{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:01:24Z","timestamp":1777888884408,"version":"3.51.4"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00790","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"8441-8450","source":"Crossref","is-referenced-by-count":0,"title":["Towards Annotation-Free Evaluation: KPAScore for Human Keypoint Detection"],"prefix":"10.1109","author":[{"given":"Xiaoxiao","family":"Wang","sequence":"first","affiliation":[{"name":"University of Chinese Academy of Sciences,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunxiao","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing Normal University,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Sun","sequence":"additional","affiliation":[{"name":"Central University of Finance and Economics,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Boming","family":"Miao","sequence":"additional","affiliation":[{"name":"Beijing Normal University,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunjian","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yao","family":"Zhu","sequence":"additional","affiliation":[{"name":"Zhejiang University,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.471"},{"issue":"3","key":"ref2","first-page":"8","article-title":"Improving image generation with better captions","volume":"2","author":"Betker","year":"2023","journal-title":"Computer Science"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_27"},{"key":"ref4","article-title":"Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks","author":"Chen","year":"2023","journal-title":"arxiv preprint arxiv"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01286"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3222784"},{"key":"ref7","volume-title":"Chatglm: A family of large language models from glm-130b to glm-4 all tools","author":"Glm","year":"2024"},{"key":"ref8","volume-title":"Deepseek-coder: When the large language model meets programming - the rise of code intelligence","author":"Guo","year":"2024"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.70675\/802872a7z8092z4556za1fdz2c7af45f0e72"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.248"},{"key":"ref12","volume-title":"Rtmpose: Real-time multi-person pose estimation based on mmpose","author":"Jiang","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref14","volume-title":"Llava-onevision: Easy visual task transfer","author":"Li","year":"2024"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73195-2_27"},{"key":"ref16","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International conference on machine learning","author":"Li","year":"2022"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72673-6_20"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref20","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00584"},{"key":"ref23","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arxiv preprint arxiv"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00065"},{"key":"ref25","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.511"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2795"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.261"},{"key":"ref29","article-title":"Minicpm-v: A gpt-4v level mllm on your phone","author":"Yao","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01030"},{"key":"ref31","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arxiv preprint arxiv"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3652583.3658032"},{"key":"ref33","article-title":"Segment everything everywhere all at once","volume":"36","author":"Zou","year":"2024","journal-title":"Advances in Neural Information Processing Systems"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445433.pdf?arnumber=11445433","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:01:20Z","timestamp":1777611680000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445433\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00790","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}