{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,20]],"date-time":"2025-10-20T10:26:16Z","timestamp":1760955976076,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":49,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,10,15]],"date-time":"2019-10-15T00:00:00Z","timestamp":1571097600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"the Natural Science Foundation of China (NSFC)","award":["61673088"],"award-info":[{"award-number":["61673088"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,10,15]]},"DOI":"10.1145\/3343031.3350959","type":"proceedings-article","created":{"date-parts":[[2019,10,21]],"date-time":"2019-10-21T16:32:26Z","timestamp":1571675546000},"page":"574-582","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["Attention Transfer (ANT) Network for View-invariant Action Recognition"],"prefix":"10.1145","author":[{"given":"Yanli","family":"Ji","sequence":"first","affiliation":[{"name":"University of Electronic Science and Technology of China UESTC, Chengdu, China"}]},{"given":"Feixiang","family":"Xu","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China UESTC, Chengdu, China"}]},{"given":"Yang","family":"Yang","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China UESTC, Chengdu, China"}]},{"given":"Ning","family":"Xie","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China UESTC, Chengdu, China"}]},{"given":"Heng Tao","family":"Shen","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China UESTC, Chengdu, China"}]},{"given":"Tatsuya","family":"Harada","sequence":"additional","affiliation":[{"name":"The University of Tokyo, Tokyo, Japan"}]}],"member":"320","published-online":{"date-parts":[[2019,10,15]]},"reference":[{"doi-asserted-by":"publisher","key":"e_1_3_2_1_1_1","DOI":"10.1016\/j.patrec.2014.04.011"},{"unstructured":"F. Baradel C. Wolf and J. Mille. 2018. Human Activity Recognition with Pose-driven Attention to RGB. In BMVC.  F. Baradel C. Wolf and J. Mille. 2018. Human Activity Recognition with Pose-driven Attention to RGB. In BMVC.","key":"e_1_3_2_1_2_1"},{"unstructured":"Y. Bin Y. Yang F. Shen N. Xie H. T. Shen and X. Li. 2018. Describing Video with Attention based Bidirectional LSTM. IEEE Transactions on Cybernetics (2018). doi:10.1109\/TCYB.2018. 2831447.  Y. Bin Y. Yang F. Shen N. Xie H. T. Shen and X. Li. 2018. Describing Video with Attention based Bidirectional LSTM. IEEE Transactions on Cybernetics (2018). doi:10.1109\/TCYB.2018. 2831447.","key":"e_1_3_2_1_3_1"},{"doi-asserted-by":"crossref","unstructured":"Y. Du Y. Fu and L. Wang. 2015. Skeleton based action recognition with convolutional neural network. In ACPR.  Y. Du Y. Fu and L. Wang. 2015. Skeleton based action recognition with convolutional neural network. In ACPR.","key":"e_1_3_2_1_4_1","DOI":"10.1109\/ACPR.2015.7486569"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_5_1","DOI":"10.1109\/TAMD.2014.2303072"},{"doi-asserted-by":"crossref","unstructured":"A. Gupta J. Martinez J. J. Little and R. J. Woodham. 2014. 3D Pose from Motion for Cross-View Action Recognition via Non-linear Circulant Temporal Encoding. In CVPR.  A. Gupta J. Martinez J. J. Little and R. J. Woodham. 2014. 3D Pose from Motion for Cross-View Action Recognition via Non-linear Circulant Temporal Encoding. In CVPR.","key":"e_1_3_2_1_6_1","DOI":"10.1109\/CVPR.2014.333"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_7_1","DOI":"10.1109\/TPAMI.2016.2640292"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_8_1","DOI":"10.1109\/TNNLS.2011.2181865"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_9_1","DOI":"10.1016\/j.cviu.2006.10.019"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_10_1","DOI":"10.1016\/j.jvcir.2015.10.001"},{"doi-asserted-by":"crossref","unstructured":"Y. Ji A. Shimada H. Nagahara and R. Taniguchi. 2013. Contribution Estimation of Participants for Human Interaction Recognition. IEEJ Transactions on Electrical and Electronic Engineering 8(3) (May 2013) 269--276.  Y. Ji A. Shimada H. Nagahara and R. Taniguchi. 2013. Contribution Estimation of Participants for Human Interaction Recognition. IEEJ Transactions on Electrical and Electronic Engineering 8(3) (May 2013) 269--276.","key":"e_1_3_2_1_11_1","DOI":"10.1002\/tee.21850"},{"doi-asserted-by":"crossref","unstructured":"Y. Ji F. Xu Y. Yang F. Shen H. T. Shen and W. Zheng. 2018. A Large-scale RGB-D Database for Arbitrary-view Human Action Recognition. In ACM MM.  Y. Ji F. Xu Y. Yang F. Shen H. T. Shen and W. Zheng. 2018. A Large-scale RGB-D Database for Arbitrary-view Human Action Recognition. In ACM MM.","key":"e_1_3_2_1_12_1","DOI":"10.1145\/3240508.3240675"},{"doi-asserted-by":"crossref","unstructured":"Y. Ji Y. Yang F. Shen H. T. Shen and X. Li. 2019. A Survey of Human Action Analysis in HRI Applications. IEEE Transactions on Circuits and Systems for Video Technology (2019). https: \/\/doi.org\/DOI:10.1109\/TCSVT.2019.2912988 10.1109\/TCSVT.2019.2912988","key":"#cr-split#-e_1_3_2_1_13_1.1","DOI":"10.1109\/TCSVT.2019.2912988"},{"doi-asserted-by":"crossref","unstructured":"Y. Ji Y. Yang F. Shen H. T. Shen and X. Li. 2019. A Survey of Human Action Analysis in HRI Applications. IEEE Transactions on Circuits and Systems for Video Technology (2019). https: \/\/doi.org\/DOI:10.1109\/TCSVT.2019.2912988","key":"#cr-split#-e_1_3_2_1_13_1.2","DOI":"10.1109\/TCSVT.2019.2912988"},{"doi-asserted-by":"crossref","unstructured":"I. N. Junejo E. Dexter I. Laptev and P. Perez. 2008. Cross-View Action Recognition from Temporal Self-Similarities. In ECCV.  I. N. Junejo E. Dexter I. Laptev and P. Perez. 2008. Cross-View Action Recognition from Temporal Self-Similarities. In ECCV.","key":"e_1_3_2_1_14_1","DOI":"10.1007\/978-3-540-88688-4_22"},{"doi-asserted-by":"crossref","unstructured":"A. Kanehira L. V. Gool Y. Ushiku and T. Harada. 2018. Viewpoint-aware Video Summarization. In CVPR.  A. Kanehira L. V. Gool Y. Ushiku and T. Harada. 2018. Viewpoint-aware Video Summarization. In CVPR.","key":"e_1_3_2_1_15_1","DOI":"10.1109\/CVPR.2018.00776"},{"doi-asserted-by":"crossref","unstructured":"Q. Ke M. Bennamoun S. An F. Sohel and F. Boussaid. 2017. A new representation of skeleton sequences for 3d action recognition. In CVPR.  Q. Ke M. Bennamoun S. An F. Sohel and F. Boussaid. 2017. A new representation of skeleton sequences for 3d action recognition. In CVPR.","key":"e_1_3_2_1_16_1","DOI":"10.1109\/CVPR.2017.486"},{"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.","key":"e_1_3_2_1_17_1","DOI":"10.1109\/CVPRW.2017.207"},{"doi-asserted-by":"crossref","unstructured":"T. S. Kim and A. Reiter. 2017. Interpretable 3d human action analysis with temporal convolutional networks. In BNMW CVPRW.  T. S. Kim and A. Reiter. 2017. Interpretable 3d human action analysis with temporal convolutional networks. In BNMW CVPRW.","key":"e_1_3_2_1_18_1","DOI":"10.1109\/CVPRW.2017.207"},{"doi-asserted-by":"crossref","unstructured":"H. Koppula and A. Saxena. 2016. Anticipating Human Activities Using Object Affordances for Reactive Robotic Response. 38 1 (2016) 14--29.  H. Koppula and A. Saxena. 2016. Anticipating Human Activities Using Object Affordances for Reactive Robotic Response. 38 1 (2016) 14--29.","key":"e_1_3_2_1_19_1","DOI":"10.1109\/TPAMI.2015.2430335"},{"doi-asserted-by":"crossref","unstructured":"C. Li Q. Zhong D. Xie and S. Pu. 2018. Co-occurrence feature learning from skeleton data for action recognition and detection with hierarchical aggregation. In IJCAI.  C. Li Q. Zhong D. Xie and S. Pu. 2018. Co-occurrence feature learning from skeleton data for action recognition and detection with hierarchical aggregation. In IJCAI.","key":"e_1_3_2_1_20_1","DOI":"10.24963\/ijcai.2018\/109"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_21_1","DOI":"10.1109\/TCYB.2016.2582918"},{"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.","key":"e_1_3_2_1_22_1","DOI":"10.1109\/CVPR.2011.5995729"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_23_1","DOI":"10.1016\/j.patcog.2017.02.030"},{"unstructured":"M. Long Y. Cao J. Wang and M. I. Jordan. 2015. Learning Transferable Features with Deep Adaptation Networks. In ICML.  M. Long Y. Cao J. Wang and M. I. Jordan. 2015. Learning Transferable Features with Deep Adaptation Networks. In ICML.","key":"e_1_3_2_1_24_1"},{"doi-asserted-by":"crossref","unstructured":"B. Mahasseni and S. Todorovic. 2013. Latent Multitask Learning for View-Invariant Action Recognition. In ICCV.  B. Mahasseni and S. Todorovic. 2013. Latent Multitask Learning for View-Invariant Action Recognition. In ICCV.","key":"e_1_3_2_1_25_1","DOI":"10.1109\/ICCV.2013.388"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_26_1","DOI":"10.1109\/TKDE.2009.191"},{"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.","key":"e_1_3_2_1_27_1","DOI":"10.1109\/CVPR.2016.167"},{"volume-title":"ACM\/IEEE International Conference on Human-Robot Interaction.","author":"Ryoo M. S.","key":"e_1_3_2_1_28_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.","key":"e_1_3_2_1_29_1","DOI":"10.1109\/CVPR.2016.115"},{"doi-asserted-by":"crossref","unstructured":"X. Shen F. Shen Q. Sun Y. Yang Y. Yuan and H. T. Shen. 2017. Learning Latent Hash Codes for Semi-Paired Cross-View Retrieval: Learning Latent Hash Codes for Semi-paired Cross-view Retrieval. IEEE Transactions on Cybernetics 47(21) (2017) 4275--4288.  X. Shen F. Shen Q. Sun Y. Yang Y. Yuan and H. T. Shen. 2017. Learning Latent Hash Codes for Semi-Paired Cross-View Retrieval: Learning Latent Hash Codes for Semi-paired Cross-view Retrieval. IEEE Transactions on Cybernetics 47(21) (2017) 4275--4288.","key":"e_1_3_2_1_30_1","DOI":"10.1109\/TCYB.2016.2606441"},{"doi-asserted-by":"crossref","unstructured":"S. Song C. Lan J. Xing W. Zeng and J. Liu. 2017. An End-to- End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data. In AAAI.  S. Song C. Lan J. Xing W. Zeng and J. Liu. 2017. An End-to- End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data. In AAAI.","key":"e_1_3_2_1_31_1","DOI":"10.1609\/aaai.v31i1.11212"},{"doi-asserted-by":"crossref","unstructured":"Y. Tang Y. Tian J. Lu P. Li and J. Zhou. 2018. Deep Progressive Reinforcement Learning for Skeleton-based Action Recognition. In CVPR.  Y. Tang Y. Tian J. Lu P. Li and J. Zhou. 2018. Deep Progressive Reinforcement Learning for Skeleton-based Action Recognition. In CVPR.","key":"e_1_3_2_1_32_1","DOI":"10.1109\/CVPR.2018.00558"},{"unstructured":"K. Thakkar and P. J. Narayanan. 2018. Part-based graph convolutional network for action recognition. In BMVC.  K. Thakkar and P. J. Narayanan. 2018. Part-based graph convolutional network for action recognition. In BMVC.","key":"e_1_3_2_1_33_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_34_1","DOI":"10.1109\/TPAMI.2013.198"},{"doi-asserted-by":"crossref","unstructured":"J. Wang X. Nie Y. Xia Y. Wu and S.C. Zhu. 2014. Cross-View Action Modeling Learning and Recognition. In CVPR.  J. Wang X. Nie Y. Xia Y. Wu and S.C. Zhu. 2014. Cross-View Action Modeling Learning and Recognition. In CVPR.","key":"e_1_3_2_1_35_1","DOI":"10.1109\/CVPR.2014.339"},{"doi-asserted-by":"crossref","unstructured":"P. Wei Y. Zhao N. Zheng and S.C. Zhu. 2013. Modeling 4D Human-Object Interactions for Event and Object Recognition. In ICCV.  P. Wei Y. Zhao N. Zheng and S.C. Zhu. 2013. Modeling 4D Human-Object Interactions for Event and Object Recognition. In ICCV.","key":"e_1_3_2_1_36_1","DOI":"10.1109\/ICCV.2013.406"},{"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.","key":"e_1_3_2_1_37_1","DOI":"10.1109\/ICCV.2007.4408849"},{"doi-asserted-by":"crossref","unstructured":"D. Weinland R. Ronfard and E. Boyer. 2006. Free viewpoint action recognition using motion history volumes. Computer Vision and Image Understanding 104(2--3) (2006) 249--257.  D. Weinland R. Ronfard and E. Boyer. 2006. Free viewpoint action recognition using motion history volumes. Computer Vision and Image Understanding 104(2--3) (2006) 249--257.","key":"e_1_3_2_1_38_1","DOI":"10.1016\/j.cviu.2006.07.013"},{"doi-asserted-by":"crossref","unstructured":"L. Xia C. Chen and J. K. Aggarwal. 2012. View Invariant Human Action Recognition Using Histograms of 3D Joints. In CVPRW.  L. Xia C. Chen and J. K. Aggarwal. 2012. View Invariant Human Action Recognition Using Histograms of 3D Joints. In CVPRW.","key":"e_1_3_2_1_39_1","DOI":"10.1109\/CVPRW.2012.6239233"},{"doi-asserted-by":"crossref","unstructured":"X. Xu F. Shen Z. Huang Y. Yang L. He and J. Song. 2016. Cross-modal Retrieval with Label Completion. In ACM MM.  X. Xu F. Shen Z. Huang Y. Yang L. He and J. Song. 2016. Cross-modal Retrieval with Label Completion. In ACM MM.","key":"e_1_3_2_1_40_1","DOI":"10.1145\/2964284.2967231"},{"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_41_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.","key":"e_1_3_2_1_42_1","DOI":"10.1609\/aaai.v32i1.12328"},{"doi-asserted-by":"crossref","unstructured":"Y. Yang Y. Li C. Fermuler and Y. Aloimonos. 2015. Robot Learning Manipulation Action Plans by ?Watching\" Unconstrained Videos From the World Wide Web. In AAAI.  Y. Yang Y. Li C. Fermuler and Y. Aloimonos. 2015. Robot Learning Manipulation Action Plans by ?Watching\" Unconstrained Videos From the World Wide Web. In AAAI.","key":"e_1_3_2_1_43_1","DOI":"10.1609\/aaai.v29i1.9671"},{"doi-asserted-by":"crossref","unstructured":"M. Ye Q. Zhang L. Wang J. Zhu R. Yang and J. Gall. 2013. A survey on human motion analysis from depth data. In Time-of- Flight and depth imaging sensors algorithms and applications. Springer New York 149--187.  M. Ye Q. Zhang L. Wang J. Zhu R. Yang and J. Gall. 2013. A survey on human motion analysis from depth data. In Time-of- Flight and depth imaging sensors algorithms and applications. Springer New York 149--187.","key":"e_1_3_2_1_44_1","DOI":"10.1007\/978-3-642-44964-2_8"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_45_1","DOI":"10.1109\/TIP.2018.2836323"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_46_1","DOI":"10.1109\/TIP.2016.2548242"},{"doi-asserted-by":"crossref","unstructured":"X. Zhou F. Shen L. Liu W. Liu L. Nie Y. Yang and H. T. Shen. 2018. Graph Convolutional Network Hashing. (2018). https:\/\/doi.org\/10.1109\/TCYB.2018.2883970  X. Zhou F. Shen L. Liu W. Liu L. Nie Y. Yang and H. T. Shen. 2018. Graph Convolutional Network Hashing. (2018). https:\/\/doi.org\/10.1109\/TCYB.2018.2883970","key":"e_1_3_2_1_47_1","DOI":"10.1109\/TCYB.2018.2883970"},{"doi-asserted-by":"crossref","unstructured":"L. Zhu Z. Huang Z. Li L. Xie and H. T. Shen. 2018. Exploring Auxiliary Context: Discrete Semantic Transfer Hashing for Scalable Image Retrieval. TNNLS 29(11) (2018) 5264--5276.  L. Zhu Z. Huang Z. Li L. Xie and H. T. Shen. 2018. Exploring Auxiliary Context: Discrete Semantic Transfer Hashing for Scalable Image Retrieval. TNNLS 29(11) (2018) 5264--5276.","key":"e_1_3_2_1_48_1","DOI":"10.1109\/TNNLS.2018.2797248"}],"event":{"sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"acronym":"MM '19","name":"MM '19: The 27th ACM International Conference on Multimedia","location":"Nice France"},"container-title":["Proceedings of the 27th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3343031.3350959","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3343031.3350959","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:13:17Z","timestamp":1750201997000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3343031.3350959"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10,15]]},"references-count":49,"alternative-id":["10.1145\/3343031.3350959","10.1145\/3343031"],"URL":"https:\/\/doi.org\/10.1145\/3343031.3350959","relation":{},"subject":[],"published":{"date-parts":[[2019,10,15]]},"assertion":[{"value":"2019-10-15","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}