{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T08:05:34Z","timestamp":1784534734738,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":16,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819234257","type":"print"},{"value":"9789819234264","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T00:00:00Z","timestamp":1784592000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T00:00:00Z","timestamp":1784592000000},"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":[[2027]]},"DOI":"10.1007\/978-981-92-3426-4_14","type":"book-chapter","created":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T07:33:44Z","timestamp":1784532824000},"page":"160-171","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ManifoldMM: Riemannian Manifold Alignment with Cross-Modal Knowledge Distillation for Structured Multimodal Learning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-0292-481X","authenticated-orcid":false,"given":"Junling","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0943-0883","authenticated-orcid":false,"given":"Jinbao","family":"Hong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3066-2780","authenticated-orcid":false,"given":"Jiaqi","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-8763-3268","authenticated-orcid":false,"given":"Wentian","family":"Zhai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,21]]},"reference":[{"key":"14_CR1","first-page":"689","volume":"11","author":"J Ngiam","year":"2011","unstructured":"Ngiam, J., Khosla, A., Kim, M., Nam, J., Lee, H., Ng, A.Y., et al.: Multimodal deep learning. ICML 11, 689\u2013696 (2011)","journal-title":"ICML"},{"key":"14_CR2","unstructured":"Lu, J., Batra, D., Parikh, D., Lee, S.: Vilbert: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. Adv. Neural Inf. Process. Syst. 32 (2019)"},{"key":"14_CR3","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: Blip-2: bootstrapping language-image pre-training with frozen image encoders and large language models. In: International Conference on Machine Learning, pp. 19730\u201319742. PMLR (2023)"},{"key":"14_CR4","unstructured":"Yoon, M., Koh, J.Y., Hooi, B., Salakhutdinov, R.: Multimodal graph learning for generative tasks. arXiv preprint arXiv:2310.07478 (2023)"},{"key":"14_CR5","unstructured":"Kipf, T.: Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2017)"},{"key":"14_CR6","unstructured":"Villani, C., et al.: Optimal Transport: Old and New, vol. 338. Springer, Heidelberg (2009)"},{"key":"14_CR7","unstructured":"M. Cuturi, \u201cSinkhorn distances: Lightspeed computation of optimal transport,\u201d Advances in Neural Information Processing Systems, vol. 26, 2013"},{"key":"14_CR8","unstructured":"Courty, N., Flamary, R., Habrard, A., Rakotomamonjy, A.: Joint distribution optimal transportation for domain adaptation. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"14_CR9","unstructured":"Arjovsky, M., Chintala, S., Bottou, L.: Wasserstein generative adversarial networks. In: International Conference on Machine Learning, pp. 214\u2013223. PMLR (2017)"},{"key":"14_CR10","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)"},{"key":"14_CR11","unstructured":"Burns, A., et al.: WikiWeb2M: a page-level multimodal wikipedia dataset. arXiv preprint arXiv:2305.05432 (2023)"},{"key":"14_CR12","unstructured":"Zhu, J., Zhou, Y., Qian, S., He, Z., Zhao, T., Shah, N., Koutra, D.: Multimodal graph benchmark. arXiv e-prints arXiv\u20132406 (2024)"},{"key":"14_CR13","unstructured":"Wang, P., et al.: Qwen2-VL: enhancing vision-language model's perception of the world at any resolution. arXiv preprint arXiv:2409.12191 (2024)"},{"key":"14_CR14","unstructured":"Zhang, S., et al.: OPT: Open pre-trained transformer language models. arXiv preprint arXiv:2205.01068 (2022)"},{"key":"14_CR15","unstructured":"Touvron, H., et al.: LLaMA: open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"14_CR16","unstructured":"Kochurov, M., Karimov, R., Kozlukov, S.: Geoopt: riemannian optimization in pytorch. arXiv preprint arXiv:2005.02819 (2020)"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-92-3426-4_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T07:33:44Z","timestamp":1784532824000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-3426-4_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,21]]},"ISBN":["9789819234257","9789819234264"],"references-count":16,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-3426-4_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,21]]},"assertion":[{"value":"21 July 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Toronto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 July 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2026a","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2026\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}