{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,3]],"date-time":"2026-11-03T17:38:31Z","timestamp":1793727511382,"version":"4.6.1"},"publisher-location":"New York, NY, USA","reference-count":49,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,10,12]],"date-time":"2020-10-12T00:00:00Z","timestamp":1602460800000},"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":[],"published-print":{"date-parts":[[2020,10,12]]},"DOI":"10.1145\/3394171.3413548","type":"proceedings-article","created":{"date-parts":[[2020,10,12]],"date-time":"2020-10-12T12:27:38Z","timestamp":1602505658000},"page":"2490-2498","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":207,"title":["MS2L"],"prefix":"10.1145","author":[{"given":"Lilang","family":"Lin","sequence":"first","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sijie","family":"Song","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenhan","family":"Yang","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaying","family":"Liu","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2020,10,12]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"Ting Chen Simon Kornblith Mohammad Norouzi and Geoffrey Hinton. 2020. A simple framework for contrastive learning of visual representations. arXiv preprint arXiv:2002.05709 (2020).  Ting Chen Simon Kornblith Mohammad Norouzi and Geoffrey Hinton. 2020. A simple framework for contrastive learning of visual representations. arXiv preprint arXiv:2002.05709 (2020)."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"crossref","unstructured":"Girum G Demisse Konstantinos Papadopoulos Djamila Aouada and Bjorn Ottersten. 2018. Pose Encoding for Robust Skeleton-Based Action Recognition. (2018) 188--194.  Girum G Demisse Konstantinos Papadopoulos Djamila Aouada and Bjorn Ottersten. 2018. Pose Encoding for Robust Skeleton-Based Action Recognition. (2018) 188--194.","DOI":"10.1109\/CVPRW.2018.00056"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.167"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2552404"},{"key":"e_1_3_2_2_5_1","volume-title":"Proc. IEEE Conference on Computer Vision and Pattern Recognition. 1110--1118","author":"Du Yong","year":"2015"},{"key":"e_1_3_2_2_6_1","first-page":"625","article-title":"Why does unsupervised pre-training help deep learning","author":"Erhan Dumitru","year":"2010","journal-title":"Journal of Machine Learning Research 11"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.607"},{"key":"e_1_3_2_2_8_1","volume-title":"Proc. Int'l Conference on Learning Representations.","author":"Gidaris Spyros","year":"2018"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2015.50"},{"key":"e_1_3_2_2_10_1","volume-title":"Proc. IEEE Conference on Computer Vision and Pattern Recognition. 1735--1742","author":"Hadsell R."},{"key":"e_1_3_2_2_11_1","volume-title":"Proc. IEEE Int?l Conference on Computer Vision. 4918--4927","author":"He Kaiming","year":"2019"},{"key":"e_1_3_2_2_12_1","unstructured":"Sepp Hochreiter Yoshua Bengio Paolo Frasconi J\u00fcrgen Schmidhuber etal 2001. Gradient flowin recurrent nets: the difficulty of learning long-term dependencies.  Sepp Hochreiter Yoshua Bengio Paolo Frasconi J\u00fcrgen Schmidhuber et al. 2001. Gradient flowin recurrent nets: the difficulty of learning long-term dependencies."},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_2_2_14_1","unstructured":"Eric Jang Coline Devin Vincent Vanhoucke and Sergey Levine. 2018. Grasp2vec: Learning object representations from self-supervised grasping. arXiv preprint arXiv:1811.06964 (2018).  Eric Jang Coline Devin Vincent Vanhoucke and Sergey Levine. 2018. Grasp2vec: Learning object representations from self-supervised grasping. arXiv preprint arXiv:1811.06964 (2018)."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.486"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018545"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.79"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3365212"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.02.030"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/11744085_28"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_32"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/0304-4076(88)90048-6"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_5"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00975"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_39"},{"key":"e_1_3_2_2_26_1","unstructured":"Sebastian Ruder. 2017. An overview of multi-task learning in deep neural networks. arXiv preprint arXiv:1706.05098 (2017).  Sebastian Ruder. 2017. An overview of multi-task learning in deep neural networks. arXiv preprint arXiv:1706.05098 (2017)."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.115"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01230"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00132"},{"key":"e_1_3_2_2_30_1","volume-title":"Proc. AAAI Conference on Artificial Intelligence. 4263--4270","author":"Song Sijie","year":"2017"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2818328"},{"key":"e_1_3_2_2_32_1","volume-title":"PREDICT CLUSTER: Unsupervised Skeleton Based Action Recognition. ArXiv abs\/1911.12409","author":"Su Kun","year":"2019"},{"key":"e_1_3_2_2_33_1","unstructured":"Ilya Sutskever Oriol Vinyals and Quoc V Le. 2014. Sequence to Sequence Learning with Neural Networks. (2014) 3104--3112.  Ilya Sutskever Oriol Vinyals and Quoc V Le. 2014. Sequence to Sequence Learning with Neural Networks. (2014) 3104--3112."},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.82"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.484"},{"key":"e_1_3_2_2_36_1","volume-title":"Proc. Advances in Neural Information Processing Systems. 613--621","author":"Vondrick Carl","year":"2016"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00413"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247813"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"crossref","unstructured":"JiangWang Xiaohan Nie Yin Xia YingWu and Songchun Zhu. 2014. Cross-View Action Modeling Learning and Recognition. (2014) 2649--2656.  JiangWang Xiaohan Nie Yin Xia YingWu and Songchun Zhu. 2014. Cross-View Action Modeling Learning and Recognition. (2014) 2649--2656.","DOI":"10.1109\/CVPR.2014.339"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2016.2576761"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00201"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2010.10.002"},{"key":"e_1_3_2_2_43_1","volume-title":"Proc. AAAI Conference on Artificial Intelligence. 7444--7452","author":"Yan Sijie","year":"2018"},{"key":"e_1_3_2_2_44_1","volume-title":"Proc. IEEE Int'l Conference on Computer Vision. 1476--1485","author":"Zhai Xiaohua","year":"2019"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.233"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_9"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_40"},{"key":"e_1_3_2_2_48_1","volume-title":"Proc. AAAI Conference on Artificial Intelligence. 2644--2651","author":"Zheng Nenggan","year":"2018"},{"key":"e_1_3_2_2_49_1","volume-title":"Proc. AAAI Conference on Artificial Intelligence. 3697--3703","author":"Zhu Wentao","year":"2016"}],"event":{"name":"MM '20: The 28th ACM International Conference on Multimedia","location":"Seattle WA USA","acronym":"MM '20","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 28th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3394171.3413548","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3394171.3413548","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:47:13Z","timestamp":1750193233000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3394171.3413548"}},"subtitle":["Multi-Task Self-Supervised Learning for Skeleton Based Action Recognition"],"short-title":[],"issued":{"date-parts":[[2020,10,12]]},"references-count":49,"alternative-id":["10.1145\/3394171.3413548","10.1145\/3394171"],"URL":"https:\/\/doi.org\/10.1145\/3394171.3413548","relation":{},"subject":[],"published":{"date-parts":[[2020,10,12]]},"assertion":[{"value":"2020-10-12","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}