{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T12:27:35Z","timestamp":1742992055388,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":30,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819620708"},{"type":"electronic","value":"9789819620715"}],"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\/978-981-96-2071-5_21","type":"book-chapter","created":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T15:34:06Z","timestamp":1735745646000},"page":"283-297","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Vision-Language Pretraining for\u00a0Variable-Shot Image Classification"],"prefix":"10.1007","author":[{"given":"Sotirios","family":"Papadopoulos","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Konstantinos","family":"Ioannidis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stefanos","family":"Vrochidis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ioannis","family":"Kompatsiaris","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ioannis","family":"Patras","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,1,2]]},"reference":[{"key":"21_CR1","unstructured":"Bao, H., Dong, L., Piao, S., Wei, F.: BeIT: BERT pre-training of image transformers. arXiv preprint arXiv:2106.08254 (2021)"},{"key":"21_CR2","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":"21_CR3","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":"21_CR4","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"21_CR5","doi-asserted-by":"crossref","unstructured":"Dong, X., et\u00a0al.: MaskCLIP: masked self-distillation advances contrastive language-image pretraining. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10995\u201311005 (2023)","DOI":"10.1109\/CVPR52729.2023.01058"},{"key":"21_CR6","first-page":"6704","volume":"35","author":"S Goel","year":"2022","unstructured":"Goel, S., Bansal, H., Bhatia, S., Rossi, R., Vinay, V., Grover, A.: CyCLIP: cyclic contrastive language-image pretraining. Adv. Neural. Inf. Process. Syst. 35, 6704\u20136719 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"21_CR7","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: International Conference on Machine Learning, pp. 4904\u20134916. PMLR (2021)"},{"key":"21_CR8","first-page":"18661","volume":"33","author":"P Khosla","year":"2020","unstructured":"Khosla, P., et al.: Supervised contrastive learning. Adv. Neural. Inf. Process. Syst. 33, 18661\u201318673 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"21_CR9","unstructured":"Krizhevsky, A., Hinton, G., et\u00a0al.: Learning multiple layers of features from tiny images (2009)"},{"key":"21_CR10","unstructured":"Li, Y., et al.: Supervision exists everywhere: a data efficient contrastive language-image pre-training paradigm. arXiv preprint arXiv:2110.05208 (2021)"},{"key":"21_CR11","doi-asserted-by":"crossref","unstructured":"Liang, F., et al.: Open-vocabulary semantic segmentation with mask-adapted clip. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7061\u20137070 (2023)","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"21_CR12","first-page":"17612","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":"21_CR13","unstructured":"Ma, C., Jiang, Y., Wen, X., Yuan, Z., Qi, X.: CoDet: co-occurrence guided region-word alignment for open-vocabulary object detection. Adv. Neural Inf. Process. Syst. 36 (2024)"},{"key":"21_CR14","unstructured":"Maji, S., Rahtu, E., Kannala, J., Blaschko, M., Vedaldi, A.: Fine-grained visual classification of aircraft. arXiv preprint arXiv:1306.5151 (2013)"},{"key":"21_CR15","unstructured":"Minderer, M., Gritsenko, A., Houlsby, N.: Scaling open-vocabulary object detection. Adv. Neural Inf. Process. Syst. 36 (2024)"},{"key":"21_CR16","doi-asserted-by":"crossref","unstructured":"Minderer, M., et\u00a0al.: Simple open-vocabulary object detection. In: European Conference on Computer Vision, pp. 728\u2013755. Springer (2022)","DOI":"10.1007\/978-3-031-20080-9_42"},{"key":"21_CR17","doi-asserted-by":"crossref","unstructured":"Mu, N., Kirillov, A., Wagner, D., Xie, S.: SLIP: self-supervision meets language-image pre-training. In: European Conference on Computer Vision, pp. 529\u2013544. Springer (2022)","DOI":"10.1007\/978-3-031-19809-0_30"},{"key":"21_CR18","doi-asserted-by":"crossref","unstructured":"Nilsback, M.E., Zisserman, A.: Automated flower classification over a large number of classes. In: 2008 Sixth Indian Conference on Computer Vision, Graphics and Image Processing, pp. 722\u2013729. IEEE (2008)","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"21_CR19","unstructured":"Oh, C., et al.: Geodesic multi-modal mixup for robust fine-tuning. Adv. Neural Inf. Process. Syst. 36 (2024)"},{"key":"21_CR20","doi-asserted-by":"crossref","unstructured":"Parkhi, O.M., Vedaldi, A., Zisserman, A., Jawahar, C.: Cats and dogs. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 3498\u20133505. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"21_CR21","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"21_CR22","doi-asserted-by":"crossref","unstructured":"Ramasinghe, S., Shevchenko, V., Avraham, G., Thalaiyasingam, A.: Accept the modality gap: an exploration in the hyperbolic space. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 27263\u201327272 (2024)","DOI":"10.1109\/CVPR52733.2024.02574"},{"key":"21_CR23","unstructured":"Schrodi, S., Hoffmann, D.T., Argus, M., Fischer, V., Brox, T.: Two effects, one trigger: on the modality gap, object bias, and information imbalance in contrastive vision-language representation learning. arXiv preprint arXiv:2404.07983 (2024)"},{"key":"21_CR24","doi-asserted-by":"crossref","unstructured":"Sharma, P., Ding, N., Goodman, S., Soricut, R.: Conceptual captions: a cleaned, hypernymed, image alt-text dataset for automatic image captioning. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, Volume 1: Long Papers, pp. 2556\u20132565 (2018)","DOI":"10.18653\/v1\/P18-1238"},{"key":"21_CR25","unstructured":"Shi, P., Welle, M.C., Bj\u00f6rkman, M., Kragic, D.: Towards understanding the modality gap in clip. In: ICLR 2023 Workshop on Multimodal Representation Learning: Perks and Pitfalls (2023)"},{"key":"21_CR26","unstructured":"Udandarao, V.: Understanding and fixing the modality gap in vision-language models, Master\u2019s thesis, University of Cambridge (2022)"},{"key":"21_CR27","doi-asserted-by":"crossref","unstructured":"Xie, B., Cao, J., Xie, J., Khan, F.S., Pang, Y.: SED: a simple encoder-decoder for open-vocabulary semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3426\u20133436 (2024)","DOI":"10.1109\/CVPR52733.2024.00329"},{"key":"21_CR28","doi-asserted-by":"crossref","unstructured":"Xu, M., Zhang, Z., Wei, F., Hu, H., Bai, X.: Side adapter network for open-vocabulary semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2945\u20132954 (2023)","DOI":"10.1109\/CVPR52729.2023.00288"},{"key":"21_CR29","doi-asserted-by":"crossref","unstructured":"Zhai, X., Mustafa, B., Kolesnikov, A., Beyer, L.: Sigmoid loss for language image pre-training. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11975\u201311986 (2023)","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"21_CR30","doi-asserted-by":"crossref","unstructured":"Zhong, Y., et\u00a0al.: RegionCLIP: region-based language-image pretraining. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16793\u201316803 (2022)","DOI":"10.1109\/CVPR52688.2022.01629"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-2071-5_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T16:03:12Z","timestamp":1735747392000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-2071-5_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819620708","9789819620715"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-2071-5_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"2 January 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"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":"Nara","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 January 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 January 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/mmm2025.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}