{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T16:26:43Z","timestamp":1790353603766,"version":"4.1.0"},"publisher-location":"Cham","reference-count":49,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726637","type":"print"},{"value":"9783031726644","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\/978-3-031-72664-4_8","type":"book-chapter","created":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T13:02:04Z","timestamp":1729861324000},"page":"130-147","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["CLAP: Isolating Content from\u00a0Style Through Contrastive Learning with\u00a0Augmented Prompts"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1607-8948","authenticated-orcid":false,"given":"Yichao","family":"Cai","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8195-9349","authenticated-orcid":false,"given":"Yuhang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2805-4396","authenticated-orcid":false,"given":"Zhen","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9126-2107","authenticated-orcid":false,"given":"Javen Qinfeng","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,26]]},"reference":[{"key":"8_CR1","doi-asserted-by":"publisher","unstructured":"Albuquerque, I., Monteiro, J., Darvishi, M., Falk, T.H., Mitliagkas, I.: Generalizing to unseen domains via distribution matching. arXiv preprint arXiv:1911.00804 (2019). https:\/\/doi.org\/10.48550\/arXiv.1911.00804","DOI":"10.48550\/arXiv.1911.00804"},{"key":"8_CR2","doi-asserted-by":"publisher","unstructured":"Bollen, K.A.: Structural Equations with Latent Variables, vol.\u00a0210. John Wiley & Sons, Hoboken (1989). https:\/\/doi.org\/10.1002\/9781118619179","DOI":"10.1002\/9781118619179"},{"key":"8_CR3","unstructured":"Brown, T., et\u00a0al.: Language models are few-shot learners. Adv. Neural Inf. Process. Syst. 33, 1877\u20131901 (2020). https:\/\/dl.acm.org\/doi\/abs\/10.5555\/3495724.3495883"},{"key":"8_CR4","unstructured":"Carlini, N., Terzis, A.: Poisoning and backdooring contrastive learning. In: International Conference on Learning Representations (2021). https:\/\/openreview.net\/forum?id=iC4UHbQ01Mp"},{"key":"8_CR5","doi-asserted-by":"publisher","unstructured":"Carlini, N., Wagner, D.: Towards evaluating the robustness of neural networks. In: 2017 IEEE Symposium on Security and Privacy (SP), pp. 39\u201357. IEEE Computer Society (2017). https:\/\/doi.org\/10.1109\/SP.2017.49","DOI":"10.1109\/SP.2017.49"},{"key":"8_CR6","doi-asserted-by":"publisher","unstructured":"Chen, P., Liu, S., Zhao, H., Jia, J.: Gridmask data augmentation. arXiv preprint arXiv:2001.04086 (2020). https:\/\/doi.org\/10.48550\/arXiv.2001.04086","DOI":"10.48550\/arXiv.2001.04086"},{"key":"8_CR7","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). https:\/\/dl.acm.org\/doi\/abs\/10.5555\/3524938.3525087"},{"key":"8_CR8","doi-asserted-by":"publisher","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). https:\/\/doi.org\/10.1109\/CVPR46437.2021.01549","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"8_CR9","doi-asserted-by":"publisher","unstructured":"Cho, J., Nam, G., Kim, S., Yang, H., Kwak, S.: Promptstyler: prompt-driven style generation for source-free domain generalization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 15702\u201315712 (2023). https:\/\/doi.org\/10.1109\/ICCV51070.2023.01439","DOI":"10.1109\/ICCV51070.2023.01439"},{"key":"8_CR10","unstructured":"Daunhawer, I., Bizeul, A., Palumbo, E., Marx, A., Vogt, J.E.: Identifiability results for multimodal contrastive learning. In: ICLR (2023). https:\/\/openreview.net\/forum?id=U_2kuqoTcB"},{"key":"8_CR11","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (2020). https:\/\/openreview.net\/forum?id=YicbFdNTTy"},{"key":"8_CR12","doi-asserted-by":"publisher","unstructured":"Fort, S.: Adversarial vulnerability of powerful near out-of-distribution detection. arXiv preprint arXiv:2201.07012 (2022). https:\/\/doi.org\/10.48550\/arXiv.2201.07012","DOI":"10.48550\/arXiv.2201.07012"},{"issue":"2","key":"8_CR13","doi-asserted-by":"publisher","first-page":"581","DOI":"10.1007\/s11263-023-01891-x","volume":"132","author":"P Gao","year":"2024","unstructured":"Gao, P., et al.: Clip-adapter: better vision-language models with feature adapters. Int. J. Comput. Vision 132(2), 581\u2013595 (2024). https:\/\/doi.org\/10.1007\/s11263-023-01891-x","journal-title":"Int. J. Comput. Vision"},{"key":"8_CR14","doi-asserted-by":"publisher","unstructured":"Ge, C., Huang, R., Xie, M., Lai, Z., Song, S., Li, S., Huang, G.: Domain adaptation via prompt learning. arXiv preprint arXiv:2202.06687 (2022). https:\/\/doi.org\/10.48550\/arXiv.2202.06687","DOI":"10.48550\/arXiv.2202.06687"},{"key":"8_CR15","doi-asserted-by":"publisher","unstructured":"Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. In: International Conference on Learning Representations (2015). https:\/\/doi.org\/10.48550\/arXiv.1412.6572","DOI":"10.48550\/arXiv.1412.6572"},{"key":"8_CR16","unstructured":"Grill, J.B., et\u00a0al.: Bootstrap your own latent-a new approach to self-supervised learning. Adv. Neural Inf. Process. Syst. 33, 21271\u201321284 (2020). https:\/\/dl.acm.org\/doi\/abs\/10.5555\/3495724.3497510"},{"key":"8_CR17","doi-asserted-by":"publisher","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16000\u201316009 (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.01553","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"8_CR18","doi-asserted-by":"publisher","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9729\u20139738 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00975","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"8_CR19","doi-asserted-by":"publisher","unstructured":"Hong, T., Guo, X., Ma, J.: Itmix: image-text mix augmentation for transferring clip to image classification. In: 2022 16th IEEE International Conference on Signal Processing (ICSP), vol.\u00a01, pp. 129\u2013133. IEEE (2022). https:\/\/doi.org\/10.1109\/ICSP56322.2022.9965292","DOI":"10.1109\/ICSP56322.2022.9965292"},{"key":"8_CR20","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). https:\/\/proceedings.mlr.press\/v139\/jia21b.html"},{"key":"8_CR21","doi-asserted-by":"publisher","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). https:\/\/doi.org\/10.1109\/CVPR52729.2023.01832","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"8_CR22","unstructured":"Kong, L., et al.: Partial disentanglement for domain adaptation. In: International Conference on Machine Learning, pp. 11455\u201311472. PMLR (2022). https:\/\/proceedings.mlr.press\/v162\/kong22a.html"},{"key":"8_CR23","doi-asserted-by":"publisher","unstructured":"Li, D., Yang, Y., Song, Y.Z., Hospedales, T.M.: Deeper, broader and artier domain generalization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5542\u20135550 (2017). https:\/\/doi.org\/10.1109\/ICCV.2017.591","DOI":"10.1109\/ICCV.2017.591"},{"key":"8_CR24","unstructured":"Li, H., Wang, X., Zhang, Z., Yuan, Z., Li, H., Zhu, W.: Disentangled contrastive learning on graphs. Adv. Neural Inf. Process. Syst. 34, 21872\u201321884 (2021). https:\/\/dl.acm.org\/doi\/10.5555\/3540261.3541935"},{"key":"8_CR25","unstructured":"Li, Y., et al.: Supervision exists everywhere: a data efficient contrastive language-image pre-training paradigm. In: International Conference on Learning Representations (2021)"},{"key":"8_CR26","unstructured":"Liu, Y., et al.: Identifiable latent polynomial causal models through the lens of change. In: The Twelfth International Conference on Learning Representations (2024). https:\/\/openreview.net\/forum?id=ia9fKO1Vjq"},{"key":"8_CR27","doi-asserted-by":"publisher","unstructured":"Liu, Y., et al.: Identifying weight-variant latent causal models. arXiv preprint arXiv:2208.14153 (2022). https:\/\/doi.org\/10.48550\/arXiv.2208.14153","DOI":"10.48550\/arXiv.2208.14153"},{"key":"8_CR28","doi-asserted-by":"publisher","unstructured":"Liu, Y., et al.: Identifiable latent neural causal models. arXiv preprint arXiv:2403.15711 (2024). https:\/\/doi.org\/10.48550\/arXiv.2403.15711","DOI":"10.48550\/arXiv.2403.15711"},{"key":"8_CR29","doi-asserted-by":"publisher","unstructured":"Liu, Y., et al.: Identifying latent causal content for multi-source domain adaptation. arXiv preprint arXiv:2208.14161 (2022). https:\/\/doi.org\/10.48550\/arXiv.2208.14161","DOI":"10.48550\/arXiv.2208.14161"},{"key":"8_CR30","unstructured":"Madry, A., Makelov, A., Schmidt, L., Tsipras, D., Vladu, A.: Towards deep learning models resistant to adversarial attacks. In: International Conference on Learning Representations (2018). https:\/\/openreview.net\/forum?id=rJzIBfZAb"},{"key":"8_CR31","unstructured":"Mahajan, D., Tople, S., Sharma, A.: Domain generalization using causal matching. In: International Conference on Machine Learning, pp. 7313\u20137324. PMLR (2021). https:\/\/proceedings.mlr.press\/v139\/mahajan21b.html"},{"key":"8_CR32","unstructured":"Mamooler, S.: Clip explainability. https:\/\/github.com\/sMamooler\/CLIP_Explainability. Accessed 06 Mar 2024"},{"key":"8_CR33","unstructured":"Mao, C., Geng, S., Yang, J., Wang, X., Vondrick, C.: Understanding zero-shot adversarial robustness for large-scale models. In: The Eleventh International Conference on Learning Representations (2022). https:\/\/openreview.net\/forum?id=P4bXCawRi5J"},{"key":"8_CR34","doi-asserted-by":"publisher","unstructured":"Oord, A.V.D., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018). https:\/\/doi.org\/10.48550\/arXiv.1807.03748","DOI":"10.48550\/arXiv.1807.03748"},{"key":"8_CR35","doi-asserted-by":"publisher","unstructured":"Peng, X., Bai, Q., Xia, X., Huang, Z., Saenko, K., Wang, B.: Moment matching for multi-source domain adaptation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1406\u20131415 (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00149","DOI":"10.1109\/ICCV.2019.00149"},{"key":"8_CR36","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021). https:\/\/proceedings.mlr.press\/v139\/radford21a.html"},{"key":"8_CR37","doi-asserted-by":"publisher","unstructured":"Rahman, M.M., Fookes, C., Baktashmotlagh, M., Sridharan, S.: Multi-component image translation for deep domain generalization. In: 2019 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 579\u2013588. IEEE (2019). https:\/\/doi.org\/10.1109\/WACV.2019.00067","DOI":"10.1109\/WACV.2019.00067"},{"key":"8_CR38","unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generation. In: International Conference on Machine Learning, pp. 8821\u20138831. PMLR (2021). https:\/\/proceedings.mlr.press\/v139\/ramesh21a.html"},{"key":"8_CR39","doi-asserted-by":"publisher","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). https:\/\/doi.org\/10.1109\/CVPR52729.2023.01389","DOI":"10.1109\/CVPR52729.2023.01389"},{"key":"8_CR40","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"205","DOI":"10.1007\/978-3-030-58542-6_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"EH Sanchez","year":"2020","unstructured":"Sanchez, E.H., Serrurier, M., Ortner, M.: Learning disentangled representations via mutual information estimation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12367, pp. 205\u2013221. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58542-6_13"},{"key":"8_CR41","unstructured":"Von\u00a0K\u00fcgelgen, J., et al.: Self-supervised learning with data augmentations provably isolates content from style. Adv. Neural Inf. Processing Syst. 34, 16451\u201316467 (2021). https:\/\/dl.acm.org\/doi\/10.5555\/3540261.3541519"},{"key":"8_CR42","doi-asserted-by":"publisher","unstructured":"Wei, J., Zou, K.: Eda: easy data augmentation techniques for boosting performance on text classification tasks. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp. 6382\u20136388 (2019).https:\/\/doi.org\/10.18653\/v1\/D19-1670","DOI":"10.18653\/v1\/D19-1670"},{"key":"8_CR43","doi-asserted-by":"publisher","unstructured":"Wortsman, M., et\u00a0al.: Robust fine-tuning of zero-shot models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7959\u20137971 (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.00780","DOI":"10.1109\/CVPR52688.2022.00780"},{"key":"8_CR44","doi-asserted-by":"publisher","unstructured":"Yang, M., Liu, F., Chen, Z., Shen, X., Hao, J., Wang, J.: Causalvae: disentangled representation learning via neural structural causal models. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 9593\u20139602 (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.00947","DOI":"10.1109\/CVPR46437.2021.00947"},{"key":"8_CR45","doi-asserted-by":"publisher","unstructured":"Yang, W., Mirzasoleiman, B.: Robust contrastive language-image pretraining against adversarial attacks. arXiv preprint arXiv:2303.06854 (2023). https:\/\/doi.org\/10.48550\/arXiv.2303.06854","DOI":"10.48550\/arXiv.2303.06854"},{"key":"8_CR46","doi-asserted-by":"publisher","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: IEEE International Conference on Computer Vision (ICCV) (2023). https:\/\/doi.org\/10.1109\/ICCV51070.2023.00355","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"8_CR47","doi-asserted-by":"publisher","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). https:\/\/doi.org\/10.1109\/CVPR52688.2022.01631","DOI":"10.1109\/CVPR52688.2022.01631"},{"issue":"9","key":"8_CR48","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). https:\/\/doi.org\/10.1007\/s11263-022-01653-1","journal-title":"Int. J. Comput. Vision"},{"key":"8_CR49","unstructured":"Zimmermann, R.S., Sharma, Y., Schneider, S., Bethge, M., Brendel, W.: Contrastive learning inverts the data generating process. In: International Conference on Machine Learning, pp. 12979\u201312990. PMLR (2021). https:\/\/proceedings.mlr.press\/v139\/zimmermann21a.html"}],"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\/978-3-031-72664-4_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T13:03:42Z","timestamp":1729861422000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72664-4_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,26]]},"ISBN":["9783031726637","9783031726644"],"references-count":49,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72664-4_8","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"}}]}}