{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T03:22:57Z","timestamp":1774495377744,"version":"3.50.1"},"reference-count":59,"publisher":"Association for Computing Machinery (ACM)","issue":"2s","license":[{"start":{"date-parts":[[2022,6,30]],"date-time":"2022-06-30T00:00:00Z","timestamp":1656547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Multimedia Comput. Commun. Appl."],"published-print":{"date-parts":[[2022,6,30]]},"abstract":"<jats:p>\n            Multi-frame human pose estimation is at the core of many computer vision tasks. Although state-of-the-art approaches have demonstrated remarkable results for human pose estimation on static images, their performances inevitably come short when being applied to videos. A central issue lies in the visual degeneration of video frames induced by rapid motion and pose occlusion in dynamic environments. This problem, by nature, is insurmountable for a single frame. Therefore, incorporating complementary visual cues from other video frames becomes an intuitive paradigm. Current state-of-the-art methods usually leverage information from adjacent frames, which unfortunately place excessive focus on only the temporally nearby frames. In this paper, we argue that combining global semantically similar information and local temporal visual context will deliver more comprehensive and more robust representations for human pose estimation. Towards this end, we present an effective framework, namely\n            <jats:bold>global-local enhanced pose estimation<\/jats:bold>\n            (\n            <jats:bold>GLPose<\/jats:bold>\n            ) network. Our framework consists of a feature processing module that conditionally incorporates global semantic information and local visual context to generate a robust human representation and a feature enhancement module that excavates complementary information from this aggregated representation to enhance keyframe features for precise estimation. We empirically find that the proposed GLpose outperforms existing methods by a large margin and achieves new state-of-the-art results on large benchmark datasets.\n          <\/jats:p>","DOI":"10.1145\/3519305","type":"journal-article","created":{"date-parts":[[2022,3,12]],"date-time":"2022-03-12T11:50:20Z","timestamp":1647085820000},"page":"1-16","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["GLPose: Global-Local Representation Learning for Human Pose Estimation"],"prefix":"10.1145","volume":"18","author":[{"given":"Yingying","family":"Jiao","sequence":"first","affiliation":[{"name":"Jilin University, Changchun, Jilin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haipeng","family":"Chen","sequence":"additional","affiliation":[{"name":"Jilin University, Changchun, Jilin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4912-6646","authenticated-orcid":false,"given":"Runyang","family":"Feng","sequence":"additional","affiliation":[{"name":"Zhejiang Gongshang University, Hangzhou, Zhejaing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4137-0417","authenticated-orcid":false,"given":"Haoming","family":"Chen","sequence":"additional","affiliation":[{"name":"Zhejiang Gongshang University, Hangzhou, Zhejaing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sifan","family":"Wu","sequence":"additional","affiliation":[{"name":"Zhejiang Gongshang University, Hangzhou, Zhejaing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6525-6133","authenticated-orcid":false,"given":"Yifang","family":"Yin","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research, A*STAR Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenguang","family":"Liu","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, Zhejiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,10,6]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00542"},{"key":"e_1_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00706"},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2980194"},{"key":"e_1_3_1_5_2","first-page":"3027","volume-title":"Advances in Neural Information Processing Systems","author":"Bertasius Gedas","year":"2019","unstructured":"Gedas Bertasius, Christoph Feichtenhofer, Du Tran, Jianbo Shi, and Lorenzo Torresani. 2019. Learning temporal pose estimation from sparsely-labeled videos. In Advances in Neural Information Processing Systems. 3027\u20133038."},{"key":"e_1_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.512"},{"key":"e_1_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3416299"},{"key":"e_1_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.334"},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01035"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00543"},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.601"},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.391"},{"key":"e_1_3_1_14_2","article-title":"Joint flow: Temporal flow fields for multi person tracking","author":"Doering Andreas","year":"2018","unstructured":"Andreas Doering, Umar Iqbal, and Juergen Gall. 2018. Joint flow: Temporal flow fields for multi person tracking. arXiv preprint arXiv:1805.04596 (2018).","journal-title":"arXiv preprint arXiv:1805.04596"},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01151"},{"key":"e_1_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.256"},{"key":"e_1_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475450"},{"key":"e_1_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00044"},{"key":"e_1_3_1_19_2","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"Guo Hengkai","year":"2018","unstructured":"Hengkai Guo, Tang Tang, Guozhong Luo, Riwei Chen, Yongchen Lu, and Linfu Wen. 2018. Multi-domain pose network for multi-person pose estimation and tracking. In Proceedings of the European Conference on Computer Vision (ECCV)."},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2019.8851734"},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2017.61"},{"key":"e_1_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00581"},{"key":"e_1_3_1_24_2","article-title":"Human pose regression with residual log-likelihood estimation","author":"Li Jiefeng","year":"2021","unstructured":"Jiefeng Li, Siyuan Bian, Ailing Zeng, Can Wang, Bo Pang, Wentao Liu, and Cewu Lu. 2021. Human pose regression with residual log-likelihood estimation. arXiv preprint arXiv:2107.11291 (2021).","journal-title":"arXiv preprint arXiv:2107.11291"},{"key":"e_1_3_1_25_2","article-title":"Learning a disentangled embedding for monocular 3D shape retrieval and pose estimation","author":"Lin Kyaw Zaw","year":"2018","unstructured":"Kyaw Zaw Lin, Weipeng Xu, Qianru Sun, Christian Theobalt, and Tat-Seng Chua. 2018. Learning a disentangled embedding for monocular 3D shape retrieval and pose estimation. arXiv preprint arXiv:1812.09899 (2018).","journal-title":"arXiv preprint arXiv:1812.09899"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3026625"},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240549"},{"key":"e_1_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00059"},{"key":"e_1_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3139918"},{"key":"e_1_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00546"},{"key":"e_1_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00704"},{"key":"e_1_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126552"},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.222"},{"key":"e_1_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00475"},{"key":"e_1_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15552-9_30"},{"key":"e_1_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00251"},{"key":"e_1_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.590"},{"key":"e_1_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00582"},{"key":"e_1_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00584"},{"key":"e_1_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248079"},{"key":"e_1_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475218"},{"key":"e_1_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00678"},{"key":"e_1_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.214"},{"key":"e_1_3_1_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01310"},{"key":"e_1_3_1_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.83"},{"key":"e_1_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01110"},{"key":"e_1_3_1_49_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-88690-7_53"},{"key":"e_1_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.511"},{"key":"e_1_3_1_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00931"},{"key":"e_1_3_1_52_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_29"},{"key":"e_1_3_1_53_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298734"},{"key":"e_1_3_1_54_2","article-title":"Pose flow: Efficient online pose tracking","author":"Xiu Yuliang","year":"2018","unstructured":"Yuliang Xiu, Jiefeng Li, Haoyu Wang, Yinghong Fang, and Cewu Lu. 2018. Pose flow: Efficient online pose tracking. arXiv preprint arXiv:1802.00977 (2018).","journal-title":"arXiv preprint arXiv:1802.00977"},{"key":"e_1_3_1_55_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2765836"},{"key":"e_1_3_1_56_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00798"},{"key":"e_1_3_1_57_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00712"},{"key":"e_1_3_1_58_2","article-title":"FastPose: Towards real-time pose estimation and tracking via scale-normalized multi-task networks","author":"Zhang Jiabin","year":"2019","unstructured":"Jiabin Zhang, Zheng Zhu, Wei Zou, Peng Li, Yanwei Li, Hu Su, and Guan Huang. 2019. FastPose: Towards real-time pose estimation and tracking via scale-normalized multi-task networks. arXiv preprint arXiv:1908.05593 (2019).","journal-title":"arXiv preprint arXiv:1908.05593"},{"key":"e_1_3_1_59_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459306"},{"key":"e_1_3_1_60_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_36"}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3519305","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3519305","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:00:04Z","timestamp":1750186804000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3519305"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,30]]},"references-count":59,"journal-issue":{"issue":"2s","published-print":{"date-parts":[[2022,6,30]]}},"alternative-id":["10.1145\/3519305"],"URL":"https:\/\/doi.org\/10.1145\/3519305","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"value":"1551-6857","type":"print"},{"value":"1551-6865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,6,30]]},"assertion":[{"value":"2021-11-11","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-02-15","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-10-06","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}