{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T04:27:08Z","timestamp":1770697628768,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":33,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819569564","type":"print"},{"value":"9789819569571","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\/978-981-95-6957-1_18","type":"book-chapter","created":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T10:43:51Z","timestamp":1770633831000},"page":"247-261","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["MP-CLIP: Unlocking Long-Text Understanding in\u00a0CLIP via\u00a0Multi-paragraph Encoding"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-4562-4249","authenticated-orcid":false,"given":"Zhaofu","family":"Zeng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5066-9110","authenticated-orcid":false,"given":"Jian","family":"Xing","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,2,10]]},"reference":[{"key":"18_CR1","unstructured":"Beltagy, I., Peters, M.E., Cohan, A.: Longformer: the long-document transformer. arXiv preprint arXiv:2004.05150 (2020)"},{"key":"18_CR2","doi-asserted-by":"crossref","unstructured":"Changpinyo, S., Sharma, P., Ding, R.: Conceptual 12m: pushing web-scale image-text pre-training to recognize long-tail visual concepts. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3558\u20133568 (2021)","DOI":"10.1109\/CVPR46437.2021.00356"},{"key":"18_CR3","doi-asserted-by":"crossref","unstructured":"Chen, L., et al.: Sharegpt4v: improving large multi-modal models with better captions. In: European Conference on Computer Vision, pp. 370\u2013387. Springer (2024)","DOI":"10.1007\/978-3-031-72643-9_22"},{"key":"18_CR4","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"18_CR5","doi-asserted-by":"crossref","unstructured":"Esmaeilpour, S., Liu, B., Robertson, E., Shu, L.: Zero-shot out-of-distribution detection based on the pre-trained model clip. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a036, pp. 6568\u20136576 (2022)","DOI":"10.1609\/aaai.v36i6.20610"},{"key":"18_CR6","unstructured":"Fan, L., Krishnan, D., Isola, P., Katabi, D., Tian, Y.: Improving clip training with language rewrites. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"issue":"2","key":"18_CR7","doi-asserted-by":"publisher","first-page":"581","DOI":"10.1007\/s11263-023-01891-x","volume":"132","author":"P Gao","year":"2024","unstructured":"Gao, P., Geng, S., Zhang, R., Ma, T., Fang, H., Qiao, Y.: Clip-adapter: better vision-language models with feature adapters. Int. J. Comput. Vision 132(2), 581\u2013595 (2024)","journal-title":"Int. J. Comput. Vision"},{"key":"18_CR8","unstructured":"Gu, X., Lin, T.Y., Kuo, W., Cui, Y.: Open-vocabulary object detection via vision and language knowledge distillation. arXiv preprint arXiv:2104.13921 (2021)"},{"key":"18_CR9","doi-asserted-by":"crossref","unstructured":"Hendrycks, D., Zhao, K., Basart, S., Steinhardt, J., Song, D.: Natural adversarial examples. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15262\u201315271 (2021)","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"18_CR10","doi-asserted-by":"crossref","unstructured":"Huang, Y., et al.: Structure-clip: towards scene graph knowledge to enhance multi-modal structured representations. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 2417\u20132425 (2024)","DOI":"10.1609\/aaai.v38i3.28017"},{"key":"18_CR11","doi-asserted-by":"crossref","unstructured":"Kim, D., Angelova, A., Kuo, W.: Region-aware pretraining for open-vocabulary object detection with vision transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11144\u201311154 (2023)","DOI":"10.1109\/CVPR52729.2023.01072"},{"key":"18_CR12","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, W.Y., et\u00a0al.: Segment anything. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4015\u20134026 (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"18_CR13","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2017","unstructured":"Krishna, R., Zhu, Y., Groth, O., Johnson, J., Hata, D.A., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vision 123, 32\u201373 (2017)","journal-title":"Int. J. Comput. Vision"},{"key":"18_CR14","unstructured":"Krizhevsky, A., Hinton, G., et\u00a0al.: Learning multiple layers of features from tiny images (2009)"},{"key":"18_CR15","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":"18_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"18_CR17","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved baselines with visual instruction tuning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 26296\u201326306 (2024)","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"18_CR18","unstructured":"Podell, D., English, Z., Lacey, K., Blattmann, A., Dockhorn, T., M\u00fcller, R.: SDXL: improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:2307.01952 (2023)"},{"key":"18_CR19","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, J., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PmLR (2021)"},{"key":"18_CR20","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.061251(2), 3 (2022)"},{"key":"18_CR21","doi-asserted-by":"crossref","unstructured":"Rasheed, H., Khattak, M.U., Maaz, M., Khan, S., Khan, F.S.: Fine-tuned clip models are efficient video learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6545\u20136554 (2023)","DOI":"10.1109\/CVPR52729.2023.00633"},{"key":"18_CR22","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"18_CR23","first-page":"25278","volume":"35","author":"C Schuhmann","year":"2022","unstructured":"Schuhmann, C., Beaumont, R., Vencu, R., Gordon, C., Wightman, M., et al.: Laion-5b: an open large-scale dataset for training next generation image-text models. Adv. Neural. Inf. Process. Syst. 35, 25278\u201325294 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"18_CR24","unstructured":"Sun, Q., Fang, Y., Wu, L., Wang, X., Cao, Y.: Eva-clip: improved training techniques for clip at scale. arXiv preprint arXiv:2303.15389 (2023)"},{"key":"18_CR25","doi-asserted-by":"crossref","unstructured":"Sun, Z., et al.: Alpha-clip: a clip model focusing on wherever you want. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13019\u201313029 (2024)","DOI":"10.1109\/CVPR52733.2024.01237"},{"key":"18_CR26","doi-asserted-by":"crossref","unstructured":"Tao, M., Bao, B.K., Tang, H., Xu, C.: Galip: generative adversarial clips for text-to-image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14214\u201314223 (2023)","DOI":"10.1109\/CVPR52729.2023.01366"},{"key":"18_CR27","doi-asserted-by":"crossref","unstructured":"Thrush, T., Jiang, R., Bartolo, M., Singh, A., Williams, A., Kiela, C.: Winoground: probing vision and language models for visio-linguistic compositionality. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5238\u20135248 (2022)","DOI":"10.1109\/CVPR52688.2022.00517"},{"key":"18_CR28","doi-asserted-by":"crossref","unstructured":"Wasim, S.T., Naseer, M., Khan, S., Khan, F.S., Shah, M.: Vita-clip: video and text adaptive clip via multimodal prompting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 23034\u201323044 (2023)","DOI":"10.1109\/CVPR52729.2023.02206"},{"key":"18_CR29","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1162\/tacl_a_00166","volume":"2","author":"P Young","year":"2014","unstructured":"Young, P., Lai, A., Hodosh, M., Hockenmaier, J.: From image descriptions to visual denotations: new similarity metrics for semantic inference over event descriptions. Trans. Assoc. Comput. Linguist. 2, 67\u201378 (2014)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"18_CR30","unstructured":"Yuksekgonul, M., Bianchi, F., Kalluri, P., Jurafsky, D., Zou, J.: When and why vision-language models behave like bags-of-words, and what to do about it? In: The Eleventh International Conference on Learning Representations (2023). https:\/\/openreview.net\/forum?id=KRLUvxh8uaX"},{"key":"18_CR31","first-page":"17283","volume":"33","author":"M Zaheer","year":"2020","unstructured":"Zaheer, M., Guruganesh, G., Dubey, K.A., Ainslie, L., et al.: Big bird: transformers for longer sequences. Adv. Neural. Inf. Process. Syst. 33, 17283\u201317297 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"18_CR32","doi-asserted-by":"crossref","unstructured":"Zhang, B., Zhang, P., Dong, X., Zang, Y., Wang, J.: Long-clip: unlocking the long-text capability of clip. In: European Conference on Computer Vision, pp. 310\u2013325. Springer (2024)","DOI":"10.1007\/978-3-031-72983-6_18"},{"key":"18_CR33","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Lei, Y., Zhang, B., Liu, L., Liu, Y.: Zegclip: towards adapting clip for zero-shot semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11175\u201311185 (2023)","DOI":"10.1109\/CVPR52729.2023.01075"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-6957-1_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T10:43:56Z","timestamp":1770633836000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-6957-1_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819569564","9789819569571"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-6957-1_18","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":"10 February 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Prague","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Czech Republic","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":"29 January 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31 January 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"32","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/mmm2026.cz\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}