{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,10]],"date-time":"2026-10-10T16:05:29Z","timestamp":1791648329945,"version":"4.3.4"},"reference-count":69,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00091","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"890-900","source":"Crossref","is-referenced-by-count":4,"title":["Causal Disentanglement and Cross-Modal Alignment for Enhanced Few-Shot Learning"],"prefix":"10.1109","author":[{"given":"Tianjiao","family":"Jiang","sequence":"first","affiliation":[{"name":"Australian Institute for Machine Learning, The University of Adelaide,Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhen","family":"Zhang","sequence":"additional","affiliation":[{"name":"Australian Institute for Machine Learning, The University of Adelaide,Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuhang","family":"Liu","sequence":"additional","affiliation":[{"name":"Australian Institute for Machine Learning, The University of Adelaide,Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Javen Qinfeng","family":"Shi","sequence":"additional","affiliation":[{"name":"Australian Institute for Machine Learning, The University of Adelaide,Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Learning to learn by gradient descent by gradient descent","author":"Andrychowicz","year":"2016","journal-title":"Advances in neural information processing systems, 29"},{"key":"ref2","article-title":"Exploring visual prompts for adapting largescale models","author":"Bahng","year":"2022","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref4","first-page":"108","article-title":"API design for machine learning software: experiences from the scikit-learn project","volume-title":"ECML PKDD Workshop: Languages for Data Mining and Machine Learning","author":"Buitinck","year":"2013"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72664-4_8"},{"key":"ref6","article-title":"On the value of cross-modal misalignment in multimodal representation learning","author":"Cai","year":"2025","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00893"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"ref11","article-title":"Identifiability re-sults for multimodal contrastive learning","author":"Daunhawer","year":"2023","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.383"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref16","article-title":"Explaining and harnessing adversarial examples","author":"Goodfellow","year":"2014","journal-title":"arXiv preprint"},{"key":"ref17","first-page":"217","article-title":"The incomplete rosetta stone problem: Identifiability results for multiview nonlinear ica","author":"Gresele","year":"2020","journal-title":"Uncertainty in Artificial Intelligence"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2918242"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02244"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-97982-3_16"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS.1999.777510"},{"key":"ref23","first-page":"859","article-title":"Nonlinear ica using auxiliary variables and generalized contrastive learning","volume-title":"The 22nd International Conference on Artificial Intelligence and Statistics","author":"Hyvarinen","year":"2019"},{"key":"ref24","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"International conference on machine learning","author":"Jia","year":"2021"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"ref27","first-page":"2207","article-title":"Variational autoencoders and nonlinear ica: A unifying framework","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Khemakhem","year":"2020"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref29","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International conference on machine learning","author":"Li","year":"2022"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01852"},{"key":"ref31","article-title":"Identifying weight-variant latent causal models","author":"Liu","year":"2022","journal-title":"arXiv preprint"},{"key":"ref32","article-title":"Identifiable latent neural causal models","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref33","article-title":"Identifiable latent polynomial causal models through the lens of change","volume-title":"The Twelfth International Conference on Learning Representations","author":"Liu","year":"2024"},{"key":"ref34","article-title":"Revealing multimodal contrastive representation learning through latent partial causal models","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref35","article-title":"I predict therefore i am: Is next token prediction enough to learn human-interpretable concepts from data?","author":"Liu","year":"2025","journal-title":"arXiv preprint"},{"key":"ref36","article-title":"Latent covariate shift: Unlocking partial identifiability for multi-source domain adaptation","author":"Liu","year":"2025","journal-title":"Transactions on Machine Learning Research"},{"key":"ref37","article-title":"Fine-grained visual classification of aircraft","author":"Maji","year":"2013","journal-title":"arXiv preprint"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02722"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01438"},{"key":"ref42","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref43","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"International conference on machine learning","author":"Ramesh","year":"2021"},{"key":"ref44","first-page":"5389","article-title":"Do imagenet classifiers generalize to imagenet?","volume-title":"International conference on machine learning","author":"Recht","year":"2019"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02693"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i11.17155"},{"key":"ref48","article-title":"Prototypical networks for few-shot learning","author":"Snell","year":"2017","journal-title":"arXiv preprint"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1888"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00049"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00131"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02201"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00257"},{"key":"ref55","article-title":"Matching networks for one shot learning","author":"Vinyals","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref56","first-page":"10506","article-title":"Learning robust global representations by penalizing local predictive power","author":"Wang","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3386252"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01049"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01287"},{"key":"ref61","article-title":"Unified vision and language prompt learning","author":"Zang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_29"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01460"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02713"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01435"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00246"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445365.pdf?arnumber=11445365","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:31:59Z","timestamp":1777613519000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445365\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":69,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00091","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}