{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T19:59:58Z","timestamp":1780516798790,"version":"3.54.1"},"reference-count":57,"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\/iccv51701.2025.00052","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"478-487","source":"Crossref","is-referenced-by-count":2,"title":["Interpretable Zero-Shot Learning with Locally-Aligned Vision-Language Model"],"prefix":"10.1109","author":[{"given":"Shiming","family":"Chen","sequence":"first","affiliation":[{"name":"Mohamed bin Zayed University of AI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bowen","family":"Duan","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Salman","family":"Khan","sequence":"additional","affiliation":[{"name":"Mohamed bin Zayed University of AI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fahad Shahbaz","family":"Khan","sequence":"additional","affiliation":[{"name":"Mohamed bin Zayed University of AI"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2487986"},{"key":"ref2","first-page":"214","article-title":"Wasserstein generative adversarial networks","author":"Arjovsky","year":"2017","journal-title":"ICML"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref4","article-title":"PLOT: prompt learning with optimal transport for vision-language models","author":"Chen","year":"2023","journal-title":"ICLR"},{"key":"ref5","article-title":"Hsva: Hierarchical semantic-visual adaptation for zero-shot learning","author":"Chen","year":"2021","journal-title":"NeurIPS"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00746"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3229526"},{"key":"ref8","article-title":"Evolving semantic prototype improves generative zero-shot learning","author":"Chen","year":"2023","journal-title":"ICML"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02262"},{"key":"ref10","author":"Chen","year":"2025","journal-title":"Genzsl: Generative zero-shot learning via inductive variational autoencoder"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-025-02394-7"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73039-9_11"},{"key":"ref13","first-page":"2292","article-title":"Sinkhorn distances: Lightspeed computation of optimal transport","author":"Cuturi","year":"2013","journal-title":"NeurIPS"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref15","article-title":"Image2sentence based asymmetrical zero-shot composed image retrieval","author":"Du","year":"2024","journal-title":"ICLR"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1544"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00255"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00454"},{"key":"ref22","first-page":"49044916","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","author":"Jia","year":"2021","journal-title":"ICML"},{"key":"ref23","article-title":"Multimodal classifiers for open-vocabulary object detection","author":"Kaul","year":"2023","journal-title":"ICML"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01029"},{"key":"ref26","first-page":"1955","article-title":"Co-clustering through optimal transport","author":"Laclau","year":"2017","journal-title":"ICML"},{"key":"ref27","article-title":"Visual-text cross alignment: Refining the similarity score in vision-language models","author":"Li","year":"2024","journal-title":"ICML"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01408"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01472"},{"key":"ref30","article-title":"Visual classification via description from large language models","author":"Menon","year":"2023","journal-title":"ICLR"},{"key":"ref31","article-title":"Robust calibration of large visionlanguage adapters","author":"Murugesan","year":"2024","journal-title":"ECCV"},{"key":"ref32","first-page":"147","article-title":"Robust calibration of large visionlanguage adapters","author":"Murugesan","year":"2024","journal-title":"E C C V"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02053-3"},{"key":"ref34","first-page":"1410","article-title":"Zero-shot learning with semantic output codes","author":"Palatucci","year":"2009","journal-title":"NeurIPS"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1561\/9781680835519"},{"key":"ref37","first-page":"15645","article-title":"What does a platypus look like? generating customized prompts for zeroshot image classification","author":"Pratt","year":"2022","journal-title":"ICCV"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01438"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02341"},{"key":"ref40","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref41","first-page":"5389","article-title":"Do imagenet classifiers generalize to imagenet?","author":"Recht","year":"2019","journal-title":"ICML"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01443"},{"key":"ref43","first-page":"8247","article-title":"Generalized zero- and fewshot learning via aligned variational autoencoders","author":"Sch\u00f6nfeld","year":"2019","journal-title":"CVPR"},{"key":"ref44","article-title":"Testtime prompt tuning for zero-shot generalization in visionlanguage models","author":"Shu","year":"2022","journal-title":"NeurIPS"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00320"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02700"},{"key":"ref47","article-title":"Tuning multi-mode tokenlevel prompt alignment across modalities","author":"Wang","year":"2023","journal-title":"NeurIPS"},{"key":"ref48","first-page":"10506","article-title":"Learning robust global representations by penalizing local predictive power","author":"Wang","year":"2019","journal-title":"NeurIPS"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-017-1027-5"},{"key":"ref50","article-title":"Caltech-ucsd birds 200","volume-title":"Technical Report CNS-TR-2010\u2013001","author":"Welinder","year":"2010"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.328"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00581"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00339"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2723009"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01435"}],"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\/11444061.pdf?arnumber=11444061","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:59:26Z","timestamp":1777611566000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444061\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00052","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}