{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T20:57:32Z","timestamp":1767646652223,"version":"3.48.0"},"reference-count":93,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Hong Kong SAR Research Grants Council (RGC) Early Career Scheme","award":["26208924"],"award-info":[{"award-number":["26208924"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62222207"],"award-info":[{"award-number":["62222207"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62172226"],"award-info":[{"award-number":["62172226"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62472208"],"award-info":[{"award-number":["62472208"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62427808"],"award-info":[{"award-number":["62427808"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Natural Science Foundation of China Young Scholar Fund","award":["62402408"],"award-info":[{"award-number":["62402408"]}]},{"name":"Hong Kong University of Science and Technology (HKUST) Sports Science and Technology Research","award":["SSTRG24EG04"],"award-info":[{"award-number":["SSTRG24EG04"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1109\/tcsvt.2025.3585888","type":"journal-article","created":{"date-parts":[[2025,7,4]],"date-time":"2025-07-04T13:52:43Z","timestamp":1751637163000},"page":"11863-11876","source":"Crossref","is-referenced-by-count":0,"title":["Eliminating Semantic Ambiguity in Human Pose Estimation via Stable Feature Upsampling"],"prefix":"10.1109","volume":"35","author":[{"given":"Shu","family":"Jiang","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4543-2179","authenticated-orcid":false,"given":"Dong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0694-9458","authenticated-orcid":false,"given":"Rui","family":"Yan","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4902-4663","authenticated-orcid":false,"given":"Xiangbo","family":"Shu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3975-286X","authenticated-orcid":false,"given":"Pingcheng","family":"Dong","sequence":"additional","affiliation":[{"name":"Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6148-9709","authenticated-orcid":false,"given":"Long","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4641-1994","authenticated-orcid":false,"given":"Xiaoyu","family":"Du","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.471"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_12"},{"key":"ref3","first-page":"655","article-title":"Causal intervention for weakly-supervised semantic segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Zhang"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00235"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858819"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019251"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3603618"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01594-9"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3542945"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3377325.3377505"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_20"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01928-1"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3084827"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3086142"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3238642"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3197352"},{"key":"ref17","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547858"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3153044"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3005522"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3215564"},{"key":"ref22","article-title":"A review on deep learning techniques applied to semantic segmentation","author":"Garcia-Garcia","year":"2017","journal-title":"arXiv:1704.06857"},{"article-title":"Deep learning for medical image segmentation: Tricks, challenges and future directions","year":"2022","author":"Zhang","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108594"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00584"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-021-3590-1"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-34372-9"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2893965"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01485"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.214"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3390\/computers8020030"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2010.2050108"},{"key":"ref33","article-title":"Attention-based image upsampling","author":"Kundu","year":"2020","journal-title":"arXiv:2012.09904"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.10.007"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-023-14877-1"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01611"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_29"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.207"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00310"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00167"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00324"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/0304-3991(81)90061-9"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1137\/0717021"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126474"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01142"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3074370"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_28"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00336"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3004474"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00677"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_14"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02191-8"},{"key":"ref54","first-page":"1","article-title":"SAPA: Similarity-aware point affiliation for feature upsampling","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Lu"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00554"},{"key":"ref56","first-page":"1","article-title":"FeatUp: A model-agnostic framework for features at any resolution","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Fu"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.533"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2929257"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00543"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref61","first-page":"1","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Ren"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref63","article-title":"RTMDet: An empirical study of designing real-time object detectors","author":"Lyu","year":"2022","journal-title":"arXiv:2212.07784"},{"key":"ref64","article-title":"HRFormer: High-resolution transformer for dense prediction","author":"Yuan","year":"2021","journal-title":"arXiv:2110.09408"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3222784"},{"key":"ref67","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Touvron"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref69","first-page":"38571","article-title":"ViTPose: Simple vision transformer baselines for human pose estimation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Xu"},{"key":"ref70","article-title":"RTMPose: Real-time multi-person pose estimation based on MMPose","author":"Jiang","year":"2023","journal-title":"arXiv:2303.07399"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20068-7_6"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00455"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00708"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2021.104285"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110955"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2023.111200"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.102033"},{"key":"ref79","first-page":"1114","article-title":"HUM3DIL: Semi-supervised multi-modal 3D humanpose estimation for autonomous driving","volume-title":"Proc. 6th Conf. Robot Learn.","author":"Zanfir"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.5555\/3104322.3104425"},{"key":"ref81","article-title":"Rigid-motion scattering for texture classification","author":"Sifre","year":"2014","journal-title":"arXiv:1403.1687"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01587"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref84","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"article-title":"MMPose contributors. OpenMMLab pose estimation tool-box and benchmark","year":"2020","author":"Contributors","key":"ref85"},{"key":"ref86","first-page":"1","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Paszke"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2956516"},{"key":"ref89","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref90","first-page":"1","article-title":"Associative embedding: End-to-end learning for joint detection and grouping","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Newell"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"article-title":"Vitpose+: Vision transformer foundation model for generic body pose estimation","year":"2022","author":"Xu","key":"ref93"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11278843\/11071896.pdf?arnumber=11071896","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T18:41:10Z","timestamp":1767638470000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11071896\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":93,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3585888","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"type":"print","value":"1051-8215"},{"type":"electronic","value":"1558-2205"}],"subject":[],"published":{"date-parts":[[2025,12]]}}}