{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T16:29:14Z","timestamp":1776356954221,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,12,15]],"date-time":"2019-12-15T00:00:00Z","timestamp":1576368000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science","doi-asserted-by":"publisher","award":["JP17H06101, JP17K00237"],"award-info":[{"award-number":["JP17H06101, JP17K00237"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,12,15]]},"DOI":"10.1145\/3338533.3366569","type":"proceedings-article","created":{"date-parts":[[2020,1,11]],"date-time":"2020-01-11T04:30:32Z","timestamp":1578717032000},"page":"1-6","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":166,"title":["Make Skeleton-based Action Recognition Model Smaller, Faster and Better"],"prefix":"10.1145","author":[{"given":"Fan","family":"Yang","sequence":"first","affiliation":[{"name":"Nara Institute of Science and Technology, Japan, RIKEN, Center for Advanced Intelligence Project, Japan"}]},{"given":"Yang","family":"Wu","sequence":"additional","affiliation":[{"name":"Kyoto University, Japan"}]},{"given":"Sakriani","family":"Sakti","sequence":"additional","affiliation":[{"name":"Nara Institute of Science and Technology, Japan, RIKEN, Center for Advanced Intelligence Project, Japan"}]},{"given":"Satoshi","family":"Nakamura","sequence":"additional","affiliation":[{"name":"Nara Institute of Science and Technology, Japan, RIKEN, Center for Advanced Intelligence Project, Japan"}]}],"member":"320","published-online":{"date-parts":[[2020,1,10]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"},{"key":"e_1_3_2_1_2_1","volume-title":"A 3 Cent Recognizer: Simple and Effective Retrieval and Classification of Mid-air Gestures from Single 3D Traces. Smart Tools and Apps for Graphics","author":"Caputo Fabio Marco","year":"2017","unstructured":"Fabio Marco Caputo , Pietro Prebianca , Alessandro Carcangiu , Lucio D Spano , and Andrea Giachetti . 2017. A 3 Cent Recognizer: Simple and Effective Retrieval and Classification of Mid-air Gestures from Single 3D Traces. Smart Tools and Apps for Graphics . Eurographics Association ( 2017 ). Fabio Marco Caputo, Pietro Prebianca, Alessandro Carcangiu, Lucio D Spano, and Andrea Giachetti. 2017. A 3 Cent Recognizer: Simple and Effective Retrieval and Classification of Mid-air Gestures from Single 3D Traces. Smart Tools and Apps for Graphics. Eurographics Association (2017)."},{"key":"e_1_3_2_1_3_1","volume-title":"A Kinect-based system for physical rehabilitation: A pilot study for young adults with motor disabilities. Research in developmental disabilities 32, 6","author":"Chang Yao-Jen","year":"2011","unstructured":"Yao-Jen Chang , Shu-Fang Chen , and Jun-Da Huang . 2011. A Kinect-based system for physical rehabilitation: A pilot study for young adults with motor disabilities. Research in developmental disabilities 32, 6 ( 2011 ), 2566--2570. Yao-Jen Chang, Shu-Fang Chen, and Jun-Da Huang. 2011. A Kinect-based system for physical rehabilitation: A pilot study for young adults with motor disabilities. Research in developmental disabilities 32, 6 (2011), 2566--2570."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2010.272"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.3390\/s19020239"},{"key":"e_1_3_2_1_6_1","unstructured":"Fran\u00e7ois Chollet et al. 2015. Keras.  Fran\u00e7ois Chollet et al. 2015. Keras."},{"key":"e_1_3_2_1_7_1","volume-title":"PoTion: Pose MoTion Representation for Action Recognition. In CVPR","author":"Choutas Vasileios","year":"2018","unstructured":"Vasileios Choutas , Philippe Weinzaepfel , J\u00e9r\u00f4me Revaud , and Cordelia Schmid . 2018 . PoTion: Pose MoTion Representation for Action Recognition. In CVPR 2018. Vasileios Choutas, Philippe Weinzaepfel, J\u00e9r\u00f4me Revaud, and Cordelia Schmid. 2018. PoTion: Pose MoTion Representation for Action Recognition. In CVPR 2018."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2016.153"},{"key":"e_1_3_2_1_9_1","volume-title":"SHREC'17 Track: 3D Hand Gesture Recognition Using a Depth and Skeletal Dataset. In 10th Eurographics Workshop on 3D Object Retrieval.","author":"Smedt Quentin De","year":"2017","unstructured":"Quentin De Smedt , Hazem Wannous , Jean-Philippe Vandeborre , Joris Guerry , Bertrand Le Saux , and David Filliat . 2017 . SHREC'17 Track: 3D Hand Gesture Recognition Using a Depth and Skeletal Dataset. In 10th Eurographics Workshop on 3D Object Retrieval. Quentin De Smedt, Hazem Wannous, Jean-Philippe Vandeborre, Joris Guerry, Bertrand Le Saux, and David Filliat. 2017. SHREC'17 Track: 3D Hand Gesture Recognition Using a Depth and Skeletal Dataset. In 10th Eurographics Workshop on 3D Object Retrieval."},{"key":"e_1_3_2_1_10_1","unstructured":"Guillaume Devineau Wang Xi Fabien Moutarde and Jie Yang. 2018. Convolutional Neural Networks for Multivariate Time Series Classification using both Inter-and Intra-Channel Parallel Convolutions. In Reconnaissance des Formes Image Apprentissage et Perception (RFIAP'2018).  Guillaume Devineau Wang Xi Fabien Moutarde and Jie Yang. 2018. Convolutional Neural Networks for Multivariate Time Series Classification using both Inter-and Intra-Channel Parallel Convolutions. In Reconnaissance des Formes Image Apprentissage et Perception (RFIAP'2018)."},{"key":"e_1_3_2_1_11_1","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition. 1110--1118","author":"Du Yong","year":"2015","unstructured":"Yong Du , Wei Wang , and Liang Wang . 2015 . Hierarchical recurrent neural network for skeleton based action recognition . In Proceedings of the IEEE conference on computer vision and pattern recognition. 1110--1118 . Yong Du, Wei Wang, and Liang Wang. 2015. Hierarchical recurrent neural network for skeleton based action recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition. 1110--1118."},{"key":"e_1_3_2_1_12_1","volume-title":"Slow-Fast Networks for Video Recognition. arXiv preprint arXiv:1812.03982","author":"Feichtenhofer Christoph","year":"2018","unstructured":"Christoph Feichtenhofer , Haoqi Fan , Jitendra Malik , and Kaiming He. 2018. Slow-Fast Networks for Video Recognition. arXiv preprint arXiv:1812.03982 ( 2018 ). Christoph Feichtenhofer, Haoqi Fan, Jitendra Malik, and Kaiming He. 2018. Slow-Fast Networks for Video Recognition. arXiv preprint arXiv:1812.03982 (2018)."},{"key":"e_1_3_2_1_13_1","volume-title":"Realtime 3D Hand Pose Estimation with 3D Convolutional Neural Networks","author":"Ge Liuhao","year":"2018","unstructured":"Liuhao Ge , Hui Liang , Junsong Yuan , and Daniel Thalmann . 2018. Realtime 3D Hand Pose Estimation with 3D Convolutional Neural Networks . IEEE Transactions on Pattern Analysis and Machine Intelligence ( 2018 ). Liuhao Ge, Hui Liang, Junsong Yuan, and Daniel Thalmann. 2018. Realtime 3D Hand Pose Estimation with 3D Convolutional Neural Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence (2018)."},{"key":"e_1_3_2_1_14_1","volume-title":"Spatial-Temporal Attention Res-TCN for Skeleton-based Dynamic Hand Gesture Recognition. gesture 30, 5","author":"Hou Jingxuan","year":"2018","unstructured":"Jingxuan Hou , Guijin Wang , Xinghao Chen , Jing-Hao Xue , Rui Zhu , and Huazhong Yang . 2018. Spatial-Temporal Attention Res-TCN for Skeleton-based Dynamic Hand Gesture Recognition. gesture 30, 5 ( 2018 ), 3. Jingxuan Hou, Guijin Wang, Xinghao Chen, Jing-Hao Xue, Rui Zhu, and Huazhong Yang. 2018. Spatial-Temporal Attention Res-TCN for Skeleton-based Dynamic Hand Gesture Recognition. gesture 30, 5 (2018), 3."},{"key":"e_1_3_2_1_15_1","volume-title":"International Conf. on Computer Vision (ICCV). 3192--3199","author":"Jhuang H.","unstructured":"H. Jhuang , J. Gall , S. Zuffi , C. Schmid , and M. J. Black . 2013. Towards understanding action recognition . In International Conf. on Computer Vision (ICCV). 3192--3199 . H. Jhuang, J. Gall, S. Zuffi, C. Schmid, and M. J. Black. 2013. Towards understanding action recognition. In International Conf. on Computer Vision (ICCV). 3192--3199."},{"key":"e_1_3_2_1_16_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba . 2014 . Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014). Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.115"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2017.2678539"},{"key":"e_1_3_2_1_19_1","volume-title":"Multimedia & Expo Workshops (ICMEW), 2017 IEEE International Conference on. IEEE, 585--590","author":"Li Chuankun","year":"2017","unstructured":"Chuankun Li , Pichao Wang , Shuang Wang , Yonghong Hou , and Wanqing Li . 2017 . Skeleton-based action recognition using LSTM and CNN . In Multimedia & Expo Workshops (ICMEW), 2017 IEEE International Conference on. IEEE, 585--590 . Chuankun Li, Pichao Wang, Shuang Wang, Yonghong Hou, and Wanqing Li. 2017. Skeleton-based action recognition using LSTM and CNN. In Multimedia & Expo Workshops (ICMEW), 2017 IEEE International Conference on. IEEE, 585--590."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_50"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.02.030"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00127"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"crossref","unstructured":"Dennis Ludl Thomas Gulde and Crist'obal Curio. 2019. Simple yet efficient real-time pose-based action recognition. In ITSC.  Dennis Ludl Thomas Gulde and Crist'obal Curio. 2019. Simple yet efficient real-time pose-based action recognition. In ITSC.","DOI":"10.1109\/ITSC.2019.8917128"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073596"},{"key":"e_1_3_2_1_25_1","volume-title":"A survey of computer vision-based human motion capture. Computer vision and image understanding 81, 3","author":"Moeslund Thomas B","year":"2001","unstructured":"Thomas B Moeslund and Erik Granum . 2001. A survey of computer vision-based human motion capture. Computer vision and image understanding 81, 3 ( 2001 ), 231--268. Thomas B Moeslund and Erik Granum. 2001. A survey of computer vision-based human motion capture. Computer vision and image understanding 81, 3 (2001), 231--268."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.10.033"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/2072298.2072443"},{"key":"e_1_3_2_1_28_1","first-page":"4263","article-title":"An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data","volume":"1","author":"Song Sijie","year":"2017","unstructured":"Sijie Song , Cuiling Lan , Junliang Xing , Wenjun Zeng , and Jiaying Liu . 2017 . An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data .. In AAAI , Vol. 1. 4263 -- 4270 . Sijie Song, Cuiling Lan, Junliang Xing, Wenjun Zeng, and Jiaying Liu. 2017. An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data.. In AAAI, Vol. 1. 4263--4270.","journal-title":"AAAI"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00558"},{"key":"e_1_3_2_1_30_1","volume-title":"Can WiFi Estimate Person Pose? arXiv preprint arXiv:1904.00277","author":"Wang Fei","year":"2019","unstructured":"Fei Wang , Stanislav Panev , Ziyi Dai , Jinsong Han , and Dong Huang . 2019. Can WiFi Estimate Person Pose? arXiv preprint arXiv:1904.00277 ( 2019 ). Fei Wang, Stanislav Panev, Ziyi Dai, Jinsong Han, and Dong Huang. 2019. Can WiFi Estimate Person Pose? arXiv preprint arXiv:1904.00277 (2019)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"crossref","unstructured":"Hongsong Wang and Liang Wang. 2017. Modeling temporal dynamics and spatial configurations of actions using two-stream recurrent neural networks. In e Conference on Computer Vision and Pa ern Recognition (CVPR).  Hongsong Wang and Liang Wang. 2017. Modeling temporal dynamics and spatial configurations of actions using two-stream recurrent neural networks. In e Conference on Computer Vision and Pa ern Recognition (CVPR).","DOI":"10.1109\/CVPR.2017.387"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/2660505.2660512"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_29"},{"key":"e_1_3_2_1_34_1","volume-title":"Spatial temporal graph convolutional networks for skeleton-based action recognition. arXiv preprint arXiv:1801.07455","author":"Yan Sijie","year":"2018","unstructured":"Sijie Yan , Yuanjun Xiong , and Dahua Lin . 2018. Spatial temporal graph convolutional networks for skeleton-based action recognition. arXiv preprint arXiv:1801.07455 ( 2018 ). Sijie Yan, Yuanjun Xiong, and Dahua Lin. 2018. Spatial temporal graph convolutional networks for skeleton-based action recognition. arXiv preprint arXiv:1801.07455 (2018)."},{"key":"e_1_3_2_1_35_1","volume-title":"Action Recognition with Spatio-Temporal Visual Attention on Skeleton Image Sequences","author":"Yang Zhengyuan","year":"2018","unstructured":"Zhengyuan Yang , Yuncheng Li , Jianchao Yang , and Jiebo Luo . 2018. Action Recognition with Spatio-Temporal Visual Attention on Skeleton Image Sequences . IEEE Transactions on Circuits and Systems for Video Technology ( 2018 ). Zhengyuan Yang, Yuncheng Li, Jianchao Yang, and Jiebo Luo. 2018. Action Recognition with Spatio-Temporal Visual Attention on Skeleton Image Sequences. IEEE Transactions on Circuits and Systems for Video Technology (2018)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2802648"},{"key":"e_1_3_2_1_37_1","volume-title":"Microsoft kinect sensor and its effect","author":"Zhang Zhengyou","year":"2012","unstructured":"Zhengyou Zhang . 2012. Microsoft kinect sensor and its effect . IEEE multimedia 19, 2 ( 2012 ), 4--10. Zhengyou Zhang. 2012. Microsoft kinect sensor and its effect. IEEE multimedia 19, 2 (2012), 4--10."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00768"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.316"}],"event":{"name":"MMAsia '19: ACM Multimedia Asia","location":"Beijing China","acronym":"MMAsia '19","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the ACM Multimedia Asia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3338533.3366569","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3338533.3366569","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:44:46Z","timestamp":1750203886000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3338533.3366569"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12,15]]},"references-count":39,"alternative-id":["10.1145\/3338533.3366569","10.1145\/3338533"],"URL":"https:\/\/doi.org\/10.1145\/3338533.3366569","relation":{},"subject":[],"published":{"date-parts":[[2019,12,15]]},"assertion":[{"value":"2020-01-10","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}