{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T17:43:43Z","timestamp":1778694223061,"version":"3.51.4"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"UAE University Startup Research","award":["12T095"],"award-info":[{"award-number":["12T095"]}]},{"name":"UAE University Startup Research","award":["G00005050"],"award-info":[{"award-number":["G00005050"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Open J. Comput. Soc."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/ojcs.2026.3654171","type":"journal-article","created":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T20:52:39Z","timestamp":1768510359000},"page":"365-375","source":"Crossref","is-referenced-by-count":1,"title":["AG-CLIP: Attribute-Guided CLIP for Zero-Shot Fine-Grained Recognition"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8407-5971","authenticated-orcid":false,"given":"Jamil","family":"Ahmad","sequence":"first","affiliation":[{"name":"Department of Computer Science and Software Engineering, United Arab Emirates University (UAEU), Abu Dhabi, UAE"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mustaqeem","family":"Khan","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Software Engineering, United Arab Emirates University (UAEU), Abu Dhabi, UAE"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6490-4648","authenticated-orcid":false,"given":"Wail","family":"Guiaeab","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering and Computer Science, University of Ottawa, Ottawa, ON, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7690-8547","authenticated-orcid":false,"given":"Abdulmotaleb","family":"Elsaddik","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering and Computer Science, University of Ottawa, Ottawa, ON, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3284-880X","authenticated-orcid":false,"given":"Giulia","family":"De Masi","sequence":"additional","affiliation":[{"name":"SAFIR, Sorbonne University, Abu Dhabi, UAE"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4217-1372","authenticated-orcid":false,"given":"Fakhri","family":"Karray","sequence":"additional","affiliation":[{"name":"Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI), Abu Dhabi, UAE"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447207"},{"key":"ref2","first-page":"3032","article-title":"Improving zero-shot generalization for clip with synthesized prompts","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","author":"Wang","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2025.128946"},{"key":"ref4","article-title":"Fine-grained zero-shot learning: Advances, challenges, and prospects","author":"Guo","year":"2024"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3295772"},{"key":"ref6","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/OJCS.2025.3568044"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00746"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19909"},{"key":"ref10","first-page":"26342","article-title":"CHiLS: Zero-shot image classification with hierarchical label sets","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Novack","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/OJCS.2025.3525560"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/597"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/jproc.2023.3279374"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/OJCS.2025.3564493"},{"key":"ref15","first-page":"2121","article-title":"DeViSE: A deep visual-semantic embedding model","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Frome","year":"2013"},{"key":"ref16","first-page":"16622","article-title":"HSVA: Hierarchical semantic-visual adaptation for zero-shot learning","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst.","author":"Chen","year":"2021"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00019"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3450042"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00101"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-45654-6"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3460426.3463592"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3191696"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_33"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00379"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref26","first-page":"12283","article-title":"I2DFormer: Learning image to document attention for zero-shot image classification","volume-title":"Proc. Adv. Neural Informat. Process. Syst.","author":"Naeem","year":"2022"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00260"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01058"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27955"},{"key":"ref30","first-page":"27896","article-title":"FineCLIP: Self-distilled region-based CLIP for better fine-grained understanding","volume-title":"Proc. Workshop Vis.- Lang. Models","author":"Jing","year":"2024"},{"key":"ref31","article-title":"Focusclip: Multimodal subject-level guidance for zero-shot transfer in human-centric tasks","author":"Khan","year":"2024"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01438"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP51287.2024.10648166"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01438"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01460"},{"key":"ref36","article-title":"Rethinking the openness of clip","author":"Ren","year":"2022"},{"key":"ref37","first-page":"1","article-title":"Questioning, answering, and captioning for zero-shot detailed image captioning","volume-title":"Proc. Workshop Vis.- Lang. Models","author":"Luu","year":"2024"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00680"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2305016120"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-48044-7_26"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.54"},{"key":"ref42","article-title":"RTGen: Generating region-text pairs for open-vocabulary object detection","author":"Chen","year":"2024"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_42"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25114"},{"key":"ref45","article-title":"The caltech-ucsd birds-200-2011 dataset","author":"Wah","year":"2011"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3263042"},{"key":"ref47","article-title":"Accessible large-scale plant pathology recognition","volume-title":"Proc. NeurIPS 2022 Workshop Tackling Climate Change Mach. Learn.","author":"Conde","year":"2022"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.dib.2022.108174"},{"key":"ref49","article-title":"iBean","year":"2020"},{"key":"ref50","first-page":"21969","article-title":"Attribute prototype network for zero-shot learning","volume-title":"Proc. 34th Int. Conf. Neural Informat. Process. Syst.","author":"Xu","year":"2020"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01472"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00680"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00581"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01052"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01405"},{"key":"ref56","first-page":"19849","article-title":"Compositional zero-shot learning via fine-grained dense feature composition","volume-title":"Proc. 34th Int. Conf. Neural Informat. Process. Syst.","author":"Huynh","year":"2020"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01515"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00019"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00909"},{"key":"ref60","first-page":"2121","article-title":"DeViSE: A deep visual-semantic embedding model","volume-title":"Proc. Adv. Neural Informat. Process. Syst.","author":"Frome","year":"2013"},{"key":"ref61","first-page":"2009","article-title":"Generalized zero-shot learning with deep calibration network","volume-title":"Proc. Adv. Neural Informat. Process. Syst.","author":"Liu","year":"2018"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00844"},{"key":"ref63","first-page":"46","article-title":"Zero-shot learning via simultaneous generating and learning","volume-title":"Proc. Adv. Neural Informat. Process. Syst.","author":"Yu","year":"2019"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00115"},{"key":"ref65","first-page":"14943","article-title":"Semantic-guided multi-attention localization for zero-shot learning","volume-title":"Proc. Adv. Neural Informat. Process. Syst.","author":"Zhu","year":"2019"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00961"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00454"}],"container-title":["IEEE Open Journal of the Computer Society"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8782664\/11319293\/11352798.pdf?arnumber=11352798","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T09:42:25Z","timestamp":1769679745000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11352798\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":67,"URL":"https:\/\/doi.org\/10.1109\/ojcs.2026.3654171","relation":{},"ISSN":["2644-1268"],"issn-type":[{"value":"2644-1268","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}