{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T13:21:31Z","timestamp":1780579291052,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":44,"publisher":"ACM","license":[{"start":{"date-parts":[[2018,10,15]],"date-time":"2018-10-15T00:00:00Z","timestamp":1539561600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Natural Science Foundation of China (NSFC)","award":["61673088"],"award-info":[{"award-number":["61673088"]}]},{"name":"Natural Science Foundation of China (NSFC)","award":["61305043"],"award-info":[{"award-number":["61305043"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2018,10,15]]},"DOI":"10.1145\/3240508.3240675","type":"proceedings-article","created":{"date-parts":[[2018,10,18]],"date-time":"2018-10-18T17:52:08Z","timestamp":1539885128000},"page":"1510-1518","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":63,"title":["A Large-scale RGB-D Database for Arbitrary-view Human Action Recognition"],"prefix":"10.1145","author":[{"given":"Yanli","family":"Ji","sequence":"first","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feixiang","family":"Xu","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Yang","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fumin","family":"Shen","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Heng Tao","family":"Shen","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei-Shi","family":"Zheng","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2018,10,15]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Yi Bin Yang Yang Fumin Shen Ning Xie Heng Tao Shen and Xuelong Li. 2018. Describing Video with Attention based Bidirectional LSTM. IEEE Transactions on Cybernetics (2018).  Yi Bin Yang Yang Fumin Shen Ning Xie Heng Tao Shen and Xuelong Li. 2018. Describing Video with Attention based Bidirectional LSTM. IEEE Transactions on Cybernetics (2018)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.83"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2017.03.014"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.333"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"K. Hara H. Kataoka Y. Satoh and Satoh. 2018. Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?. In CVPR.  K. Hara H. Kataoka Y. Satoh and Satoh. 2018. Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?. In CVPR.","DOI":"10.1109\/CVPR.2018.00685"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"J. Hu W. Zheng J. Lai S. Gong and T. Xiang. 2016. Exemplarbased Recognition of Human-Object Interactions. IEEE Transactions on Circuits and Systems for Video Technology 26(4) (2016) 647--660.  J. Hu W. Zheng J. Lai S. Gong and T. Xiang. 2016. Exemplarbased Recognition of Human-Object Interactions. IEEE Transactions on Circuits and Systems for Video Technology 26(4) (2016) 647--660.","DOI":"10.1109\/TCSVT.2015.2397200"},{"key":"e_1_3_2_1_7_1","volume-title":"Proc. of ECCV.","author":"Hu J."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2640292"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"crossref","unstructured":"J. Hu W. S. Zheng J. H. Lai and J. Zhang. 2015. Jointly learning heterogeneous features for RGB-D activity recognition. In CVPR.  J. Hu W. S. Zheng J. H. Lai and J. Zhang. 2015. Jointly learning heterogeneous features for RGB-D activity recognition. In CVPR.","DOI":"10.1109\/CVPR.2015.7299172"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2717185"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2015.10.001"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/2390776.2390785"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2017.06.001"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2456412"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2670560"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"crossref","unstructured":"T. Kim and A. Reiter. 2017. Interpretable 3D Human Action Analysis with Temporal Convolutional Networks. In CVPRW.  T. Kim and A. Reiter. 2017. Interpretable 3D Human Action Analysis with Temporal Convolutional Networks. In CVPRW.","DOI":"10.1109\/CVPRW.2017.207"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2310117"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","unstructured":"C. Lea M. D. Flynn R. Vidal A. Reiter and G. D. Hager. 2017. Temporal convolutional networks for action segmentation and detection. In CVPR.  C. Lea M. D. Flynn R. Vidal A. Reiter and G. D. Hager. 2017. Temporal convolutional networks for action segmentation and detection. In CVPR.","DOI":"10.1109\/CVPR.2017.113"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2670782"},{"key":"e_1_3_2_1_20_1","unstructured":"C. Li P. Wang S. Wang Y. Hou and W. Li. 2017. Skeleton-based Action Recognition Using LSTM and CNN. CoRR abs\/1707.02356 (2017).  C. Li P. Wang S. Wang Y. Hou and W. Li. 2017. Skeleton-based Action Recognition Using LSTM and CNN. CoRR abs\/1707.02356 (2017)."},{"key":"e_1_3_2_1_21_1","unstructured":"R. Li and T. Zickler. 2012. Discriminative virtual views for crossview action recognition. In CVPR.   R. Li and T. Zickler. 2012. Discriminative virtual views for crossview action recognition. In CVPR."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2582918"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"crossref","unstructured":"J. Liu M. Shah B. Kuipers and S. Savarese. 2011. Cross-view action recognition via view knowledge transfer. In CVPR.  J. Liu M. Shah B. Kuipers and S. Savarese. 2011. Cross-view action recognition via view knowledge transfer. In CVPR.","DOI":"10.1109\/CVPR.2011.5995729"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.02.030"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"crossref","unstructured":"H. Rahmani A. Mahmood D. Huynh and A. Mian. 2014. Histogram of Oriented Principal Components for Cross-View Action Recognition. In ECCV.  H. Rahmani A. Mahmood D. Huynh and A. Mian. 2014. Histogram of Oriented Principal Components for Cross-View Action Recognition. In ECCV.","DOI":"10.1007\/978-3-319-10605-2_48"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2533389"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"crossref","unstructured":"H. Rahmani and A. Mian. 2015. Learning a non-linear knowledge transfer model for cross-view action recognition. In CVPR.  H. Rahmani and A. Mian. 2015. Learning a non-linear knowledge transfer model for cross-view action recognition. In CVPR.","DOI":"10.1109\/CVPR.2015.7298860"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","unstructured":"H. Rahmani and A. Mian. 2016. 3D Action Recognition from Novel Viewpoints. In CVPR.  H. Rahmani and A. Mian. 2016. 3D Action Recognition from Novel Viewpoints. In CVPR.","DOI":"10.1109\/CVPR.2016.167"},{"key":"e_1_3_2_1_29_1","volume-title":"11th IEEE-RAS International Conference on Humanoid Robots (Humanoids","author":"Rybok L.","year":"2011"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","unstructured":"A. Shahroudy J. Liu T. T. Ng and G. Wang. 2016. NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis. In CVPR.  A. Shahroudy J. Liu T. T. Ng and G. Wang. 2016. NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis. In CVPR.","DOI":"10.1109\/CVPR.2016.115"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"crossref","unstructured":"Y. Shen R. Ji S. Zhang W. Zuo Y Wang and F. Huang. 2018. Generative Adversarial Learning Towards Fast Weakly Supervised Detection. In CVPR.  Y. Shen R. Ji S. Zhang W. Zuo Y Wang and F. Huang. 2018. Generative Adversarial Learning Towards Fast Weakly Supervised Detection. In CVPR.","DOI":"10.1109\/CVPR.2018.00604"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.198"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.339"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.406"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"crossref","unstructured":"D. Weinland E. Boyer and R. Ronfard. 2007. Action Recognition from Arbitrary Views using 3D Exemplars. In ICCV.  D. Weinland E. Boyer and R. Ronfard. 2007. Action Recognition from Arbitrary Views using 3D Exemplars. In ICCV.","DOI":"10.1109\/ICCV.2007.4408849"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2006.07.013"},{"key":"e_1_3_2_1_37_1","unstructured":"P. Yan S. M. Khan and M. Shah. 2008. Learning 4D action feature models for arbitrary view action recognition. In CVPR.  P. Yan S. M. Khan and M. Shah. 2008. Learning 4D action feature models for arbitrary view action recognition. In CVPR."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"crossref","unstructured":"S. Yan Y. Xiong and D. Lin. 2018. Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition. In AAAI.  S. Yan Y. Xiong and D. Lin. 2018. Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition. In AAAI.","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2614136"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33868-7_6"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2675205"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2502147"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.347"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2012.04.016"}],"event":{"name":"MM '18: ACM Multimedia Conference","location":"Seoul Republic of Korea","acronym":"MM '18","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 26th ACM international conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3240508.3240675","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3240508.3240675","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T00:43:31Z","timestamp":1750207411000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3240508.3240675"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,10,15]]},"references-count":44,"alternative-id":["10.1145\/3240508.3240675","10.1145\/3240508"],"URL":"https:\/\/doi.org\/10.1145\/3240508.3240675","relation":{},"subject":[],"published":{"date-parts":[[2018,10,15]]},"assertion":[{"value":"2018-10-15","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}