{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T07:05:49Z","timestamp":1790233549079,"version":"4.1.0"},"publisher-location":"Cham","reference-count":47,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370099","type":"print"},{"value":"9783032370105","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-37010-5_16","type":"book-chapter","created":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T06:56:18Z","timestamp":1790232978000},"page":"285-301","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["BIP: Bi-Level Information Transfer and\u00a0Completion Prompting for\u00a0Visual Recognition with\u00a0Missing Modalities"],"prefix":"10.1007","author":[{"given":"Haoran","family":"Fan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xu","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xianglong","family":"Bao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zheng","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Fan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaojiao","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,25]]},"reference":[{"key":"16_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)"},{"issue":"320","key":"16_CR2","first-page":"201","volume":"16","author":"D Barber","year":"2004","unstructured":"Barber, D., Agakov, F.: The im algorithm: a variational approach to information maximization. Adv. Neural. Inf. Process. Syst. 16(320), 201 (2004)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"16_CR3","unstructured":"Bishop, C.M.: Mixture density networks (1994)"},{"key":"16_CR4","doi-asserted-by":"crossref","unstructured":"Bossard, L., Guillaumin, M., Van Gool, L.: Food-101-mining discriminative components with random forests. In: European Conference on Computer Vision, pp. 446\u2013461. Springer (2014)","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"16_CR5","unstructured":"Dosovitskiy, A., et al.: An image is worth $$16\\times 16$$ words: Transformers for image recognition at scale. In: International Conference on Learning Representations (ICLR) (2021)"},{"key":"16_CR6","doi-asserted-by":"crossref","unstructured":"Gallo, I., Ria, G., Landro, N., La Grassa, R.: Image and text fusion for upmc food-101 using bert and cnns. In: 2020 35th International Conference on Image and Vision Computing New Zealand (IVCNZ), pp. 1\u20136. IEEE (2020)","DOI":"10.1109\/IVCNZ51579.2020.9290622"},{"key":"16_CR7","doi-asserted-by":"crossref","unstructured":"Guo, Z., Jin, T., Zhao, Z.: Multimodal prompt learning with missing modalities for sentiment analysis and emotion recognition. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (volume 1: Long papers), pp. 1726\u20131736 (2024)","DOI":"10.18653\/v1\/2024.acl-long.94"},{"key":"16_CR8","unstructured":"Ha, D., Dai, A., Le, Q.V.: (2016). arXiv preprint arXiv:1609.09106 Hypernetworks."},{"key":"16_CR9","doi-asserted-by":"crossref","unstructured":"Havaei, M., Guizard, N., Chapados, N., Bengio, Y.: Hemis: hetero-modal image segmentation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 469\u2013477. Springer (2016)","DOI":"10.1007\/978-3-319-46723-8_54"},{"key":"16_CR10","doi-asserted-by":"crossref","unstructured":"Hoffman, J., Gupta, S., Darrell, T.: Learning with side information through modality hallucination. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 826\u2013834 (2016)","DOI":"10.1109\/CVPR.2016.96"},{"key":"16_CR11","doi-asserted-by":"publisher","first-page":"67446","DOI":"10.52202\/079017-2153","volume":"37","author":"L Hu","year":"2024","unstructured":"Hu, L., Shi, T., Feng, W., Shang, F., Wan, L.: Deep correlated prompting for visual recognition with missing modalities. Adv. Neural. Inf. Process. Syst. 37, 67446\u201367466 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"16_CR12","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: Proceedings of the European Conference on Computer Vision (ECCV), pp. 709\u2013727. Springer (2022)","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"16_CR13","doi-asserted-by":"crossref","unstructured":"Ke, G., et al.: Knowledge bridger: towards training-free missing modality completion. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 25864\u201325873 (2025)","DOI":"10.1109\/CVPR52734.2025.02409"},{"key":"16_CR14","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":"16_CR15","first-page":"2611","volume":"33","author":"D Kiela","year":"2020","unstructured":"Kiela, D., et al.: 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":"16_CR16","doi-asserted-by":"crossref","unstructured":"Kim, D., Kim, T.: Missing modality prediction for unpaired multimodal learning via joint embedding of unimodal models. In: European Conference on Computer Vision, pp. 171\u2013187. Springer (2024)","DOI":"10.1007\/978-3-031-73016-0_11"},{"key":"16_CR17","unstructured":"Kim, W., Son, B., Kim, I.: Vilt: Vision-and-language transformer without convolution or region supervision. In: Proceedings of the 38th International Conference on Machine Learning (ICML). Proceedings of Machine Learning Research, vol.\u00a0139, pp. 5583\u20135594 (2021)"},{"issue":"3","key":"16_CR18","first-page":"455","volume":"51","author":"TG Kolda","year":"2009","unstructured":"Kolda, T.G., Bader, B.W.: Tensor decompositions and applications. SIAM review 51(3), 455\u2013500 (2009)","journal-title":"Tensor decompositions and applications. SIAM review"},{"key":"16_CR19","unstructured":"Kornblith, S., Norouzi, M., Lee, H., Hinton, G.: Similarity of neural network representations revisited. In: International Conference on Machine Learning, pp. 3519\u20133529. PMlR (2019)"},{"key":"16_CR20","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, pp. 14943\u201314952 (2023)","DOI":"10.1109\/CVPR52729.2023.01435"},{"key":"16_CR21","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In: International Conference on Machine Learning, pp. 12888\u201312900. PMLR (2022)"},{"key":"16_CR22","doi-asserted-by":"publisher","first-page":"17612","DOI":"10.52202\/068431-1280","volume":"35","author":"VW Liang","year":"2022","unstructured":"Liang, V.W., Zhang, Y., Kwon, Y., Yeung, S., Zou, J.Y.: Mind the gap: understanding the modality gap in multi-modal contrastive representation learning. Adv. Neural. Inf. Process. Syst. 35, 17612\u201317625 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"16_CR23","doi-asserted-by":"publisher","first-page":"1686","DOI":"10.1162\/tacl_a_00628","volume":"11","author":"R Lin","year":"2023","unstructured":"Lin, R., Hu, H.: Missmodal: increasing robustness to missing modality in multimodal sentiment analysis. Trans. Assoc. Comput. Linguist. 11, 1686\u20131702 (2023)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"16_CR24","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, pp. 18177\u201318186 (2022)","DOI":"10.1109\/CVPR52688.2022.01764"},{"key":"16_CR25","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. 35, pp. 2302\u20132310(2021)","DOI":"10.1609\/aaai.v35i3.16330"},{"key":"16_CR26","doi-asserted-by":"crossref","unstructured":"Pipoli, V., et al.: Semantically conditioned prompts for visual recognition under missing modality scenarios. In: 2025 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 4968\u20134977. IEEE (2025)","DOI":"10.1109\/WACV61041.2025.00486"},{"key":"16_CR27","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: Proceedings of the 38th International Conference on Machine Learning (ICML). Proceedings of Machine Learning Research, vol. 139, pp. 8748\u20138763 (2021)"},{"key":"16_CR28","doi-asserted-by":"crossref","unstructured":"Shang, C., Palmer, A., Sun, J., Chen, K.S., Lu, J., Bi, J.: Vigan: missing view imputation with generative adversarial networks. In: 2017 IEEE International Conference on Big Data (Big Data), pp. 766\u2013775. IEEE (2017)","DOI":"10.1109\/BigData.2017.8257992"},{"key":"16_CR29","unstructured":"Shi, Y., Paige, B., Torr, P.: Variational mixture-of-experts autoencoders for multi-modal deep generative models. Adv. Neural. Inf. Process. Syst. 32 (2019)"},{"key":"16_CR30","unstructured":"Srivastava, N., Salakhutdinov, R.R.: Multimodal learning with deep boltzmann machines. In: Advances in neural information processing systems, p. 25 (2012)"},{"key":"16_CR31","first-page":"24804","volume":"34","author":"Y Tashiro","year":"2021","unstructured":"Tashiro, Y., Song, J., Song, Y., Ermon, S.: Csdi: conditional score-based diffusion models for probabilistic time series imputation. Adv. Neural. Inf. Process. Syst. 34, 24804\u201324816 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"16_CR32","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":"16_CR33","doi-asserted-by":"crossref","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)","DOI":"10.1109\/ICMEW.2015.7169757"},{"key":"16_CR34","doi-asserted-by":"crossref","unstructured":"Wang, Y., Cui, Z., Li, Y.: Distribution-consistent modal recovering for incomplete multimodal learning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 22025\u201322034 (2023)","DOI":"10.1109\/ICCV51070.2023.02013"},{"key":"16_CR35","unstructured":"Wu, R., Wang, H., Chen, H.T., Carneiro, G.: Deep multimodal learning with missing modality: A survey (2024). arXiv preprintarXiv:2409.07825"},{"key":"16_CR36","doi-asserted-by":"crossref","unstructured":"Xu, Y., Zhou, F., Zhao, C., Wang, Y., Yang, C., Chen, H.: Distilled prompt learning for incomplete multimodal survival prediction. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 5102\u20135111 (2025)","DOI":"10.1109\/CVPR52734.2025.00481"},{"key":"16_CR37","doi-asserted-by":"crossref","unstructured":"Yan, W., Wang, Y., Lin, W., Guo, Z., Zhao, Z., Jin, T.: Low-rank prompt interaction for continual vision-language retrieval. In: Proceedings of the 32nd ACM International Conference on Multimedia, pp. 8257\u20138266 (2024)","DOI":"10.1145\/3664647.3681264"},{"key":"16_CR38","doi-asserted-by":"crossref","unstructured":"Yao, H., Zhang, R., Xu, C.: Visual-language prompt tuning with knowledge-guided context optimization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6757\u20136767 (2023)","DOI":"10.1109\/CVPR52729.2023.00653"},{"key":"16_CR39","doi-asserted-by":"crossref","unstructured":"Yao, H., Zhang, R., Xu, C.: Tcp: Textual-based class-aware prompt tuning for visual-language model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 23438\u201323448 (2024)","DOI":"10.1109\/CVPR52733.2024.02212"},{"key":"16_CR40","doi-asserted-by":"crossref","unstructured":"Zeng, J., Liu, T., Zhou, J.: Tag-assisted multimodal sentiment analysis under uncertain missing modalities. In: Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 1545\u20131554 (2022)","DOI":"10.1145\/3477495.3532064"},{"key":"16_CR41","doi-asserted-by":"crossref","unstructured":"Zhang, J., Wu, S., Gao, L., Shen, H.T., Song, J.: Dept: decoupled prompt tuning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12924\u201312933 (2024)","DOI":"10.1109\/CVPR52733.2024.01228"},{"key":"16_CR42","doi-asserted-by":"publisher","first-page":"182","DOI":"10.1016\/j.neucom.2021.12.005","volume":"473","author":"Z Zhang","year":"2022","unstructured":"Zhang, Z., Schomaker, L.: Divergan: an efficient and effective single-stage framework for diverse text-to-image generation. Neurocomputing 473, 182\u2013198 (2022)","journal-title":"Neurocomputing"},{"key":"16_CR43","doi-asserted-by":"crossref","unstructured":"Zhang, Z., et al.: Synergistic prompting for robust visual recognition with missing modalities. arXiv preprint arXiv:2507.07802 (2025)","DOI":"10.1109\/ICCV51701.2025.00183"},{"key":"16_CR44","doi-asserted-by":"crossref","unstructured":"Zhao, J., Li, R., Jin, Q.: Missing modality imagination network for emotion recognition with uncertain missing modalities. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pp. 2608\u20132618 (2021)","DOI":"10.18653\/v1\/2021.acl-long.203"},{"key":"16_CR45","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":"16_CR46","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"},{"key":"16_CR47","doi-asserted-by":"crossref","unstructured":"Zhu, B., Niu, Y., Han, Y., Wu, Y., Zhang, H.: Prompt-aligned gradient for prompt tuning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15659\u201315669 (2023)","DOI":"10.1109\/ICCV51070.2023.01435"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37010-5_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T06:56:30Z","timestamp":1790232990000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37010-5_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370099","9783032370105"],"references-count":47,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37010-5_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"25 September 2026","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":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","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":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}