{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T08:05:00Z","timestamp":1761897900716,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":39,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819944019"},{"type":"electronic","value":"9789819944026"}],"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\/978-981-99-4402-6_13","type":"book-chapter","created":{"date-parts":[[2023,7,26]],"date-time":"2023-07-26T23:02:45Z","timestamp":1690412565000},"page":"179-193","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Multimodal Intent Recognition Based on\u00a0Contrastive Learning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-5146-9923","authenticated-orcid":false,"given":"Yuxuan","family":"Wu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6913-0514","authenticated-orcid":false,"given":"Zhizhong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5289-3337","authenticated-orcid":false,"given":"Zhaohui","family":"Su","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5536-1979","authenticated-orcid":false,"given":"Xiaoyu","family":"Song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,7,27]]},"reference":[{"issue":"1","key":"13_CR1","doi-asserted-by":"publisher","first-page":"29","DOI":"10.19030\/jss.v7i1.8911","volume":"7","author":"F Guennemann","year":"2014","unstructured":"Guennemann, F., Cho, Y.C., et al.: The effectiveness of product placement by media types: impact of image and intention to purchase. J. Serv. Sci. (JSS) 7(1), 29\u201342 (2014)","journal-title":"J. Serv. Sci. (JSS)"},{"key":"13_CR2","unstructured":"Akbari, M., Mohades, A., Shirali-Shahreza, M.H.: A hybrid architecture for out of domain intent detection and intent discovery. arXiv preprint arXiv:2303.04134 (2023)"},{"key":"13_CR3","doi-asserted-by":"crossref","unstructured":"Zhang, Q., Wang, S., Li, J.: A heterogeneous interaction graph network for multi-intent spoken language understanding. Neural Process. Lett. 1\u201319 (2023)","DOI":"10.1007\/s11063-023-11210-7"},{"key":"13_CR4","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1016\/j.inffus.2022.09.029","volume":"91","author":"M Firdaus","year":"2023","unstructured":"Firdaus, M., Ekbal, A., Cambria, E.: Multitask learning for multilingual intent detection and slot filling in dialogue systems. Inf. Fusion 91, 299\u2013315 (2023)","journal-title":"Inf. Fusion"},{"key":"13_CR5","doi-asserted-by":"publisher","first-page":"826","DOI":"10.1109\/TASLP.2023.3237156","volume":"31","author":"J Mei","year":"2023","unstructured":"Mei, J., Wang, Y., Tu, X., Dong, M., He, T.: Incorporating BERT with probability-aware gate for spoken language understanding. IEEE\/ACM Trans. Audio Speech Lang. Process. 31, 826\u2013834 (2023)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"13_CR6","doi-asserted-by":"crossref","unstructured":"Rafiepour, M., Sartakhti, J.S.: CTRAN: CNN-transformer-based network for natural language understanding. arXiv preprint arXiv:2303.10606 (2023)","DOI":"10.1016\/j.engappai.2023.107013"},{"key":"13_CR7","unstructured":"Huang, Y., Du, C., Xue, Z., Chen, X., Zhao, H., Huang, L.: What makes multi-modal learning better than single (provably). In: Advances in Neural Information Processing Systems, vol. 34, pp. 10944\u201310956 (2021)"},{"key":"13_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"749","DOI":"10.1007\/978-3-031-17120-8_58","volume-title":"Natural Language Processing and Chinese Computing","author":"S Yuan","year":"2022","unstructured":"Yuan, S., et al.: MCIC: multimodal conversational intent classification for E-commerce customer service. In: Lu, W., Huang, S., Hong, Y., Zhou, X. (eds.) NLPCC 2022 Part I. LNCS, vol. 13551, pp. 749\u2013761. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-17120-8_58"},{"key":"13_CR9","unstructured":"Chen, Y.Y., Hsieh, S.K.: An analysis of multimodal document intent in Instagram posts. In: Proceedings of the 32nd Conference on Computational Linguistics and Speech Processing (ROCLING 2020), pp. 193\u2013207 (2020)"},{"key":"13_CR10","doi-asserted-by":"crossref","unstructured":"Kruk, J., Lubin, J., Sikka, K., Lin, X., Jurafsky, D., Divakaran, A.: Integrating text and image: determining multimodal document intent in Instagram posts. arXiv preprint arXiv:1904.09073 (2019)","DOI":"10.18653\/v1\/D19-1469"},{"key":"13_CR11","doi-asserted-by":"crossref","unstructured":"Ignat, O., Castro, S., Miao, H., Li, W., Mihalcea, R.: WhyAct: identifying action reasons in lifestyle vlogs. arXiv preprint arXiv:2109.02747 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.392"},{"key":"13_CR12","doi-asserted-by":"crossref","unstructured":"Huang, X., Kovashka, A.: Inferring visual persuasion via body language, setting, and deep features. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 73\u201379 (2016)","DOI":"10.1109\/CVPRW.2016.102"},{"issue":"11","key":"13_CR13","doi-asserted-by":"publisher","first-page":"4773","DOI":"10.1109\/TITS.2019.2946642","volume":"21","author":"Z Fang","year":"2019","unstructured":"Fang, Z., L\u00f3pez, A.M.: Intention recognition of pedestrians and cyclists by 2D pose estimation. IEEE Trans. Intell. Transp. Syst. 21(11), 4773\u20134783 (2019)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"13_CR14","doi-asserted-by":"crossref","unstructured":"Hussain, Z., et al.: Automatic understanding of image and video advertisements. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1705\u20131715 (2017)","DOI":"10.1109\/CVPR.2017.123"},{"key":"13_CR15","doi-asserted-by":"publisher","first-page":"1830","DOI":"10.1109\/TMM.2021.3073267","volume":"24","author":"L Zhang","year":"2021","unstructured":"Zhang, L., et al.: Multimodal marketing intent analysis for effective targeted advertising. IEEE Trans. Multimedia 24, 1830\u20131843 (2021)","journal-title":"IEEE Trans. Multimedia"},{"key":"13_CR16","doi-asserted-by":"publisher","first-page":"290","DOI":"10.1109\/TASLP.2022.3224287","volume":"31","author":"GV Singh","year":"2022","unstructured":"Singh, G.V., Firdaus, M., Ekbal, A., Bhattacharyya, P.: EmoInt-trans: a multimodal transformer for identifying emotions and intents in social conversations. IEEE\/ACM Trans. Audio Speech Lang. Process. 31, 290\u2013300 (2022)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"13_CR17","doi-asserted-by":"crossref","unstructured":"Ma, Z., Li, J., Li, G., Cheng, Y.: UniTranSeR: a unified transformer semantic representation framework for multimodal task-oriented dialog system. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics, vol. 1 (Long Papers), pp. 103\u2013114 (2022)","DOI":"10.18653\/v1\/2022.acl-long.9"},{"key":"13_CR18","doi-asserted-by":"crossref","unstructured":"Qin, L., Xie, T., Che, W., Liu, T.: A survey on spoken language understanding: recent advances and new frontiers. arXiv preprint arXiv:2103.03095 (2021)","DOI":"10.24963\/ijcai.2021\/622"},{"key":"13_CR19","doi-asserted-by":"crossref","unstructured":"Qin, L., Xu, X., Che, W., Liu, T.: AGIF: an adaptive graph-interactive framework for joint multiple intent detection and slot filling. arXiv preprint arXiv:2004.10087 (2020)","DOI":"10.18653\/v1\/2020.findings-emnlp.163"},{"key":"13_CR20","doi-asserted-by":"crossref","unstructured":"Jia, M., Wu, Z., Reiter, A., Cardie, C., Belongie, S., Lim, S.N.: Intentonomy: a dataset and study towards human intent understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12986\u201312996 (2021)","DOI":"10.1109\/CVPR46437.2021.01279"},{"key":"13_CR21","doi-asserted-by":"crossref","unstructured":"Joo, J., Li, W., Steen, F.F., Zhu, S.C.: Visual persuasion: inferring communicative intents of images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 216\u2013223 (2014)","DOI":"10.1109\/CVPR.2014.35"},{"key":"13_CR22","doi-asserted-by":"crossref","unstructured":"Zhang, H., Xu, H., Wang, X., Zhou, Q., Zhao, S., Teng, J.: MIntRec: a new dataset for multimodal intent recognition. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 1688\u20131697 (2022)","DOI":"10.1145\/3503161.3547906"},{"key":"13_CR23","doi-asserted-by":"crossref","unstructured":"Maharana, A., et al.: Multimodal intent discovery from livestream videos. In: Findings of the Association for Computational Linguistics: NAACL 2022, pp. 476\u2013489 (2022)","DOI":"10.18653\/v1\/2022.findings-naacl.36"},{"key":"13_CR24","doi-asserted-by":"crossref","unstructured":"Liu, H., Wang, W., Li, H.: Towards multi-modal sarcasm detection via hierarchical congruity modeling with knowledge enhancement. arXiv preprint arXiv:2210.03501 (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.333"},{"key":"13_CR25","doi-asserted-by":"crossref","unstructured":"Han, X.Q., Xu, S.S., Feng, Z., He, R.Q., Lu, Z.Y.: A simple framework for contrastive learning phases of matter. arXiv preprint arXiv:2205.05607 (2022)","DOI":"10.1088\/0256-307X\/40\/2\/027501"},{"key":"13_CR26","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"},{"key":"13_CR27","unstructured":"Gunel, B., Du, J., Conneau, A., Stoyanov, V.: Supervised contrastive learning for pre-trained language model fine-tuning. arXiv preprint arXiv:2011.01403 (2020)"},{"key":"13_CR28","doi-asserted-by":"crossref","unstructured":"Sun, S., Gan, Z., Cheng, Y., Fang, Y., Wang, S., Liu, J.: Contrastive distillation on intermediate representations for language model compression. arXiv preprint arXiv:2009.14167 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.36"},{"key":"13_CR29","doi-asserted-by":"crossref","unstructured":"Li, Z., Xu, B., Zhu, C., Zhao, T.: CLMLF: a contrastive learning and multi-layer fusion method for multimodal sentiment detection. arXiv preprint arXiv:2204.05515 (2022)","DOI":"10.18653\/v1\/2022.findings-naacl.175"},{"key":"13_CR30","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"13_CR31","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"13_CR32","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"13_CR33","unstructured":"Baevski, A., Zhou, Y., Mohamed, A., Auli, M.: wav2vec 2.0: a framework for self-supervised learning of speech representations. In: Advances in Neural Information Processing Systems, vol. 33, pp. 12449\u201312460 (2020)"},{"key":"13_CR34","doi-asserted-by":"crossref","unstructured":"Mai, S., Zeng, Y., Hu, H.: Multimodal information bottleneck: learning minimal sufficient unimodal and multimodal representations. IEEE Trans. Multimedia (2022)","DOI":"10.1109\/TMM.2022.3171679"},{"key":"13_CR35","unstructured":"Xie, Q., Dai, Z., Hovy, E., Luong, T., Le, Q.: Unsupervised data augmentation for consistency training. In: Advances in Neural Information Processing Systems, vol. 33, pp. 6256\u20136268 (2020)"},{"key":"13_CR36","doi-asserted-by":"crossref","unstructured":"Wang, P., Wang, J.: Data augmentation method in image retrieval of digital equipment. In: 5th International Conference on Computer Information Science and Application Technology (CISAT 2022), vol. 12451, pp. 312\u2013316. SPIE (2022)","DOI":"10.1117\/12.2656757"},{"key":"13_CR37","doi-asserted-by":"crossref","unstructured":"Tsai, Y.H.H., Bai, S., Liang, P.P., Kolter, J.Z., Morency, L.P., Salakhutdinov, R.: Multimodal transformer for unaligned multimodal language sequences. In: Proceedings of the Conference. Association for Computational Linguistics. Meeting, vol. 2019, p. 6558. NIH Public Access (2019)","DOI":"10.18653\/v1\/P19-1656"},{"key":"13_CR38","doi-asserted-by":"crossref","unstructured":"Rahman, W., et al.: Integrating multimodal information in large pretrained transformers. In: Proceedings of the Conference. Association for Computational Linguistics. Meeting, vol. 2020, p. 2359. NIH Public Access (2020)","DOI":"10.18653\/v1\/2020.acl-main.214"},{"key":"13_CR39","doi-asserted-by":"crossref","unstructured":"Hazarika, D., Zimmermann, R., Poria, S.: MISA: modality-invariant and-specific representations for multimodal sentiment analysis. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 1122\u20131131 (2020)","DOI":"10.1145\/3394171.3413678"}],"container-title":["Communications in Computer and Information Science","Service Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-4402-6_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,17]],"date-time":"2023-12-17T22:08:27Z","timestamp":1702850907000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-4402-6_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9789819944019","9789819944026"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-4402-6_13","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"27 July 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICSS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Service Science","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Harbin","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":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 May 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 May 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icss22023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conf.ccf.org.cn\/ICSS2023","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":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"71","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":"36","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":"2","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":"51% - 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","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}