{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T16:08:17Z","timestamp":1784218097749,"version":"3.55.0"},"reference-count":68,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Research Grants Council through the Areas of Excellence scheme","award":["AoE\/E-601\/22-R"],"award-info":[{"award-number":["AoE\/E-601\/22-R"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,11]]},"DOI":"10.1109\/tpami.2025.3594097","type":"journal-article","created":{"date-parts":[[2025,8,11]],"date-time":"2025-08-11T17:43:12Z","timestamp":1754934192000},"page":"10836-10847","source":"Crossref","is-referenced-by-count":1,"title":["VLPose: Bridging the Domain Gap in Pose Estimation With Language-Vision Tuning"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5121-1153","authenticated-orcid":false,"given":"Jingyao","family":"Li","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, The Chinese University of Hong Kong (CUHK), Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1746-5127","authenticated-orcid":false,"given":"Pengguang","family":"Chen","sequence":"additional","affiliation":[{"name":"SmartMore, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuan","family":"Ju","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, The Chinese University of Hong Kong (CUHK), Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2903-9270","authenticated-orcid":false,"given":"Shu","family":"Liu","sequence":"additional","affiliation":[{"name":"SmartMore, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9359-9571","authenticated-orcid":false,"given":"Hong","family":"Xu","sequence":"additional","affiliation":[{"name":"Associate Professor from Department of Computer Science and Engineering, The Chinese University of Hong Kong (CUHK), Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1246-553X","authenticated-orcid":false,"given":"Jiaya","family":"Jia","sequence":"additional","affiliation":[{"name":"SmartMore, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3524497"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.248"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01112"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00484"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_17"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3550454.3555437"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00746"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/646"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392462"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14426"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00535"},{"key":"ref13","first-page":"38 571","article-title":"ViTPose: Simple vision transformer baselines for human pose estimation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xu"},{"key":"ref14","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Brown"},{"key":"ref15","article-title":"GPT-4 technical report","year":"2023"},{"key":"ref16","article-title":"Visual instruction tuning","author":"Liu","year":"2023"},{"key":"ref17","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023"},{"key":"ref18","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00915"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00542"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.471"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01842-6"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2019.00256"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00098"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530106"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3569089"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46604-0_57"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00067"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_12"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01084"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00257"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/icme.2019.00256"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00198"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01112"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01159"},{"key":"ref37","article-title":"AP-10K: A benchmark for animal pose estimation in the wild","author":"Yu","year":"2021"},{"key":"ref38","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"ref39","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","author":"Jia","year":"2021"},{"key":"ref40","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-58577-8_7","article-title":"Uniter: Universal image-text representation learning","author":"Chen","year":"2020"},{"key":"ref41","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-58577-8_8","article-title":"Oscar: Object-semantics aligned pre-training for vision-language tasks","author":"Li","year":"2020"},{"key":"ref42","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/D19-1514","article-title":"LXMERT: Learning cross-modality encoder representations from transformers","author":"Tan","year":"2019"},{"key":"ref43","article-title":"ViLT: Vision-and-language transformer without convolution or region supervision","author":"Kim","year":"2021"},{"key":"ref44","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","author":"Li","year":"2022"},{"key":"ref45","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52688.2022.01522","article-title":"Vision-language pre-training with triple contrastive learning","author":"Yang","year":"2022"},{"key":"ref46","article-title":"ActionCLIP: A new paradigm for video action recognition","author":"Wang","year":"2021"},{"key":"ref47","doi-asserted-by":"crossref","DOI":"10.1145\/3503161.3547910","article-title":"X-CLIP: End-to-end multi-grained contrastive learning for video-text retrieval","author":"Ma","year":"2022"},{"key":"ref48","article-title":"FitCLIP: Refining large-scale pretrained image-text models for zero-shot video understanding tasks","author":"Castro","year":"2022"},{"key":"ref49","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-19833-5_7","article-title":"Prompting visual-language models for efficient video understanding","author":"Ju","year":"2022"},{"key":"ref50","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52729.2023.00633","article-title":"Fine-tuned CLIP models are efficient video learners","author":"Rasheed","year":"2023"},{"key":"ref51","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v37i3.25386","article-title":"Revisiting classifier: Transferring vision-language models for video recognition","author":"Wu","year":"2023"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01784"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref54","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","author":"Li","year":"2021"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref56","article-title":"SegViT: Semantic segmentation with plain vision transformers","author":"Zhang","year":"2022"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045167"},{"key":"ref58","article-title":"Deep learning using rectified linear units (ReLU)","author":"Agarap","year":"2018"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3039359"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_29"},{"key":"ref61","article-title":"Vision transformer adapter for dense predictions","author":"Chen","year":"2023"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0274-8"},{"key":"ref65","article-title":"On the convergence of adam and beyond","author":"Reddi","year":"2019"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00574"},{"key":"ref67","first-page":"5753","article-title":"XLNet: Generalized autoregressive pretraining for language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref68","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11192800\/11122431.pdf?arnumber=11122431","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T17:37:18Z","timestamp":1759772238000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11122431\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11]]},"references-count":68,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3594097","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":[[2025,11]]}}}