{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T13:14:43Z","timestamp":1781615683855,"version":"3.54.5"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031730153","type":"print"},{"value":"9783031730160","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T00:00:00Z","timestamp":1729900800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T00:00:00Z","timestamp":1729900800000},"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\/978-3-031-73016-0_11","type":"book-chapter","created":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T19:02:40Z","timestamp":1729882960000},"page":"171-187","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Missing Modality Prediction for\u00a0Unpaired Multimodal Learning via\u00a0Joint Embedding of\u00a0Unimodal Models"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-0900-0099","authenticated-orcid":false,"given":"Donggeun","family":"Kim","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6056-6836","authenticated-orcid":false,"given":"Taesup","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,26]]},"reference":[{"key":"11_CR1","unstructured":"Arevalo, J., Solorio, T., Montes-y G\u00f3mez, M., Gonz\u00e1lez, F.A.: Gated multimodal units for information fusion. arXiv preprint arXiv:1702.01992 (2017)"},{"key":"11_CR2","unstructured":"Bardes, A., Ponce, J., LeCun, Y.: Vicreg: Variance-invariance-covariance regularization for self-supervised learning. arXiv preprint arXiv:2105.04906 (2021)"},{"key":"11_CR3","first-page":"9912","volume":"33","author":"M Caron","year":"2020","unstructured":"Caron, M., Misra, I., Mairal, J., Goyal, P., Bojanowski, P., Joulin, A.: Unsupervised learning of visual features by contrasting cluster assignments. Adv. Neural. Inf. Process. Syst. 33, 9912\u20139924 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"11_CR4","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International conference on machine learning. pp. 1597\u20131607. PMLR (2020)"},{"key":"11_CR5","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":"11_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Y.C., Li, L., Yu, L., El\u00a0Kholy, A., Ahmed, F., Gan, Z., Cheng, Y., Liu, J.: Uniter: Universal image-text representation learning. In: European conference on computer vision. pp. 104\u2013120. Springer (2020)","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"11_CR7","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et\u00a0al.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"11_CR8","unstructured":"Gong, Y., Rouditchenko, A., Liu, A.H., Harwath, D., Karlinsky, L., Kuehne, H., Glass, J.: Contrastive audio-visual masked autoencoder. arXiv preprint arXiv:2210.07839 (2022)"},{"key":"11_CR9","first-page":"21271","volume":"33","author":"JB Grill","year":"2020","unstructured":"Grill, J.B., Strub, F., Altch\u00e9, F., Tallec, C., Richemond, P., Buchatskaya, E., Doersch, C., Avila Pires, B., Guo, Z., Gheshlaghi Azar, M., et al.: Bootstrap your own latent-a new approach to self-supervised learning. Adv. Neural. Inf. Process. Syst. 33, 21271\u201321284 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"11_CR10","unstructured":"Houlsby, N., Giurgiu, A., Jastrzebski, S., Morrone, B., De\u00a0Laroussilhe, Q., Gesmundo, A., Attariyan, M., Gelly, S.: Parameter-efficient transfer learning for nlp. In: International Conference on Machine Learning. pp. 2790\u20132799. PMLR (2019)"},{"key":"11_CR11","unstructured":"Hu, E.J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., Chen, W.: Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)"},{"key":"11_CR12","doi-asserted-by":"crossref","unstructured":"Huang, S.C., Shen, L., Lungren, M.P., Yeung, S.: Gloria: A multimodal global-local representation learning framework for label-efficient medical image recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 3942\u20133951 (2021)","DOI":"10.1109\/ICCV48922.2021.00391"},{"key":"11_CR13","doi-asserted-by":"crossref","unstructured":"Jia, M., Tang, L., Chen, B.C., Cardie, C., Belongie, S., Hariharan, B., Lim, S.N.: Visual prompt tuning. In: European Conference on Computer Vision. pp. 709\u2013727. Springer (2022)","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"11_CR14","unstructured":"Khan, Z., Fu, Y.: Contrastive alignment of vision to language through parameter-efficient transfer learning. arXiv preprint arXiv:2303.11866 (2023)"},{"key":"11_CR15","doi-asserted-by":"crossref","unstructured":"Khattak, M.U., Rasheed, H., Maaz, M., Khan, S., Khan, F.S.: Maple: Multi-modal prompt learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 19113\u201319122 (2023)","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"11_CR16","doi-asserted-by":"crossref","unstructured":"Khattak, M.U., Wasim, S.T., Naseer, M., Khan, S., Yang, M.H., Khan, F.S.: Self-regulating prompts: Foundational model adaptation without forgetting. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 15190\u201315200 (2023)","DOI":"10.1109\/ICCV51070.2023.01394"},{"key":"11_CR17","first-page":"2611","volume":"33","author":"D Kiela","year":"2020","unstructured":"Kiela, D., Firooz, H., Mohan, A., Goswami, V., Singh, A., Ringshia, P., Testuggine, D.: The hateful memes challenge: Detecting hate speech in multimodal memes. Adv. Neural. Inf. Process. Syst. 33, 2611\u20132624 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"11_CR18","unstructured":"Kim, W., Son, B., Kim, I.: Vilt: Vision-and-language transformer without convolution or region supervision. In: International Conference on Machine Learning. pp. 5583\u20135594. PMLR (2021)"},{"key":"11_CR19","unstructured":"Kosar, V., Hoskovec, A., \u0160ulc, M., Bartyzal, R.: Glami-1m: A multilingual image-text fashion dataset. arXiv preprint arXiv:2211.14451 (2022)"},{"key":"11_CR20","unstructured":"LeCun, Y.: A path towards autonomous machine intelligence version 0.9. 2, 2022-06-27. Open Review 62(1) (2022)"},{"key":"11_CR21","doi-asserted-by":"crossref","unstructured":"Lee, D., Song, S., Suh, J., Choi, J., Lee, S., Kim, H.J.: Read-only prompt optimization for vision-language few-shot learning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 1401\u20131411 (2023)","DOI":"10.1109\/ICCV51070.2023.00135"},{"key":"11_CR22","doi-asserted-by":"crossref","unstructured":"Lee, Y.L., Tsai, Y.H., Chiu, W.C., Lee, C.Y.: Multimodal prompting with missing modalities for visual recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp. 14943\u201314952 (June 2023)","DOI":"10.1109\/CVPR52729.2023.01435"},{"key":"11_CR23","doi-asserted-by":"crossref","unstructured":"Lester, B., Al-Rfou, R., Constant, N.: The power of scale for parameter-efficient prompt tuning. arXiv preprint arXiv:2104.08691 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"11_CR24","doi-asserted-by":"crossref","unstructured":"Li, X.L., Liang, P.: Prefix-tuning: Optimizing continuous prompts for generation. arXiv preprint arXiv:2101.00190 (2021)","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"11_CR25","doi-asserted-by":"crossref","unstructured":"Ma, M., Ren, J., Zhao, L., Testuggine, D., Peng, X.: Are multimodal transformers robust to missing modality? In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp. 18177\u201318186 (June 2022)","DOI":"10.1109\/CVPR52688.2022.01764"},{"key":"11_CR26","doi-asserted-by":"crossref","unstructured":"Ma, M., Ren, J., Zhao, L., Tulyakov, S., Wu, C., Peng, X.: Smil: Multimodal learning with severely missing modality. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol.\u00a035, pp. 2302\u20132310 (2021)","DOI":"10.1609\/aaai.v35i3.16330"},{"key":"11_CR27","unstructured":"Van\u00a0der Maaten, L., Hinton, G.: Visualizing data using t-sne. Journal of machine learning research 9(11) (2008)"},{"key":"11_CR28","unstructured":"Qi, W., Ruan, Y.P., Zuo, Y., Li, T.: Parameter-efficient tuning on layer normalization for pre-trained language models. arXiv preprint arXiv:2211.08682 (2022)"},{"key":"11_CR29","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International conference on machine learning. pp. 8748\u20138763. PMLR (2021)"},{"key":"11_CR30","unstructured":"Shwartz-Ziv, R., Balestriero, R., Kawaguchi, K., Rudner, T.G., LeCun, Y.: An information-theoretic perspective on variance-invariance-covariance regularization. arXiv preprint arXiv:2303.00633 (2023)"},{"key":"11_CR31","doi-asserted-by":"crossref","unstructured":"Srinivasan, K., Raman, K., Chen, J., Bendersky, M., Najork, M.: Wit: Wikipedia-based image text dataset for multimodal multilingual machine learning. In: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. pp. 2443\u20132449 (2021)","DOI":"10.1145\/3404835.3463257"},{"key":"11_CR32","doi-asserted-by":"crossref","unstructured":"Sun, C., Myers, A., Vondrick, C., Murphy, K., Schmid, C.: Videobert: A joint model for video and language representation learning. In: Proceedings of the IEEE\/CVF international conference on computer vision. pp. 7464\u20137473 (2019)","DOI":"10.1109\/ICCV.2019.00756"},{"key":"11_CR33","doi-asserted-by":"crossref","unstructured":"Tan, H., Bansal, M.: Lxmert: Learning cross-modality encoder representations from transformers. arXiv preprint arXiv:1908.07490 (2019)","DOI":"10.18653\/v1\/D19-1514"},{"key":"11_CR34","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I.: Attention is all you need. Advances in neural information processing systems 30 (2017)"},{"key":"11_CR35","doi-asserted-by":"crossref","unstructured":"Wang, H., Chen, Y., Ma, C., Avery, J., Hull, L., Carneiro, G.: Multi-modal learning with missing modality via shared-specific feature modelling. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 15878\u201315887 (2023)","DOI":"10.1109\/CVPR52729.2023.01524"},{"key":"11_CR36","unstructured":"Wang, X., Kumar, D., Thome, N., Cord, M., Precioso, F.: Recipe recognition with large multimodal food dataset. In: 2015 IEEE International Conference on Multimedia & Expo Workshops (ICMEW). pp.\u00a01\u20136. IEEE (2015)"},{"key":"11_CR37","first-page":"5682","volume":"35","author":"Y Wang","year":"2022","unstructured":"Wang, Y., Huang, Z., Hong, X.: S-prompts learning with pre-trained transformers: An occam\u2019s razor for domain incremental learning. Adv. Neural. Inf. Process. Syst. 35, 5682\u20135695 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"11_CR38","doi-asserted-by":"crossref","unstructured":"Wang, Z., Zhang, Z., Ebrahimi, S., Sun, R., Zhang, H., Lee, C.Y., Ren, X., Su, G., Perot, V., Dy, J., et\u00a0al.: Dualprompt: Complementary prompting for rehearsal-free continual learning. In: European Conference on Computer Vision. pp. 631\u2013648. Springer (2022)","DOI":"10.1007\/978-3-031-19809-0_36"},{"key":"11_CR39","doi-asserted-by":"crossref","unstructured":"Wang, Z., Zhang, Z., Lee, C.Y., Zhang, H., Sun, R., Ren, X., Su, G., Perot, V., Dy, J., Pfister, T.: Learning to prompt for continual learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 139\u2013149 (2022)","DOI":"10.1109\/CVPR52688.2022.00024"},{"key":"11_CR40","unstructured":"Zaken, E.B., Ravfogel, S., Goldberg, Y.: Bitfit: Simple parameter-efficient fine-tuning for transformer-based masked language-models. arXiv preprint arXiv:2106.10199 (2021)"},{"key":"11_CR41","unstructured":"Zhang, Y., Jiang, H., Miura, Y., Manning, C.D., Langlotz, C.P.: Contrastive learning of medical visual representations from paired images and text. In: Machine Learning for Healthcare Conference. pp. 2\u201325. PMLR (2022)"},{"key":"11_CR42","doi-asserted-by":"crossref","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Conditional prompt learning for vision-language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 16816\u201316825 (2022)","DOI":"10.1109\/CVPR52688.2022.01631"},{"issue":"9","key":"11_CR43","doi-asserted-by":"publisher","first-page":"2337","DOI":"10.1007\/s11263-022-01653-1","volume":"130","author":"K Zhou","year":"2022","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Learning to prompt for vision-language models. Int. J. Comput. Vision 130(9), 2337\u20132348 (2022)","journal-title":"Int. J. Comput. Vision"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73016-0_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T19:04:57Z","timestamp":1729883097000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73016-0_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,26]]},"ISBN":["9783031730153","9783031730160"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73016-0_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,26]]},"assertion":[{"value":"26 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","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":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}