{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T20:55:03Z","timestamp":1775681703595,"version":"3.50.1"},"reference-count":94,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001459","name":"Ministry of Education - Singapore","doi-asserted-by":"publisher","award":["EDUNC-33-18-279-V12"],"award-info":[{"award-number":["EDUNC-33-18-279-V12"]}],"id":[{"id":"10.13039\/501100001459","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62476048"],"award-info":[{"award-number":["62476048"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001381","name":"National Research Foundation Singapore","doi-asserted-by":"publisher","award":["AISG2-PhD-2022-01-027"],"award-info":[{"award-number":["AISG2-PhD-2022-01-027"]}],"id":[{"id":"10.13039\/501100001381","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1109\/tpami.2026.3651728","type":"journal-article","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:00:30Z","timestamp":1768255230000},"page":"5195-5211","source":"Crossref","is-referenced-by-count":0,"title":["Unleashing the Power of Text-to-Image Diffusion Models for Category-Agnostic Pose Estimation"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3281-0772","authenticated-orcid":false,"given":"Duo","family":"Peng","sequence":"first","affiliation":[{"name":"Institute for Digital Molecular Analytics and Science, Nanyang Technological University, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengbo","family":"Zhang","sequence":"additional","affiliation":[{"name":"Singapore University of Technology and Design, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3321-6759","authenticated-orcid":false,"given":"Ping","family":"Hu","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, Sichuan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9998-3614","authenticated-orcid":false,"given":"Qiuhong","family":"Ke","sequence":"additional","affiliation":[{"name":"Monash University, Clayton, Victoria, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6490-6467","authenticated-orcid":false,"given":"De Wen","family":"Soh","sequence":"additional","affiliation":[{"name":"Singapore University of Technology and Design, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6603-3257","authenticated-orcid":false,"given":"Mohammed","family":"Bennamoun","sequence":"additional","affiliation":[{"name":"University of Western Australia, Crawley, Western Australia, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4365-4165","authenticated-orcid":false,"given":"Jun","family":"Liu","sequence":"additional","affiliation":[{"name":"Lancaster University, Lancaster, Lancashire, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2018.8451559"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00427"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3390\/electronics11213551"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-48881-3_20"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7532564"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00584"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01145"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20068-7_23"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.5555\/3294996.3295163"},{"key":"ref11","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Finn","year":"2017"},{"key":"ref12","article-title":"Revisiting fine-tuning for few-shot learning","author":"Nakamura","year":"2019"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00706"},{"key":"ref14","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":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123326"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3381347"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2729019"},{"key":"ref18","first-page":"16784","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","volume":"162","author":"Nichol","year":"2022"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref20","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.13"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72624-8_20"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.214"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298598"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2789887"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_44"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.116"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00156"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.446"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.525"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00878"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01109"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00750"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2021.3078619"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3010307"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00603"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_29"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00707"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01080"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10605-2_3"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00120"},{"key":"ref44","first-page":"13153","article-title":"Direct multi-view multi-person 3D pose estimation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Zhang","year":"2021"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73036-8_27"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73036-8_27"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73337-6_27"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02148"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"ref51","first-page":"1363","article-title":"Emergent correspondence from image diffusion","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Tang","year":"2023"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICOIN56518.2023.10049010"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3359"},{"key":"ref55","article-title":"iSeg: An iterative refinement-based framework for training-free segmentation","author":"Sun","year":"2024"},{"key":"ref56","article-title":"SLiMe: Segment like me","author":"Khani","year":"2023"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1250"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00324"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.346"},{"key":"ref60","article-title":"Bert is not a knowledge base (yet): Factual knowledge vs. Name-Based Reasoning in Unsupervised QA","author":"Poerner","year":"1911","journal-title":"CoRR"},{"key":"ref61","article-title":"How context affects language models\u2019 factual predictions","author":"Petroni","year":"2020"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref64","article-title":"Unified vision and language prompt learning","author":"Zang","year":"2022"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01436"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00653"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33786-4_2"},{"key":"ref68","article-title":"Prompt-to-prompt image editing with cross attention control","author":"Hertz","year":"2022"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/3592116"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2016.01.002"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2011.6130513"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2879980"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00548"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.3389\/fnbeh.2020.581154"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-018-0234-5"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.47994"},{"key":"ref77","article-title":"SPair-71 k: A large-scale benchmark for semantic correspondence","author":"Min","year":"2019"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.261"},{"key":"ref79","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201332"},{"key":"ref81","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Caron","year":"2020"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00382"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.12"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_22"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00629"},{"key":"ref86","article-title":"Deep ViT features as dense visual descriptors","author":"Amir","year":"2021"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01018"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1973"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2724510"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.460"},{"key":"ref91","article-title":"ExpansionNet v2: Block static expansion in fast end to end training for image captioning","author":"Hu","year":"2022"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref93","article-title":"Openjourney","year":"2023"},{"key":"ref94","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ramesh","year":"2021"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11474534\/11342303.pdf?arnumber=11342303","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T20:05:50Z","timestamp":1775678750000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11342303\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":94,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3651728","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":[[2026,5]]}}}