{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T09:52:12Z","timestamp":1788774732880,"version":"build-2803163510"},"publisher-location":"Singapore","reference-count":24,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819617098","type":"print"},{"value":"9789819617104","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\/978-981-96-1710-4_2","type":"book-chapter","created":{"date-parts":[[2025,1,31]],"date-time":"2025-01-31T09:56:36Z","timestamp":1738317396000},"page":"14-27","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["A Dual-Aligned Model for\u00a0Multimodal Recommendation"],"prefix":"10.1007","author":[{"given":"Kangning","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5078-2201","authenticated-orcid":false,"given":"Yingjie","family":"Qin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6695-4536","authenticated-orcid":false,"given":"Ruilong","family":"Su","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8726-3927","authenticated-orcid":false,"given":"Yifan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0127-2425","authenticated-orcid":false,"given":"Weinan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0281-8271","authenticated-orcid":false,"given":"Yong","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,2,1]]},"reference":[{"key":"2_CR1","doi-asserted-by":"crossref","unstructured":"Chen, X., He, K.: Exploring simple Siamese representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15750\u201315758 (2021)","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"2_CR2","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"2_CR3","unstructured":"Grill, J.B., et al.: Bootstrap your own latent-a new approach to self-supervised learning. In: Advances in Neural Information Processing Systems, vol. 33, pp. 21271\u201321284 (2020)"},{"key":"2_CR4","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":"2_CR5","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":"2_CR6","doi-asserted-by":"crossref","unstructured":"He, R., McAuley, J.: VBPR: visual Bayesian personalized ranking from implicit feedback. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 30 (2016)","DOI":"10.1609\/aaai.v30i1.9973"},{"key":"2_CR7","doi-asserted-by":"crossref","unstructured":"He, X., Deng, K., Wang, X., Li, Y., Zhang, Y., Wang, M.: LightGCN: simplifying and powering graph convolution network for recommendation. In: Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 639\u2013648 (2020)","DOI":"10.1145\/3397271.3401063"},{"key":"2_CR8","doi-asserted-by":"crossref","unstructured":"Liu, Q., Wu, S., Wang, L.: DeepStyle: learning user preferences for visual recommendation. In: Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 841\u2013844 (2017)","DOI":"10.1145\/3077136.3080658"},{"key":"2_CR9","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: AlignREC: aligning and training in multimodal recommendations (2024)","DOI":"10.1145\/3627673.3679626"},{"key":"2_CR10","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"issue":"8","key":"2_CR11","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford, A., et al.: Language models are unsupervised multitask learners. OpenAI Blog 1(8), 9 (2019)","journal-title":"OpenAI Blog"},{"key":"2_CR12","unstructured":"Rendle, S., Freudenthaler, C., Gantner, Z., Schmidt-Thieme, L.: BPR: Bayesian personalized ranking from implicit feedback. arXiv preprint arXiv:1205.2618 (2012)"},{"key":"2_CR13","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"2_CR14","doi-asserted-by":"crossref","unstructured":"Tao, Z., et al.: Self-supervised learning for multimedia recommendation. IEEE Trans. Multimedia (2022)","DOI":"10.1109\/TMM.2022.3187556"},{"key":"2_CR15","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"2_CR16","unstructured":"Wang, Q., Wei, Y., Yin, J., Wu, J., Song, X., Nie, L.: DualGNN: dual graph neural network for multimedia recommendation. IEEE Trans. Multimedia (2021)"},{"issue":"6","key":"2_CR17","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-023-2691-y","volume":"17","author":"X Wang","year":"2023","unstructured":"Wang, X., et al.: VIS+ AI: integrating visualization with artificial intelligence for efficient data analysis. Front. Comput. Sci. 17(6), 176709 (2023)","journal-title":"Front. Comput. Sci."},{"key":"2_CR18","doi-asserted-by":"crossref","unstructured":"Wei, Y., Wang, X., Nie, L., He, X., Chua, T.S.: Graph-refined convolutional network for multimedia recommendation with implicit feedback. In: Proceedings of the 28th ACM MM, pp. 3541\u20133549 (2020)","DOI":"10.1145\/3394171.3413556"},{"key":"2_CR19","doi-asserted-by":"crossref","unstructured":"Wei, Y., Wang, X., Nie, L., He, X., Hong, R., Chua, T.S.: MMGCN: multi-modal graph convolution network for personalized recommendation of micro-video. In: Proceedings of the 27th ACM MM, pp. 1437\u20131445 (2019)","DOI":"10.1145\/3343031.3351034"},{"key":"2_CR20","doi-asserted-by":"crossref","unstructured":"Zhang, J., Zhu, Y., Liu, Q., Wu, S., Wang, S., Wang, L.: Mining latent structures for multimedia recommendation. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 3872\u20133880 (2021)","DOI":"10.1145\/3474085.3475259"},{"key":"2_CR21","doi-asserted-by":"crossref","unstructured":"Zhang, K., et al.: Dream: a dual representation learning model for multimodal recommendation (2024)","DOI":"10.1137\/1.9781611978032.86"},{"key":"2_CR22","unstructured":"Zhou, H., Zhou, X., Zeng, Z., Zhang, L., Shen, Z.: A comprehensive survey on multimodal recommender systems: taxonomy, evaluation, and future directions. arXiv preprint arXiv:2302.04473 (2023)"},{"key":"2_CR23","doi-asserted-by":"crossref","unstructured":"Zhou, X.: A tale of two graphs: freezing and denoising graph structures for multimodal recommendation. arXiv preprint arXiv:2211.06924 (2022)","DOI":"10.1145\/3581783.3611943"},{"key":"2_CR24","doi-asserted-by":"crossref","unstructured":"Zhou, X., et al.: Bootstrap latent representations for multi-modal recommendation. In: Proceedings of the ACM Web Conference 2023, pp. 845\u2013854 (2023)","DOI":"10.1145\/3543507.3583251"}],"container-title":["Lecture Notes in Computer Science","Information Retrieval"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-1710-4_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,31]],"date-time":"2025-01-31T09:56:50Z","timestamp":1738317410000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-1710-4_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819617098","9789819617104"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-1710-4_2","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":"1 February 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CCIR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China Conference on Information Retrieval","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Wuhan","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccir2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.cips-ir.org.cn\/CCIR2024\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}