{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,11]],"date-time":"2026-01-11T05:36:38Z","timestamp":1768109798539,"version":"3.49.0"},"reference-count":54,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001348","name":"Agency for Science, Technology and Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001348","id-type":"DOI","asserted-by":"publisher"}]},{"name":"AME Programmatic Funding Scheme","award":["A20H4b0141"],"award-info":[{"award-number":["A20H4b0141"]}]},{"name":"National Research Foundation (NRF) Singapore"},{"name":"AI Singapore Programme AISG","award":["AISG2-TC-2021-003"],"award-info":[{"award-number":["AISG2-TC-2021-003"]}]},{"DOI":"10.13039\/501100001348","name":"Agency for Science, Technology and Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001348","id-type":"DOI","asserted-by":"publisher"}]},{"name":"RIE2020 Health and Biomedical Sciences"},{"name":"Industry Alignment Fund Pre-Positioning","award":["H20C6a0032"],"award-info":[{"award-number":["H20C6a0032"]}]},{"name":"A*STAR Central Research Fund"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,9]]},"DOI":"10.1109\/tpami.2025.3573852","type":"journal-article","created":{"date-parts":[[2025,5,26]],"date-time":"2025-05-26T13:57:41Z","timestamp":1748267861000},"page":"7660-7674","source":"Crossref","is-referenced-by-count":1,"title":["Text to Image for Multi-Label Image Recognition With Joint Prompt-Adapter Learning"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3025-8964","authenticated-orcid":false,"given":"Chun-Mei","family":"Feng","sequence":"first","affiliation":[{"name":"Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR), Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6752-6216","authenticated-orcid":false,"given":"Kai","family":"Yu","sequence":"additional","affiliation":[{"name":"Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR), Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1449-3072","authenticated-orcid":false,"given":"Xinxing","family":"Xu","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9502-1749","authenticated-orcid":false,"given":"Salman","family":"Khan","sequence":"additional","affiliation":[{"name":"Mohamed bin Zayed University of Artificial Intelligence (MBZUAI), Abu Dhabi, UAE"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9116-1595","authenticated-orcid":false,"given":"Rick Siow Mong","family":"Goh","sequence":"additional","affiliation":[{"name":"Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR), Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3330-783X","authenticated-orcid":false,"given":"Wangmeng","family":"Zuo","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Harbin, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1590-2029","authenticated-orcid":false,"given":"Yong","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR), Singapore"}]}],"member":"263","reference":[{"key":"ref1","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Alayrac"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00671"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19910"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12281"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00061"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00532"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00821"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/1646396.1646452"},{"key":"ref9","article-title":"Variational prompt tuning improves generalization of vision-language models","author":"Derakhshani","year":"2022"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00074"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref12","article-title":"Deep convolutional ranking for multilabel image annotation","author":"Gong","year":"2013"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref14","article-title":"I can\u2019t believe there\u2019s no images! learning visual tasks using only language data","author":"Gu","year":"2022"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00275"},{"key":"ref16","article-title":"Imagen video: High definition video generation with diffusion models","author":"Ho","year":"2022"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3545772"},{"key":"ref18","article-title":"Enhancing CLIP conceptual embedding through knowledge distillation","author":"Kao","year":"2024"},{"key":"ref19","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref20","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013"},{"key":"ref21","article-title":"OpenImages: A public dataset for large-scale multi-label and multi-class image classification","author":"Krasin","year":"2017"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_26"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240567"},{"key":"ref25","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00861"},{"key":"ref28","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2021"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.299"},{"key":"ref30","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20105"},{"key":"ref32","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref33","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61041.2025.00572"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.02155"},{"key":"ref37","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Saharia"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00042"},{"key":"ref39","first-page":"12533","article-title":"D2C: Diffusion-decoding models for few-shot conditional generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sinha"},{"key":"ref40","article-title":"DualCoOp: Fast adaptation to multi-label recognition with limited annotations","author":"Sun","year":"2022"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00516"},{"key":"ref42","article-title":"LLaMa: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref43","article-title":"Learning to decompose visual features with latent textual prompts","author":"Wang","year":"2022"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.251"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2612829"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6909"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.58"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/578"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01345"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_29"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00023"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01435"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11118328\/11015803.pdf?arnumber=11015803","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T17:44:22Z","timestamp":1754588662000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11015803\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9]]},"references-count":54,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3573852","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9]]}}}