Poria, S.: Towards multimodal sarcasm detection (an _obviously_ perfect paper). arXiv preprint arXiv:1906.01815 (2019)","DOI":"10.18653\/v1\/P19-1455"},{"key":"33_CR4","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"33_CR5","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9729\u20139738 (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"issue":"3","key":"33_CR6","first-page":"164","volume":"2","author":"V Jagtap","year":"2013","unstructured":"Jagtap, V., Pawar, K.: Analysis of different approaches to sentence-level sentiment classification. Int. J. Sci. Eng. Technol. 2(3), 164\u2013170 (2013)","journal-title":"Int. J. Sci. Eng. Technol."},{"key":"33_CR7","doi-asserted-by":"publisher","first-page":"785","DOI":"10.1007\/978-3-030-47436-2_59","volume":"12085","author":"T Jiang","year":"2020","unstructured":"Jiang, T., Wang, J., Liu, Z., Ling, Y.: Fusion-extraction network for multimodal sentiment analysis. Adv. Knowl. Discov. Data Min. 12085, 785 (2020)","journal-title":"Adv. Knowl. Discov. Data Min."},{"issue":"5","key":"33_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3124420","volume":"50","author":"A Joshi","year":"2017","unstructured":"Joshi, A., Bhattacharyya, P., Carman, M.J.: Automatic sarcasm detection: a survey. ACM Comput. Surv. (CSUR) 50(5), 1\u201322 (2017)","journal-title":"ACM Comput. Surv. (CSUR)"},{"issue":"2","key":"33_CR9","first-page":"38","volume":"10","author":"R Kaur","year":"2019","unstructured":"Kaur, R., Kautish, S.: Multimodal sentiment analysis: a survey and comparison. Int. J. Serv. Sci. Manag. Eng. Technol. (IJSSMET) 10(2), 38\u201358 (2019)","journal-title":"Int. J. Serv. Sci. Manag. Eng. Technol. (IJSSMET)"},{"key":"33_CR10","unstructured":"Li, J., Selvaraju, R.R., Gotmare, A.D., Joty, S., Xiong, C., Hoi, S.: Align before fuse: vision and language representation learning with momentum distillation. arXiv preprint arXiv:2107.07651 (2021)"},{"key":"33_CR11","doi-asserted-by":"crossref","unstructured":"Li, X., Bing, L., Lam, W., Shi, B.: Transformation networks for target-oriented sentiment classification. arXiv preprint arXiv:1805.01086 (2018)","DOI":"10.18653\/v1\/P18-1087"},{"key":"33_CR12","unstructured":"Liu, Y., et al.: Roberta: a robustly optimized Bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)"},{"key":"33_CR13","doi-asserted-by":"crossref","unstructured":"Lu, D., Neves, L., Carvalho, V., Zhang, N., Ji, H.: Visual attention model for name tagging in multimodal social media. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 1990\u20131999 (2018)","DOI":"10.18653\/v1\/P18-1185"},{"key":"33_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1007\/978-3-319-27674-8_2","volume-title":"MultiMedia Modeling","author":"T Niu","year":"2016","unstructured":"Niu, T., Zhu, S., Pang, L., El Saddik, A.: Sentiment analysis on multi-view social data. In: Tian, Q., Sebe, N., Qi, G.-J., Huet, B., Hong, R., Liu, X. (eds.) MMM 2016. LNCS, vol. 9517, pp. 15\u201327. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-27674-8_2"},{"key":"33_CR15","doi-asserted-by":"crossref","unstructured":"Pan, H., Lin, Z., Fu, P., Qi, Y., Wang, W.: Modeling intra and inter-modality incongruity for multi-modal sarcasm detection. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: Findings, pp. 1383\u20131392 (2020)","DOI":"10.18653\/v1\/2020.findings-emnlp.124"},{"key":"33_CR16","first-page":"8026","volume":"32","author":"A Paszke","year":"2019","unstructured":"Paszke, A., et al.: Pytorch: an imperative style, high-performance deep learning library. Adv. Neural. Inf. Process. Syst. 32, 8026\u20138037 (2019)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"33_CR17","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., J\u00e9gou, H.: Training data-efficient image transformers & distillation through attention. In: International Conference on Machine Learning, pp. 10347\u201310357. PMLR (2021)"},{"key":"33_CR18","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"33_CR19","doi-asserted-by":"crossref","unstructured":"Wang, X., Sun, X., Yang, T., Wang, H.: Building a bridge: a method for image-text sarcasm detection without pretraining on image-text data. In: Proceedings of the First International Workshop on Natural Language Processing Beyond Text, pp. 19\u201329 (2020)","DOI":"10.18653\/v1\/2020.nlpbt-1.3"},{"issue":"2","key":"33_CR20","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1109\/MMUL.2021.3069097","volume":"28","author":"Y Wu","year":"2021","unstructured":"Wu, Y., et al.: Modeling incongruity between modalities for multimodal sarcasm detection. IEEE Multimedia 28(2), 86\u201395 (2021)","journal-title":"IEEE Multimedia"},{"key":"33_CR21","doi-asserted-by":"crossref","unstructured":"Xu, N.: Analyzing multimodal public sentiment based on hierarchical semantic attentional network. In: 2017 IEEE International Conference on Intelligence and Security Informatics (ISI), pp. 152\u2013154. IEEE (2017)","DOI":"10.1109\/ISI.2017.8004895"},{"key":"33_CR22","doi-asserted-by":"crossref","unstructured":"Xu, N., Mao, W.: Multisentinet: a deep semantic network for multimodal sentiment analysis. In: Proceedings of the 2017 ACM on Conference on Information and Knowledge Management, pp. 2399\u20132402 (2017)","DOI":"10.1145\/3132847.3133142"},{"key":"33_CR23","doi-asserted-by":"crossref","unstructured":"Xu, N., Mao, W., Chen, G.: A co-memory network for multimodal sentiment analysis. In: The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval, pp. 929\u2013932 (2018)","DOI":"10.1145\/3209978.3210093"},{"key":"33_CR24","doi-asserted-by":"crossref","unstructured":"Xu, N., Zeng, Z., Mao, W.: Reasoning with multimodal sarcastic tweets via modeling cross-modality contrast and semantic association. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 3777\u20133786 (2020)","DOI":"10.18653\/v1\/2020.acl-main.349"},{"key":"33_CR25","doi-asserted-by":"publisher","first-page":"4014","DOI":"10.1109\/TMM.2020.3035277","volume":"23","author":"X Yang","year":"2020","unstructured":"Yang, X., Feng, S., Wang, D., Zhang, Y.: Image-text multimodal emotion classification via multi-view attentional network. IEEE Trans. Multimedia 23, 4014\u20134026 (2020)","journal-title":"IEEE Trans. Multimedia"},{"key":"33_CR26","doi-asserted-by":"crossref","unstructured":"Yang, X., Feng, S., Zhang, Y., Wang, D.: Multimodal sentiment detection based on multi-channel graph neural networks. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pp. 328\u2013339 (2021)","DOI":"10.18653\/v1\/2021.acl-long.28"},{"key":"33_CR27","doi-asserted-by":"crossref","unstructured":"Yao, F., Sun, X., Yu, H., Zhang, W., Liang, W., Fu, K.: Mimicking the brain\u2019s cognition of sarcasm from multidisciplines for twitter sarcasm detection. IEEE Trans. Neural Networks Learn. Syst. (2021)","DOI":"10.1109\/TNNLS.2021.3093416"},{"key":"33_CR28","doi-asserted-by":"crossref","unstructured":"Yu, J., Jiang, J.: Adapting Bert for target-oriented multimodal sentiment classification. In: IJCAI (2019)","DOI":"10.24963\/ijcai.2019\/751"},{"key":"33_CR29","doi-asserted-by":"publisher","first-page":"429","DOI":"10.1109\/TASLP.2019.2957872","volume":"28","author":"J Yu","year":"2019","unstructured":"Yu, J., Jiang, J., Xia, R.: Entity-sensitive attention and fusion network for entity-level multimodal sentiment classification. IEEE\/ACM Trans. Audio Speech Lang. Process. 28, 429\u2013439 (2019)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"33_CR30","doi-asserted-by":"crossref","unstructured":"Yu, W., et al.: Ch-sims: a Chinese multimodal sentiment analysis dataset with fine-grained annotation of modality. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 3718\u20133727 (2020)","DOI":"10.18653\/v1\/2020.acl-main.343"},{"key":"33_CR31","doi-asserted-by":"crossref","unstructured":"Zadeh, A., Chen, M., Poria, S., Cambria, E., Morency, L.P.: Tensor fusion network for multimodal sentiment analysis. arXiv preprint arXiv:1707.07250 (2017)","DOI":"10.18653\/v1\/D17-1115"},{"issue":"4","key":"33_CR32","doi-asserted-by":"publisher","DOI":"10.1002\/widm.1253","volume":"8","author":"L Zhang","year":"2018","unstructured":"Zhang, L., Wang, S., Liu, B.: Deep learning for sentiment analysis: a survey. Wiley Interdisc. Rev. Data Min. Knowl. Discov. 8(4), e1253 (2018)","journal-title":"Wiley Interdisc. Rev. Data Min. Knowl. Discov."},{"key":"33_CR33","doi-asserted-by":"crossref","unstructured":"Zhang, Q., Fu, J., Liu, X., Huang, X.: Adaptive co-attention network for named entity recognition in tweets. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.11962"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-18907-4_33","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,10]],"date-time":"2023-03-10T04:13:08Z","timestamp":1678421588000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-18907-4_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031189067","9783031189074"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-18907-4_33","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"27 October 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shenzhen","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"14 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/en.prcv.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"microsoft","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"564","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":"233","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":"41% - 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":"3.03","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":"3.35","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}