{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,20]],"date-time":"2025-06-20T04:08:22Z","timestamp":1750392502841,"version":"3.41.0"},"publisher-location":"Singapore","reference-count":31,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819681792","type":"print"},{"value":"9789819681808","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-981-96-8180-8_13","type":"book-chapter","created":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T13:16:32Z","timestamp":1750338992000},"page":"155-166","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multimodal Contrastive Learning for\u00a0Dialogue Embeddings with\u00a0Global and\u00a0Local Views"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-6932-8441","authenticated-orcid":false,"given":"Subeen","family":"Choe","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7682-8735","authenticated-orcid":false,"given":"Jihyeon","family":"Oh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0300-7705","authenticated-orcid":false,"given":"Jihoon","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,6,20]]},"reference":[{"key":"13_CR1","unstructured":"Arthur, D., Vassilvitskii, S.: k-means++: the advantages of careful seeding. In: Proceedings of the 18th ACM-SIAM Symposium on Discrete Algorithms, SODA 2007, pp. 1027\u20131035 (2007)"},{"key":"13_CR2","doi-asserted-by":"publisher","unstructured":"Bao, S., He, H., Wang, F., Wu, H., Wang, H.: PLATO: pre-trained dialogue generation model with discrete latent variable. In: Proceedings of the 58st Annual Meeting of ACL, pp. 85\u201396 (2020). https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.9","DOI":"10.18653\/v1\/2020.acl-main.9"},{"key":"13_CR3","doi-asserted-by":"crossref","unstructured":"Caron, M., et\u00a0al.: Emerging properties in self-supervised vision transformers. In: Proceedings of the ICCV, pp. 9650\u20139660 (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"13_CR4","unstructured":"Caron, M., Misra, I., Mairal, J., Goyal, P., Bojanowski, P., Joulin, A.: Unsupervised learning of visual features by contrasting cluster assignments. In: Advances in NeurIPS, vol.\u00a033, pp. 9912\u20139924 (2020)"},{"key":"13_CR5","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: Proceedings of the 37th ICML, vol.\u00a0119, pp. 1597\u20131607 (2020)"},{"key":"13_CR6","doi-asserted-by":"publisher","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the NAACL-HLT, Volume 1 (Long and Short Papers), pp. 4171\u20134186 (2019). https:\/\/doi.org\/10.18653\/v1\/N19-1423","DOI":"10.18653\/v1\/N19-1423"},{"key":"13_CR7","doi-asserted-by":"publisher","unstructured":"Feng, J., et\u00a0al.: MMDialog: a large-scale multi-turn dialogue dataset towards multi-modal open-domain conversation. In: Proceedings of the 61st Annual Meeting of ACL (Vol. 1: Long Papers), pp. 7348\u20137363 (2023). https:\/\/doi.org\/10.18653\/v1\/2023.acl-long.405","DOI":"10.18653\/v1\/2023.acl-long.405"},{"key":"13_CR8","doi-asserted-by":"publisher","unstructured":"Gao, T., Yao, X., Chen, D.: SimCSE: simple contrastive learning of sentence embeddings. In: Proceedings of EMNLP, pp. 6894\u20136910 (2021). https:\/\/doi.org\/10.18653\/v1\/2021.emnlp-main.552","DOI":"10.18653\/v1\/2021.emnlp-main.552"},{"key":"13_CR9","doi-asserted-by":"publisher","unstructured":"Giorgi, J., Nitski, O., Wang, B., Bader, G.: DeCLUTR: deep contrastive learning for unsupervised textual representations. In: Proceedings of the 59th Annual Meeting of ACL and the 11th IJCNLP (Vol. 1: Long Papers), pp. 879\u2013895 (2021). https:\/\/doi.org\/10.18653\/v1\/2021.acl-long.72","DOI":"10.18653\/v1\/2021.acl-long.72"},{"key":"13_CR10","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 CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"13_CR11","unstructured":"Jia, C., et\u00a0al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: Proceedings of the 38th ICML, vol.\u00a0139, pp. 4904\u20134916 (2021)"},{"key":"13_CR12","doi-asserted-by":"publisher","unstructured":"Klein, T., Nabi, M.: SCD: self-contrastive decorrelation of sentence embeddings. In: Proceedings of the 60st Annual Meeting of ACL (Vol. 2: Short Papers), pp. 394\u2013400 (2022). https:\/\/doi.org\/10.18653\/v1\/2022.acl-short.44","DOI":"10.18653\/v1\/2022.acl-short.44"},{"key":"13_CR13","unstructured":"Li, J., et\u00a0al.: Align before fuse: vision and language representation learning with momentum distillation. In: Advances in NeurIPS, vol.\u00a034, pp. 9694\u20139705 (2021)"},{"key":"13_CR14","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: Proceedings of the 39th ICML, vol.\u00a0162, pp. 12888\u201312900 (2022)"},{"key":"13_CR15","doi-asserted-by":"publisher","unstructured":"Li, Y., et\u00a0al.: PaCE: unified multi-modal dialogue pre-training with progressive and compositional experts. In: Proceedings of the 61st Annual Meeting of ACL (Vol. 1: Long Papers), pp. 13402\u201313416 (2023). https:\/\/doi.org\/10.18653\/v1\/2023.acl-long.749","DOI":"10.18653\/v1\/2023.acl-long.749"},{"key":"13_CR16","doi-asserted-by":"publisher","unstructured":"Liu, C., et\u00a0al.: DialogueCSE: dialogue-based contrastive learning of sentence embeddings. In: Proceedings of EMNLP, pp. 2396\u20132406 (2021). https:\/\/doi.org\/10.18653\/v1\/2021.emnlp-main.185","DOI":"10.18653\/v1\/2021.emnlp-main.185"},{"key":"13_CR17","doi-asserted-by":"publisher","unstructured":"Liu, C., Wang, R., Jiang, J., Li, Y., Huang, F.: Dial2vec: self-guided contrastive learning of unsupervised dialogue embeddings. In: Proceedings of EMNLP, pp. 7272\u20137282 (2022). https:\/\/doi.org\/10.18653\/v1\/2022.emnlp-main.490","DOI":"10.18653\/v1\/2022.emnlp-main.490"},{"key":"13_CR18","unstructured":"Liu, Y., et\u00a0al.: Roberta: a robustly optimized bert pretraining approach, arXiv:1907.11692 (2019)"},{"key":"13_CR19","doi-asserted-by":"crossref","unstructured":"Luo, Y., et\u00a0al.: Fairclip: harnessing fairness in vision-language learning. In: Proceedings of the CVPR, pp. 12289\u201312301 (2024)","DOI":"10.1109\/CVPR52733.2024.01168"},{"key":"13_CR20","unstructured":"Mustafa, B., Riquelme, C., Puigcerver, J., Jenatton, R., Houlsby, N.: Multimodal contrastive learning with limoe: the language-image mixture of experts. In: Advances in NeurIPS, vol.\u00a035, pp. 9564\u20139576 (2022)"},{"key":"13_CR21","doi-asserted-by":"publisher","unstructured":"Nishikawa, S., Ri, R., Yamada, I., Tsuruoka, Y., Echizen, I.: EASE: entity-aware contrastive learning of sentence embedding. In: Proceedings of the NAACL-HLT, pp. 3870\u20133885 (2022). https:\/\/doi.org\/10.18653\/v1\/2022.naacl-main.284","DOI":"10.18653\/v1\/2022.naacl-main.284"},{"key":"13_CR22","unstructured":"van\u00a0den Oord, A., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding, arXiv:1807.03748 (2019)"},{"key":"13_CR23","unstructured":"Paszke, A., et\u00a0al.: Pytorch: an imperative style, high-performance deep learning library. In: Advances in NeurIPS, vol.\u00a032 (2019)"},{"key":"13_CR24","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: Proceedings of the 38th ICML, vol.\u00a0139, pp. 8748\u20138763 (2021)"},{"issue":"140","key":"13_CR25","first-page":"1","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21(140), 1\u201367 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"13_CR26","doi-asserted-by":"crossref","unstructured":"Tschannen, M., Mustafa, B., Houlsby, N.: Clippo: image-and-language understanding from pixels only. In: Proceedings of the CVPR, pp. 11006\u201311017 (2023)","DOI":"10.1109\/CVPR52729.2023.01059"},{"key":"13_CR27","unstructured":"Vaswani, A., et\u00a0al.: Attention is all you need. In: Advances in NeurIPS, vol.\u00a030 (2017)"},{"key":"13_CR28","doi-asserted-by":"publisher","unstructured":"Wu, C.S., Hoi, S.C., Socher, R., Xiong, C.: TOD-BERT: pre-trained natural language understanding for task-oriented dialogue. In: Proceedings of EMNLP, pp. 917\u2013929 (2020). https:\/\/doi.org\/10.18653\/v1\/2020.emnlp-main.66","DOI":"10.18653\/v1\/2020.emnlp-main.66"},{"key":"13_CR29","doi-asserted-by":"crossref","unstructured":"Yin, Z., Hui, B., Yang, M., Huang, F., Li, Y.: Dialclip: empowering clip as multi-modal dialog retriever, arXiv:2401.01076 (2024)","DOI":"10.1109\/ICASSP48485.2024.10448111"},{"key":"13_CR30","doi-asserted-by":"publisher","unstructured":"You, H., et\u00a0al.: Learning visual representation from modality-shared contrastive language-image pre-training. In: Proceedings of the ECCV, Part XXVII, pp. 69\u201387 (2022). https:\/\/doi.org\/10.1007\/978-3-031-19812-0_5","DOI":"10.1007\/978-3-031-19812-0_5"},{"key":"13_CR31","doi-asserted-by":"publisher","unstructured":"Zang, X., et\u00a0al.: PhotoChat: a human-human dialogue dataset with photo sharing behavior for joint image-text modeling. In: Proceedings of the 59th Annual Meeting of ACL and the 11th IJCNLP (Vol. 1: Long Papers), pp. 6142\u20136152 (2021). https:\/\/doi.org\/10.18653\/v1\/2021.acl-long.479","DOI":"10.18653\/v1\/2021.acl-long.479"}],"container-title":["Lecture Notes in Computer Science","Advances in Knowledge Discovery and Data Mining"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-8180-8_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T13:16:38Z","timestamp":1750338998000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-8180-8_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819681792","9789819681808"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-8180-8_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"20 June 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PAKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific-Asia Conference on Knowledge Discovery and Data Mining","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sydney, NSW","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 June 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 June 2025","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":"pakdd2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/pakdd2025.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}