{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T12:19:51Z","timestamp":1764937191782,"version":"3.41.0"},"reference-count":41,"publisher":"Association for Computing Machinery (ACM)","issue":"3","license":[{"start":{"date-parts":[[2020,7,5]],"date-time":"2020-07-05T00:00:00Z","timestamp":1593907200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["U1609215, 61972351, 61976188, and 61702453"],"award-info":[{"award-number":["U1609215, 61972351, 61976188, and 61702453"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100004731","name":"Natural Science Foundation of Zhejiang Province","doi-asserted-by":"crossref","award":["LY19F030005, LY18F020008, LQ17F030001, and LQ20F020008"],"award-info":[{"award-number":["LY19F030005, LY18F020008, LQ17F030001, and LQ20F020008"]}],"id":[{"id":"10.13039\/501100004731","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Key R8D Program of Zhejiang Province","award":["2018C01112."],"award-info":[{"award-number":["2018C01112."]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Multimedia Comput. Commun. Appl."],"published-print":{"date-parts":[[2020,8,31]]},"abstract":"<jats:p>Research on single-person pose estimation based on deep neural networks has recently witnessed progress in both accuracy and execution efficiency. However, multiperson pose estimation is still a challenging topic, partially because the object regions are selected greedily from proposals via class-agnostic nonmaximum suppression (NMS), and the misalignment in the redundant detection yields inaccurate human poses. Therefore, we consider how to obtain the optimal input in human pose estimation under conditions in which intermediate label information is not available. As supervised learning\u2013based alignment does not generalize well to unseen samples in the human pose space, in this article, we present a mask-aware deep reinforcement learning approach to modify the detection result. We use mask information to remove the adverse effects from the cluttered background and to select the optimal action according to the revised reward function. We also propose a new regularization term to punish joints that are outside of the silhouette region in the human pose estimation stage. We evaluate our approach on the MPII Multiperson dataset and the MS-COCO Keypoints Challenge. The results show that our approach yields competing inference results when it is compared to the other state-of-the-art approaches.<\/jats:p>","DOI":"10.1145\/3397340","type":"journal-article","created":{"date-parts":[[2020,7,6]],"date-time":"2020-07-06T04:16:30Z","timestamp":1594008990000},"page":"1-18","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Improving Multiperson Pose Estimation by Mask-aware Deep Reinforcement Learning"],"prefix":"10.1145","volume":"16","author":[{"given":"Xun","family":"Wang","sequence":"first","affiliation":[{"name":"School of Computer Science and Information Engineering, Zhejiang Gongshang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7416-656X","authenticated-orcid":false,"given":"Yan","family":"Tian","sequence":"additional","affiliation":[{"name":"School of Computer Science and Information Engineering, Zhejiang Gongshang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuran","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Information Engineering, Zhejiang Gongshang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Information Engineering, Zhejiang Gongshang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Judith","family":"Gelernter","sequence":"additional","affiliation":[{"name":"School of Communication and Information, Rutgers University, New Brunswick, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jialei","family":"Wang","sequence":"additional","affiliation":[{"name":"Shining3D Research, Shining3D Tech Co., Ltd., Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guohua","family":"Cheng","sequence":"additional","affiliation":[{"name":"Institute of Science and Technology for Brain-Inspired Intelligence, Ministry of Education-Key Laboratory of Computational Neuroscience and Brain-Inspired Intelligence, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2020,7,5]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.471"},{"key":"e_1_2_1_2_1","volume-title":"Caicedo and Svetlana Lazebnik","author":"Juan","year":"2015","unstructured":"Juan C. Caicedo and Svetlana Lazebnik . 2015 . Active object localization with deep reinforcement learning. In Proceedings of the ICCV. 2488--2496. Juan C. Caicedo and Svetlana Lazebnik. 2015. Active object localization with deep reinforcement learning. In Proceedings of the ICCV. 2488--2496."},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.180"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00742"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.601"},{"key":"e_1_2_1_7_1","volume-title":"Proceedings of the NIPS Workshop. EPFL--CONF--192376","author":"Collobert Ronan","year":"2011","unstructured":"Ronan Collobert , Koray Kavukcuoglu , and Cl\u00e9ment Farabet . 2011 . Torch7: A Matlab-like environment for machine learning . In Proceedings of the NIPS Workshop. EPFL--CONF--192376 . Ronan Collobert, Koray Kavukcuoglu, and Cl\u00e9ment Farabet. 2011. Torch7: A Matlab-like environment for machine learning. In Proceedings of the NIPS Workshop. EPFL--CONF--192376."},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299025"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.343"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.321"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.256"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00762"},{"key":"e_1_2_1_14_1","first-page":"7","article-title":"Segmentation-aware convolutional networks using local attention masks","volume":"2","author":"Harley Adam W.","year":"2017","unstructured":"Adam W. Harley , Konstantinos G. Derpanis , and Iasonas Kokkinos . 2017 . Segmentation-aware convolutional networks using local attention masks . In Proceedings of the ICCV , Vol. 2. 7 . Adam W. Harley, Konstantinos G. Derpanis, and Iasonas Kokkinos. 2017. Segmentation-aware convolutional networks using local attention masks. In Proceedings of the ICCV, Vol. 2. 7.","journal-title":"Proceedings of the ICCV"},{"key":"e_1_2_1_15_1","volume-title":"Mask R-CNN. In Proceedings of the ICCV. 2980--2988","author":"He Kaiming","year":"2017","unstructured":"Kaiming He , Georgia Gkioxari , Piotr Doll\u00e1r , and Ross Girshick . 2017 . Mask R-CNN. In Proceedings of the ICCV. 2980--2988 . Kaiming He, Georgia Gkioxari, Piotr Doll\u00e1r, and Ross Girshick. 2017. Mask R-CNN. In Proceedings of the ICCV. 2980--2988."},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_1_17_1","volume-title":"Proceedings of the AAAI. 4239--4240","author":"Hong Charmgil","year":"2015","unstructured":"Charmgil Hong and Milos Hauskrecht . 2015 . Multivariate conditional anomaly detection and its clinical application . In Proceedings of the AAAI. 4239--4240 . Charmgil Hong and Milos Hauskrecht. 2015. Multivariate conditional anomaly detection and its clinical application. In Proceedings of the AAAI. 4239--4240."},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.21"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.142"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_3"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-48881-3_44"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_44"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.206"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.472"},{"volume-title":"Proceedings of the ECCV. 740--755","author":"Lin Tsung-Yi","key":"e_1_2_1_26_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 Proceedings of the ECCV. 740--755 . 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 Proceedings of the ECCV. 740--755."},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2556859"},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2013.2285526"},{"key":"e_1_2_1_29_1","volume-title":"Human-level control through deep reinforcement learning. Nature 518, 7540","author":"Mnih Volodymyr","year":"2015","unstructured":"Volodymyr Mnih , Koray Kavukcuoglu , David Silver , Andrei A. Rusu , Joel Veness , Marc G. Bellemare , Alex Graves , Martin Riedmiller , Andreas K. Fidjeland , and Georg Ostrovski . 2015. Human-level control through deep reinforcement learning. Nature 518, 7540 ( 2015 ), 529--538. Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Andrei A. Rusu, Joel Veness, Marc G. Bellemare, Alex Graves, Martin Riedmiller, Andreas K. Fidjeland, and Georg Ostrovski. 2015. Human-level control through deep reinforcement learning. Nature 518, 7540 (2015), 529--538."},{"key":"e_1_2_1_30_1","volume-title":"Proceedings of the NIPS. 2274--2284","author":"Newell Alejandro","year":"2017","unstructured":"Alejandro Newell , Zhiao Huang , and Jia Deng . 2017 . Associative embedding: End-to-end learning for joint detection and grouping . In Proceedings of the NIPS. 2274--2284 . Alejandro Newell, Zhiao Huang, and Jia Deng. 2017. Associative embedding: End-to-end learning for joint detection and grouping. In Proceedings of the NIPS. 2274--2284."},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.395"},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.533"},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.424"},{"key":"e_1_2_1_35_1","volume-title":"Proceedings of the NIPS. 91--99","author":"Ren Shaoqing","year":"2015","unstructured":"Shaoqing Ren , Kaiming He , Ross Girshick , and Jian Sun . 2015 . Faster R-CNN: Towards real-time object detection with region proposal networks . In Proceedings of the NIPS. 91--99 . Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. 2015. Faster R-CNN: Towards real-time object detection with region proposal networks. In Proceedings of the NIPS. 91--99."},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2012.06.009"},{"key":"e_1_2_1_37_1","volume-title":"Proceedings of the ICML. 560--567","author":"Wang Ziyu","year":"2016","unstructured":"Ziyu Wang , Tom Schaul , Matteo Hessel , Hado Van Hasselt , Marc Lanctot , and Nando De Freitas . 2016 . Dueling network architectures for deep reinforcement learning . In Proceedings of the ICML. 560--567 . Ziyu Wang, Tom Schaul, Matteo Hessel, Hado Van Hasselt, Marc Lanctot, and Nando De Freitas. 2016. Dueling network architectures for deep reinforcement learning. In Proceedings of the ICML. 560--567."},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2432671"},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00401"},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.144"},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.148"}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3397340","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3397340","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:12:47Z","timestamp":1750201967000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3397340"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,7,5]]},"references-count":41,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2020,8,31]]}},"alternative-id":["10.1145\/3397340"],"URL":"https:\/\/doi.org\/10.1145\/3397340","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"type":"print","value":"1551-6857"},{"type":"electronic","value":"1551-6865"}],"subject":[],"published":{"date-parts":[[2020,7,5]]},"assertion":[{"value":"2019-07-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2020-04-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2020-07-05","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}