{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:41:23Z","timestamp":1755823283813,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["No.226-2022-00051"],"award-info":[{"award-number":["No.226-2022-00051"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key R&D Program of China","award":["2020YFB1313501"],"award-info":[{"award-number":["2020YFB1313501"]}]},{"name":"Key R&D program of Zhejiang Province","award":["2021C03003, 2022C01119, 2022C01022"],"award-info":[{"award-number":["2021C03003, 2022C01119, 2022C01022"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["T2293723, 61972347"],"award-info":[{"award-number":["T2293723, 61972347"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3611790","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:40Z","timestamp":1698391660000},"page":"2591-2599","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Implicit Decouple Network for Efficient Pose Estimation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-9177-1901","authenticated-orcid":false,"given":"Lei","family":"Zhao","sequence":"first","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3414-315X","authenticated-orcid":false,"given":"Le","family":"Han","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2966-6928","authenticated-orcid":false,"given":"Min","family":"Yao","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0211-8817","authenticated-orcid":false,"given":"Nenggan","family":"Zheng","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"crossref","unstructured":"Mykhaylo Andriluka Leonid Pishchulin Peter Gehler and Bernt Schiele. 2014. 2d human pose estimation: New benchmark and state of the art analysis. In CVPR. 3686--3693.","DOI":"10.1109\/CVPR.2014.471"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Serge Belongie Jitendra Malik and Jan Puzicha. 2002. Shape matching and object recognition using shape contexts. Technical Report.","DOI":"10.1109\/34.993558"},{"volume-title":"Learning delicate local representations for multi-person pose estimation","author":"Cai Yuanhao","key":"e_1_3_2_1_3_1","unstructured":"Yuanhao Cai, Zhicheng Wang, Zhengxiong Luo, Binyi Yin, Angang Du, Haoqian Wang, Xiangyu Zhang, Xinyu Zhou, Erjin Zhou, and Jian Sun. 2020. Learning delicate local representations for multi-person pose estimation. In ECCV. Springer, 455--472."},{"key":"e_1_3_2_1_4_1","unstructured":"Xianjie Chen and Alan L Yuille. 2014. Articulated pose estimation by a graphical model with image dependent pairwise relations. In NIPS. 1736--1744."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Yilun Chen Zhicheng Wang Yuxiang Peng Zhiqiang Zhang Gang Yu and Jian Sun. 2018. Cascaded pyramid network for multi-person pose estimation. In CVPR. 7103--7112.","DOI":"10.1109\/CVPR.2018.00742"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Xiao Chu Wei Yang Wanli Ouyang Cheng Ma Alan L Yuille and Xiaogang Wang. 2017. Multi-context attention for human pose estimation. In CVPR. 1831--1840.","DOI":"10.1109\/CVPR.2017.601"},{"key":"e_1_3_2_1_7_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.256"},{"volume-title":"Mask r-cnn","author":"He Kaiming","key":"e_1_3_2_1_9_1","unstructured":"Kaiming He, Georgia Gkioxari, Piotr Doll\u00e1r, and Ross Girshick. 2017. Mask r-cnn. In ICCV. IEEE, 2980--2988."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2016. Deep residual learning for image recognition. In CVPR. 770--778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_11_1","unstructured":"Andrew Howard Andrey Zhmoginov Liang-Chieh Chen Mark Sandler and Menglong Zhu. 2018. Inverted residuals and linear bottlenecks: Mobile networks for classification detection and segmentation. (2018)."},{"key":"e_1_3_2_1_12_1","volume-title":"Squeeze-and-excitation networks. arXiv preprint arXiv:1709.01507","author":"Hu Jie","year":"2017","unstructured":"Jie Hu, Li Shen, and Gang Sun. 2017. Squeeze-and-excitation networks. arXiv preprint arXiv:1709.01507, Vol. 7 (2017)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Shaoli Huang Mingming Gong and Dacheng Tao. 2017. A coarse-fine network for keypoint localization. In ICCV. 3028--3037.","DOI":"10.1109\/ICCV.2017.329"},{"key":"e_1_3_2_1_14_1","volume-title":"Whole-Body Human Pose Estimation in the Wild. arXiv preprint arXiv:2007.11858","author":"Jin Sheng","year":"2020","unstructured":"Sheng Jin, Lumin Xu, Jin Xu, Can Wang, Wentao Liu, Chen Qian, Wanli Ouyang, and Ping Luo. 2020. Whole-Body Human Pose Estimation in the Wild. arXiv preprint arXiv:2007.11858 (2020)."},{"key":"e_1_3_2_1_15_1","unstructured":"Lipeng Ke Ming-Ching Chang Honggang Qi and Siwei Lyu. 2018. Multi-scale structure-aware network for human pose estimation. In ECCV. 713--728."},{"key":"e_1_3_2_1_16_1","unstructured":"Alex Krizhevsky Ilya Sutskever and Geoffrey E Hinton. 2012. Imagenet classification with deep convolutional neural networks. In NIPS. 1097--1105."},{"key":"e_1_3_2_1_17_1","unstructured":"Jiefeng Li Siyuan Bian Ailing Zeng Can Wang Bo Pang Wentao Liu and Cewu Lu. 2021a. Human pose regression with residual log-likelihood estimation. In ICCV. 11025--11034."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","unstructured":"Ke Li Shijie Wang Xiang Zhang Yifan Xu Weijian Xu and Zhuowen Tu. 2021b. Pose recognition with cascade transformers. In CVPR. 1944--1953.","DOI":"10.1109\/CVPR46437.2021.00198"},{"key":"e_1_3_2_1_19_1","volume-title":"Dite-hrnet: Dynamic lightweight high-resolution network for human pose estimation. arXiv preprint arXiv:2204.10762","author":"Li Qun","year":"2022","unstructured":"Qun Li, Ziyi Zhang, Fu Xiao, Feng Zhang, and Bir Bhanu. 2022b. Dite-hrnet: Dynamic lightweight high-resolution network for human pose estimation. arXiv preprint arXiv:2204.10762 (2022)."},{"volume-title":"SimCC: A Simple Coordinate Classification Perspective for Human Pose Estimation","author":"Li Yanjie","key":"e_1_3_2_1_20_1","unstructured":"Yanjie Li, Sen Yang, Peidong Liu, Shoukui Zhang, Yunxiao Wang, Zhicheng Wang, Wankou Yang, and Shu-Tao Xia. 2022a. SimCC: A Simple Coordinate Classification Perspective for Human Pose Estimation. In ECCV. Springer, 89--106."},{"key":"e_1_3_2_1_21_1","volume-title":"Tokenpose: Learning keypoint tokens for human pose estimation. In ICCV. 11313--11322.","author":"Li Yanjie","year":"2021","unstructured":"Yanjie Li, Shoukui Zhang, Zhicheng Wang, Sen Yang, Wankou Yang, Shu-Tao Xia, and Erjin Zhou. 2021c. Tokenpose: Learning keypoint tokens for human pose estimation. In ICCV. 11313--11322."},{"key":"e_1_3_2_1_22_1","first-page":"4","article-title":"Feature Pyramid Networks for Object Detection","volume":"1","author":"Lin Tsung-Yi","year":"2017","unstructured":"Tsung-Yi Lin, Piotr Doll\u00e1r, Ross B Girshick, Kaiming He, Bharath Hariharan, and Serge J Belongie. 2017. Feature Pyramid Networks for Object Detection.. In CVPR, Vol. 1. 4.","journal-title":"CVPR"},{"volume-title":"Microsoft coco: Common objects in context","author":"Lin Tsung-Yi","key":"e_1_3_2_1_23_1","unstructured":"Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Doll\u00e1r, and C Lawrence Zitnick. 2014. Microsoft coco: Common objects in context. In ECCV. Springer, 740--755."},{"key":"e_1_3_2_1_24_1","volume-title":"Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101","author":"Loshchilov Ilya","year":"2017","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)."},{"key":"e_1_3_2_1_25_1","unstructured":"Ningning Ma Xiangyu Zhang Hai-Tao Zheng and Jian Sun. 2018. Shufflenet v2: Practical guidelines for efficient cnn architecture design. In ECCV. 116--131."},{"key":"e_1_3_2_1_26_1","volume-title":"Ju Yong Chang, and Kyoung Mu Lee","author":"Moon Gyeongsik","year":"2019","unstructured":"Gyeongsik Moon, Ju Yong Chang, and Kyoung Mu Lee. 2019. Posefix: Model-agnostic general human pose refinement network. In CVPR. 7773--7781."},{"volume-title":"Estimating human body configurations using shape context matching","author":"Mori Greg","key":"e_1_3_2_1_27_1","unstructured":"Greg Mori and Jitendra Malik. 2002. Estimating human body configurations using shape context matching. In ECCV. Springer, 666--680."},{"volume-title":"Stacked hourglass networks for human pose estimation","author":"Newell Alejandro","key":"e_1_3_2_1_28_1","unstructured":"Alejandro Newell, Kaiyu Yang, and Jia Deng. 2016. Stacked hourglass networks for human pose estimation. In ECCV. Springer, 483--499."},{"key":"e_1_3_2_1_29_1","first-page":"6","article-title":"Towards accurate multi-person pose estimation in the wild","volume":"3","author":"Papandreou George","year":"2017","unstructured":"George Papandreou, Tyler Zhu, Nori Kanazawa, Alexander Toshev, Jonathan Tompson, Chris Bregler, and Kevin Murphy. 2017. Towards accurate multi-person pose estimation in the wild. In CVPR, Vol. 3. 6.","journal-title":"CVPR"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","unstructured":"Ke Sun Bin Xiao Dong Liu and Jingdong Wang. 2019. Deep High-Resolution Representation Learning for Human Pose Estimation. In CVPR.","DOI":"10.1109\/CVPR.2019.00584"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"crossref","unstructured":"Xiao Sun Bin Xiao Fangyin Wei Shuang Liang and Yichen Wei. 2018. Integral human pose regression. In ECCV. 529--545.","DOI":"10.1007\/978-3-030-01231-1_33"},{"key":"e_1_3_2_1_32_1","volume-title":"Deeppose: Human pose estimation via deep neural networks. In CVPR. 1653--1660.","author":"Toshev Alexander","year":"2014","unstructured":"Alexander Toshev and Christian Szegedy. 2014. Deeppose: Human pose estimation via deep neural networks. In CVPR. 1653--1660."},{"key":"e_1_3_2_1_33_1","unstructured":"Hugo Touvron Matthieu Cord Matthijs Douze Francisco Massa Alexandre Sablayrolles and Herv\u00e9 J\u00e9gou. 2021. Training data-efficient image transformers & distillation through attention. In ICML. PMLR 10347--10357."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"crossref","unstructured":"Bin Xiao Haiping Wu and Yichen Wei. 2018. Simple baselines for human pose estimation and tracking. In ECCV. 466--481.","DOI":"10.1007\/978-3-030-01231-1_29"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"crossref","unstructured":"Wei Yang Shuang Li Wanli Ouyang Hongsheng Li and Xiaogang Wang. 2017. Learning feature pyramids for human pose estimation. In ICCV. 1281--1290.","DOI":"10.1109\/ICCV.2017.144"},{"key":"e_1_3_2_1_36_1","volume-title":"Lite-hrnet: A lightweight high-resolution network. In CVPR. 10440--10450.","author":"Yu Changqian","year":"2021","unstructured":"Changqian Yu, Bin Xiao, Changxin Gao, Lu Yuan, Lei Zhang, Nong Sang, and Jingdong Wang. 2021. Lite-hrnet: A lightweight high-resolution network. In CVPR. 10440--10450."},{"key":"e_1_3_2_1_37_1","first-page":"7281","article-title":"Hrformer: High-resolution vision transformer for dense predict","volume":"34","author":"Yuan Yuhui","year":"2021","unstructured":"Yuhui Yuan, Rao Fu, Lang Huang, Weihong Lin, Chao Zhang, Xilin Chen, and Jingdong Wang. 2021. Hrformer: High-resolution vision transformer for dense predict. NIPS, Vol. 34 (2021), 7281--7293.","journal-title":"NIPS"},{"volume-title":"Efficient human pose estimation via parsing a tree structure based human model","author":"Zhang Xiaoqin","key":"e_1_3_2_1_38_1","unstructured":"Xiaoqin Zhang, Changcheng Li, Xiaofeng Tong, Weiming Hu, Steve Maybank, and Yimin Zhang. 2009. Efficient human pose estimation via parsing a tree structure based human model. In ICCV. IEEE, 1349--1356."},{"key":"e_1_3_2_1_39_1","volume-title":"Simple and Lightweight Human Pose Estimation. arXiv preprint arXiv:1911.10346","author":"Zhang Zhe","year":"2019","unstructured":"Zhe Zhang, Jie Tang, and Gangshan Wu. 2019. Simple and Lightweight Human Pose Estimation. arXiv preprint arXiv:1911.10346 (2019)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16463"}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Ottawa ON Canada","acronym":"MM '23"},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611790","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3611790","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:02:22Z","timestamp":1755820942000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611790"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":40,"alternative-id":["10.1145\/3581783.3611790","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3611790","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}