{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T17:05:00Z","timestamp":1783530300669,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":48,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,10,17]],"date-time":"2021-10-17T00:00:00Z","timestamp":1634428800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2018AAA0100400"],"award-info":[{"award-number":["2018AAA0100400"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,10,17]]},"DOI":"10.1145\/3474085.3475473","type":"proceedings-article","created":{"date-parts":[[2021,10,18]],"date-time":"2021-10-18T21:45:34Z","timestamp":1634593534000},"page":"3229-3237","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":126,"title":["STST: Spatial-Temporal Specialized Transformer for Skeleton-based Action Recognition"],"prefix":"10.1145","author":[{"given":"Yuhan","family":"Zhang","sequence":"first","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Wu","sequence":"additional","affiliation":[{"name":"MIT-IBM Watson AI Lab, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wen","family":"Li","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lixin","family":"Duan","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chuang","family":"Gan","sequence":"additional","affiliation":[{"name":"MIT-IBM Watson AI Lab, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2021,10,17]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"A Spatio-temporal Transformer for 3D Human Motion Prediction. arXiv e-prints","author":"Aksan Emre","year":"2020","unstructured":"Emre Aksan , Peng Cao , Manuel Kaufmann , and Otmar Hilliges . 2020. A Spatio-temporal Transformer for 3D Human Motion Prediction. arXiv e-prints ( 2020 ), arXiv--2004. Emre Aksan, Peng Cao, Manuel Kaufmann, and Otmar Hilliges. 2020. A Spatio-temporal Transformer for 3D Human Motion Prediction. arXiv e-prints (2020), arXiv--2004."},{"key":"e_1_3_2_1_2_1","volume-title":"Jamie Ryan Kiros, and Geoffrey E Hinton","author":"Ba Jimmy Lei","year":"2016","unstructured":"Jimmy Lei Ba , Jamie Ryan Kiros, and Geoffrey E Hinton . 2016 . Layer normalization. arXiv preprint arXiv:1607.06450 (2016). Jimmy Lei Ba, Jamie Ryan Kiros, and Geoffrey E Hinton. 2016. Layer normalization. arXiv preprint arXiv:1607.06450 (2016)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"},{"key":"e_1_3_2_1_4_1","volume-title":"Construct dynamic graphs for hand gesture recognition via spatial-temporal attention. arXiv preprint arXiv:1907.08871","author":"Chen Yuxiao","year":"2019","unstructured":"Yuxiao Chen , Long Zhao , Xi Peng , Jianbo Yuan , and Dimitris N Metaxas . 2019. Construct dynamic graphs for hand gesture recognition via spatial-temporal attention. arXiv preprint arXiv:1907.08871 ( 2019 ). Yuxiao Chen, Long Zhao, Xi Peng, Jianbo Yuan, and Dimitris N Metaxas. 2019. Construct dynamic graphs for hand gesture recognition via spatial-temporal attention. arXiv preprint arXiv:1907.08871 (2019)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00026"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.368"},{"key":"e_1_3_2_1_7_1","volume-title":"Hyung Jin Chang, and Wonjun Hwang","author":"Cho Hyeon","year":"2020","unstructured":"Hyeon Cho , Taehoon Kim , Hyung Jin Chang, and Wonjun Hwang . 2020 . Self-supervised spatio-temporal representation learning using variable playback speed prediction. arXiv preprint arXiv:2003.02692 (2020). Hyeon Cho, Taehoon Kim, Hyung Jin Chang, and Wonjun Hwang. 2020. Self-supervised spatio-temporal representation learning using variable playback speed prediction. arXiv preprint arXiv:2003.02692 (2020)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.2312\/3dor.20171049"},{"key":"e_1_3_2_1_9_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin , Ming-Wei Chang , Kenton Lee , and Kristina Toutanova . 2018 . Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018). Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"Zewei Ding Pichao Wang Philip O Ogunbona and Wanqing Li. 2017. Investigation of different skeleton features for cnn-based 3d action recognition. In ICMEW). 617--622.  Zewei Ding Pichao Wang Philip O Ogunbona and Wanqing Li. 2017. Investigation of different skeleton features for cnn-based 3d action recognition. In ICMEW). 617--622.","DOI":"10.1109\/ICMEW.2017.8026286"},{"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":"Proceedings of the thirteenth international conference on artificial intelligence and statistics. JMLR Workshop and Conference Proceedings, 201--208","author":"Erhan Dumitru","year":"2010","unstructured":"Dumitru Erhan , Aaron Courville , Yoshua Bengio , and Pascal Vincent . 2010 . Why does unsupervised pre-training help deep learning? . In Proceedings of the thirteenth international conference on artificial intelligence and statistics. JMLR Workshop and Conference Proceedings, 201--208 . Dumitru Erhan, Aaron Courville, Yoshua Bengio, and Pascal Vincent. 2010. Why does unsupervised pre-training help deep learning?. In Proceedings of the thirteenth international conference on artificial intelligence and statistics. JMLR Workshop and Conference Proceedings, 201--208."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Lijie Fan Wenbing Huang Chuang Gan Stefano Ermon Boqing Gong and Junzhou Huang. 2018. End-to-end learning of motion representation for video understanding. In CVPR. 6016--6025.  Lijie Fan Wenbing Huang Chuang Gan Stefano Ermon Boqing Gong and Junzhou Huang. 2018. End-to-end learning of motion representation for video understanding. In CVPR. 6016--6025.","DOI":"10.1109\/CVPR.2018.00630"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.607"},{"key":"e_1_3_2_1_15_1","unstructured":"Chuang Gan Boqing Gong Kun Liu Hao Su and Leonidas J Guibas. 2018. Geometry guided convolutional neural networks for self-supervised video representation learning. In CVPR. 5589--5597.  Chuang Gan Boqing Gong Kun Liu Hao Su and Leonidas J Guibas. 2018. Geometry guided convolutional neural networks for self-supervised video representation learning. In CVPR. 5589--5597."},{"key":"e_1_3_2_1_16_1","volume-title":"Devnet: A deep event network for multimedia event detection and evidence recounting. In CVPR. 2568--2577.","author":"Gan Chuang","year":"2015","unstructured":"Chuang Gan , Naiyan Wang , Yi Yang , Dit-Yan Yeung , and Alex G Hauptmann . 2015 . Devnet: A deep event network for multimedia event detection and evidence recounting. In CVPR. 2568--2577. Chuang Gan, Naiyan Wang, Yi Yang, Dit-Yan Yeung, and Alex G Hauptmann. 2015. Devnet: A deep event network for multimedia event detection and evidence recounting. In CVPR. 2568--2577."},{"key":"e_1_3_2_1_17_1","unstructured":"Chuang Gan Ting Yao Kuiyuan Yang Yi Yang and Tao Mei. 2016. You lead we exceed: Labor-free video concept learning by jointly exploiting web videos and images. In CVPR. 923--932.  Chuang Gan Ting Yao Kuiyuan Yang Yi Yang and Tao Mei. 2016. You lead we exceed: Labor-free video concept learning by jointly exploiting web videos and images. In CVPR. 923--932."},{"key":"e_1_3_2_1_18_1","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV) Workshops. 0--0.","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 . In Proceedings of the European Conference on Computer Vision (ECCV) Workshops. 0--0. 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. In Proceedings of the European Conference on Computer Vision (ECCV) Workshops. 0--0."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.5555\/2540128.2540483"},{"key":"e_1_3_2_1_20_1","unstructured":"Will Kay Joao Carreira Karen Simonyan Brian Zhang Chloe Hillier Sudheendra Vijayanarasimhan Fabio Viola Tim Green Trevor Back Paul Natsev etal 2017. The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017).  Will Kay Joao Carreira Karen Simonyan Brian Zhang Chloe Hillier Sudheendra Vijayanarasimhan Fabio Viola Tim Green Trevor Back Paul Natsev et al. 2017. The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.486"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.207"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.79"},{"key":"e_1_3_2_1_24_1","volume-title":"2017 IEEE International Conference on Multimedia & Expo Workshops (ICMEW). IEEE, 601--604","author":"Li Bo","year":"2017","unstructured":"Bo Li , Yuchao Dai , Xuelian Cheng , Huahui Chen , Yi Lin , and Mingyi He . 2017 . Skeleton based action recognition using translation-scale invariant image mapping and multi-scale deep CNN . In 2017 IEEE International Conference on Multimedia & Expo Workshops (ICMEW). IEEE, 601--604 . Bo Li, Yuchao Dai, Xuelian Cheng, Huahui Chen, Yi Lin, and Mingyi He. 2017. Skeleton based action recognition using translation-scale invariant image mapping and multi-scale deep CNN. In 2017 IEEE International Conference on Multimedia & Expo Workshops (ICMEW). IEEE, 601--604."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018561"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.5555\/3304415.3304527"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00371"},{"key":"e_1_3_2_1_28_1","volume-title":"TSM: Temporal Shift Module for Efficient Video Understanding. In ICCV. 7082--7092.","author":"Lin Ji","year":"2019","unstructured":"Ji Lin , Chuang Gan , and Song Han . 2019 . TSM: Temporal Shift Module for Efficient Video Understanding. In ICCV. 7082--7092. Ji Lin, Chuang Gan, and Song Han. 2019. TSM: Temporal Shift Module for Efficient Video Understanding. In ICCV. 7082--7092."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413548"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_50"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.02.030"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60639-8_40"},{"key":"e_1_3_2_1_33_1","volume-title":"Jiajun Wu, Xiao Liu, and Shilei Wen.","author":"Long Xiang","year":"2018","unstructured":"Xiang Long , Chuang Gan , Gerard De Melo , Jiajun Wu, Xiao Liu, and Shilei Wen. 2018 . Attention clusters: Purely attention based local feature integration for video classification. In CVPR. 7834--7843. Xiang Long, Chuang Gan, Gerard De Melo, Jiajun Wu, Xiao Liu, and Shilei Wen. 2018. Attention clusters: Purely attention based local feature integration for video classification. In CVPR. 7834--7843."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6840"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01231"},{"key":"e_1_3_2_1_36_1","volume-title":"Spatial temporal transformer network for skeleton-based action recognition. arXiv preprint arXiv:2008.07404","author":"Plizzari Chiara","year":"2020","unstructured":"Chiara Plizzari , Marco Cannici , and Matteo Matteucci . 2020. Spatial temporal transformer network for skeleton-based action recognition. arXiv preprint arXiv:2008.07404 ( 2020 ). Chiara Plizzari, Marco Cannici, and Matteo Matteucci. 2020. Spatial temporal transformer network for skeleton-based action recognition. arXiv preprint arXiv:2008.07404 (2020)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.115"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00810"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01230"},{"key":"e_1_3_2_1_40_1","volume-title":"2020 a. Decoupled Spatial-Temporal Attention Network for Skeleton-Based Action Recognition. arXiv preprint arXiv:2007.03263","author":"Shi Lei","year":"2020","unstructured":"Lei Shi , Yifan Zhang , Jian Cheng , and Hanqing Lu . 2020 a. Decoupled Spatial-Temporal Attention Network for Skeleton-Based Action Recognition. arXiv preprint arXiv:2007.03263 ( 2020 ). Lei Shi, Yifan Zhang, Jian Cheng, and Hanqing Lu. 2020 a. Decoupled Spatial-Temporal Attention Network for Skeleton-Based Action Recognition. arXiv preprint arXiv:2007.03263 (2020)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3028207"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.5555\/3298023.3298186"},{"key":"e_1_3_2_1_43_1","volume-title":"Attention is all you need. arXiv preprint arXiv:1706.03762","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani , Noam Shazeer , Niki Parmar , Jakob Uszkoreit , Llion Jones , Aidan N Gomez , Lukasz Kaiser , and Illia Polosukhin . 2017. Attention is all you need. arXiv preprint arXiv:1706.03762 ( 2017 ). Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. arXiv preprint arXiv:1706.03762 (2017)."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.82"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.5555\/3172077.3172316"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"e_1_3_2_1_48_1","volume-title":"Clevrer: Collision events for video representation and reasoning. arXiv preprint arXiv:1910.01442","author":"Yi Kexin","year":"2019","unstructured":"Kexin Yi , Chuang Gan , Yunzhu Li , Pushmeet Kohli , Jiajun Wu , Antonio Torralba , and Joshua B Tenenbaum . 2019 . Clevrer: Collision events for video representation and reasoning. arXiv preprint arXiv:1910.01442 (2019). Kexin Yi, Chuang Gan, Yunzhu Li, Pushmeet Kohli, Jiajun Wu, Antonio Torralba, and Joshua B Tenenbaum. 2019. Clevrer: Collision events for video representation and reasoning. arXiv preprint arXiv:1910.01442 (2019)."}],"event":{"name":"MM '21: ACM Multimedia Conference","location":"Virtual Event China","acronym":"MM '21","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 29th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3474085.3475473","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3474085.3475473","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:48:34Z","timestamp":1750193314000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3474085.3475473"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,17]]},"references-count":48,"alternative-id":["10.1145\/3474085.3475473","10.1145\/3474085"],"URL":"https:\/\/doi.org\/10.1145\/3474085.3475473","relation":{},"subject":[],"published":{"date-parts":[[2021,10,17]]},"assertion":[{"value":"2021-10-17","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}