{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T10:18:21Z","timestamp":1789726701543,"version":"4.0.1"},"publisher-location":"New York, NY, USA","reference-count":43,"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":"The National Natural Science Foundation of China","award":["Grant No. 61522203 61772275 61702265 and 61732007"],"award-info":[{"award-number":["Grant No. 61522203 61772275 61702265 and 61732007"]}]},{"name":"The CCF-Tencent Open Research Fund"},{"name":"The 973 Program","award":["Grant No. 2014CB347600"],"award-info":[{"award-number":["Grant No. 2014CB347600"]}]},{"name":"The Natural Science Foundation of Jiangsu Province","award":["Grant No. BK20170856 and BK20170033"],"award-info":[{"award-number":["Grant No. BK20170856 and BK20170033"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2018,10,15]]},"DOI":"10.1145\/3240508.3240572","type":"proceedings-article","created":{"date-parts":[[2018,10,18]],"date-time":"2018-10-18T13:52:08Z","timestamp":1539870728000},"page":"1292-1300","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":127,"title":["Participation-Contributed Temporal Dynamic Model for Group Activity Recognition"],"prefix":"10.1145","author":[{"given":"Rui","family":"Yan","sequence":"first","affiliation":[{"name":"Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinhui","family":"Tang","sequence":"additional","affiliation":[{"name":"Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangbo","family":"Shu","sequence":"additional","affiliation":[{"name":"Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zechao","family":"Li","sequence":"additional","affiliation":[{"name":"Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Tian","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab& University of Texas at San Antonio, HongKong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2018,10,15]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"crossref","unstructured":"Mohamed Rabie Amer Peng Lei and Sinisa Todorovic. 2014. HiRF: Hierarchical Random Field for Collective Activity Recognition in Videos. In ECCV .  Mohamed Rabie Amer Peng Lei and Sinisa Todorovic. 2014. HiRF: Hierarchical Random Field for Collective Activity Recognition in Videos. In ECCV .","DOI":"10.1007\/978-3-319-10599-4_37"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Jain Ashesh Zamir Amir Roshan Savarese Silvio and Saxena Ashutosh. 2016. Structural-RNN: Deep Learning on Spatio-Temporal Graphs. In CVPR .  Jain Ashesh Zamir Amir Roshan Savarese Silvio and Saxena Ashutosh. 2016. Structural-RNN: Deep Learning on Spatio-Temporal Graphs. In CVPR .","DOI":"10.1109\/CVPR.2016.573"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Timur M. Bagautdinov Alexandre Alahi Fran\u00e7ois Fleuret Pascal Fua and Silvio Savarese. 2017. Social Scene Understanding: End-to-End Multi-person Action Localization and Collective Activity Recognition. In CVPR .  Timur M. Bagautdinov Alexandre Alahi Fran\u00e7ois Fleuret Pascal Fua and Silvio Savarese. 2017. Social Scene Understanding: End-to-End Multi-person Action Localization and Collective Activity Recognition. In CVPR .","DOI":"10.1109\/CVPR.2017.365"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","unstructured":"Sovan Biswas and Juergen Gall. 2018. Structural Recurrent Neural Network (SRNN) for Group Activity Analysis. arXiv preprint arXiv:1802.02091 (2018).  Sovan Biswas and Juergen Gall. 2018. Structural Recurrent Neural Network (SRNN) for Group Activity Analysis. arXiv preprint arXiv:1802.02091 (2018).","DOI":"10.1109\/WACV.2018.00180"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Thomas Brox Andr\u00e9s Bruhn Nils Papenberg and Joachim Weickert. 2004. High Accuracy Optical Flow Estimation Based on a Theory for Warping. In ECCV .  Thomas Brox Andr\u00e9s Bruhn Nils Papenberg and Joachim Weickert. 2004. High Accuracy Optical Flow Estimation Based on a Theory for Warping. In ECCV .","DOI":"10.1007\/978-3-540-24673-2_3"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33765-9_16"},{"key":"e_1_3_2_1_7_1","volume-title":"ICCV Workshops .","author":"Choi Wongun","year":"2009"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995707"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"crossref","unstructured":"Martin Danelljan Gustav H\u00e4ger Fahad Khan and Michael Felsberg. 2014. Accurate Scale Estimation for Robust Visual Tracking. In BMVC .  Martin Danelljan Gustav H\u00e4ger Fahad Khan and Michael Felsberg. 2014. Accurate Scale Estimation for Robust Visual Tracking. In BMVC .","DOI":"10.5244\/C.28.65"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"Zhiwei Deng Arash Vahdat Hexiang Hu and Greg Mori. 2016. Structure Inference Machines: Recurrent Neural Networks for Analyzing Relations in Group Activity Recognition. In CVPR .  Zhiwei Deng Arash Vahdat Hexiang Hu and Greg Mori. 2016. Structure Inference Machines: Recurrent Neural Networks for Analyzing Relations in Group Activity Recognition. In CVPR .","DOI":"10.1109\/CVPR.2016.516"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"Zhiwei Deng Mengyao Zhai Lei Chen Yuhao Liu Srikanth Muralidharan Mehrsan Javan Roshtkhari and Greg Mori. 2015. Deep structured models for group activity recognition. In BMVC .  Zhiwei Deng Mengyao Zhai Lei Chen Yuhao Liu Srikanth Muralidharan Mehrsan Javan Roshtkhari and Greg Mori. 2015. Deep structured models for group activity recognition. In BMVC .","DOI":"10.5244\/C.29.179"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","unstructured":"Jeffrey Donahue Lisa Anne Hendricks Sergio Guadarrama Marcus Rohrbach Subhashini Venugopalan Kate Saenko and Trevor Darrell. 2015. Long-term recurrent convolutional networks for visual recognition and description. In CVPR .  Jeffrey Donahue Lisa Anne Hendricks Sergio Guadarrama Marcus Rohrbach Subhashini Venugopalan Kate Saenko and Trevor Darrell. 2015. Long-term recurrent convolutional networks for visual recognition and description. In CVPR .","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Hossein Hajimirsadeghi Wang Yan Arash Vahdat and Greg Mori. 2015. Visual recognition by counting instances: A multi-instance cardinality potential kernel. In CVPR .  Hossein Hajimirsadeghi Wang Yan Arash Vahdat and Greg Mori. 2015. Visual recognition by counting instances: A multi-instance cardinality potential kernel. In CVPR .","DOI":"10.1109\/CVPR.2015.7298875"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123321"},{"key":"e_1_3_2_1_15_1","unstructured":"Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2016. Deep Residual Learning for Image Recognition. In CVPR .  Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2016. Deep Residual Learning for Image Recognition. In CVPR ."},{"key":"e_1_3_2_1_16_1","unstructured":"Hexiang Hu Guang-Tong Zhou Zhiwei Deng Zicheng Liao and Greg Mori. 2016. Learning Structured Inference Neural Networks with Label Relations. In CVPR .  Hexiang Hu Guang-Tong Zhou Zhiwei Deng Zicheng Liao and Greg Mori. 2016. Learning Structured Inference Neural Networks with Label Relations. In CVPR ."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"crossref","unstructured":"Moustafa Ibrahim Srikanth Muralidharan Zhiwei Deng Arash Vahdat and Greg Mori. 2016. A Hierarchical Deep Temporal Model for Group Activity Recognition. In CVPR .  Moustafa Ibrahim Srikanth Muralidharan Zhiwei Deng Arash Vahdat and Greg Mori. 2016. A Hierarchical Deep Temporal Model for Group Activity Recognition. In CVPR .","DOI":"10.1109\/CVPR.2016.217"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2670560"},{"key":"e_1_3_2_1_19_1","volume-title":"Dlib-ml: A Machine Learning Toolkit .JMLR.org. 1755--1758 pages.","author":"King Davis E.","year":"2009"},{"key":"e_1_3_2_1_20_1","volume-title":"Adam: A Method for Stochastic Optimization. In ICLR .","author":"Kingma Diederik","year":"2015"},{"key":"e_1_3_2_1_21_1","unstructured":"Alex Krizhevsky Ilya Sutskever and Geoffrey E. Hinton. 2012. ImageNet classification with deep convolutional neural networks. In NIPS .   Alex Krizhevsky Ilya Sutskever and Geoffrey E. Hinton. 2012. ImageNet classification with deep convolutional neural networks. In NIPS ."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"crossref","unstructured":"Tian Lan Lei Chen Zhiwei Deng Guang-Tong Zhou and Greg Mori. 2014. Learning Action Primitives for Multi-level Video Event Understanding. In ECCV .  Tian Lan Lei Chen Zhiwei Deng Guang-Tong Zhou and Greg Mori. 2014. Learning Action Primitives for Multi-level Video Event Understanding. In ECCV .","DOI":"10.1007\/978-3-319-16199-0_7"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"crossref","unstructured":"Tian Lan Leonid Sigal and Greg Mori. 2012a. Social roles in hierarchical models for human activity recognition. In CVPR .  Tian Lan Leonid Sigal and Greg Mori. 2012a. Social roles in hierarchical models for human activity recognition. In CVPR .","DOI":"10.1109\/CVPR.2012.6247821"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.228"},{"key":"e_1_3_2_1_25_1","volume-title":"SBGAR: Semantics Based Group Activity Recognition. In ICCV .","author":"Li Xin","year":"2017"},{"key":"e_1_3_2_1_26_1","unstructured":"Zechao Li Jinhui Tang and Tao Mei. 2018. Deep Collaborative Embedding for Social Image Understanding. IEEE transactions on pattern analysis and machine intelligence (2018).  Zechao Li Jinhui Tang and Tao Mei. 2018. Deep Collaborative Embedding for Social Image Understanding. IEEE transactions on pattern analysis and machine intelligence (2018)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"crossref","unstructured":"Bingbing Ni Shuicheng Yan and Ashraf A. Kassim. 2009. Recognizing human group activities with localized causalities. In CVPR .  Bingbing Ni Shuicheng Yan and Ashraf A. Kassim. 2009. Recognizing human group activities with localized causalities. In CVPR .","DOI":"10.1109\/CVPR.2009.5206853"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","unstructured":"Vignesh Ramanathan Jonathan Huang Sami Abuelhaija Alexander Gorban Kevin Murphy and Fei Fei Li. 2016. Detecting Events and Key Actors in Multi-person Videos. In CVPR .  Vignesh Ramanathan Jonathan Huang Sami Abuelhaija Alexander Gorban Kevin Murphy and Fei Fei Li. 2016. Detecting Events and Key Actors in Multi-person Videos. In CVPR .","DOI":"10.1109\/CVPR.2016.332"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123379"},{"key":"e_1_3_2_1_30_1","unstructured":"Tianmin Shu Sinisa Todorovic and Song-Chun Zhu. 2017b. CERN: confidence-energy recurrent network for group activity recognition. In CVPR .  Tianmin Shu Sinisa Todorovic and Song-Chun Zhu. 2017b. CERN: confidence-energy recurrent network for group activity recognition. In CVPR ."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2705122"},{"key":"e_1_3_2_1_32_1","volume-title":"Concurrence-Aware Long Short-Term Sub-Memories for Person-Person Action Recognition. In CVPR Workshops .","author":"Shu Xiangbo","year":"2017"},{"key":"e_1_3_2_1_33_1","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Two-stream convolutional networks for action recognition in videos. In NIPS .   Karen Simonyan and Andrew Zisserman. 2014. Two-stream convolutional networks for action recognition in videos. In NIPS ."},{"key":"e_1_3_2_1_34_1","unstructured":"Karen Simonyan and Andrew Zisserman. 2015. Very Deep Convolutional Networks for Large-Scale Image Recognition. In ICLR .  Karen Simonyan and Andrew Zisserman. 2015. Very Deep Convolutional Networks for Large-Scale Image Recognition. In ICLR ."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"crossref","unstructured":"Christian Szegedy Wei Liu Yangqing Jia Pierre Sermanet Scott E Reed Dragomir Anguelov Dumitru Erhan Vincent Vanhoucke and Andrew Rabinovich. 2015. Going deeper with convolutions. In CVPR .  Christian Szegedy Wei Liu Yangqing Jia Pierre Sermanet Scott E Reed Dragomir Anguelov Dumitru Erhan Vincent Vanhoucke and Andrew Rabinovich. 2015. Going deeper with convolutions. In CVPR .","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2476660"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/2998574"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"crossref","unstructured":"Heng Wang Muhammad Muneeb Ullah Alexander Klaser Ivan Laptev and Cordelia Schmid. 2009. Evaluation of local spatio-temporal features for action recognition. In BMVC .  Heng Wang Muhammad Muneeb Ullah Alexander Klaser Ivan Laptev and Cordelia Schmid. 2009. Evaluation of local spatio-temporal features for action recognition. In BMVC .","DOI":"10.5244\/C.23.124"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"crossref","unstructured":"Minsi Wang Bingbing Ni and Xiaokang Yang. 2017. Recurrent Modeling of Interaction Context for Collective Activity Recognition. In CVPR .  Minsi Wang Bingbing Ni and Xiaokang Yang. 2017. Recurrent Modeling of Interaction Context for Collective Activity Recognition. In CVPR .","DOI":"10.1109\/CVPR.2017.783"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2010.10.002"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502089"},{"key":"e_1_3_2_1_42_1","unstructured":"Yichao Yan Bingbing Ni and Xiaokang Yang. 2017. Predicting Human Interaction via Relative Attention Model. In IJCAI .   Yichao Yan Bingbing Ni and Xiaokang Yang. 2017. Predicting Human Interaction via Relative Attention Model. In IJCAI ."},{"key":"e_1_3_2_1_43_1","unstructured":"Zheng Zhou Kan Li Xiangjian He and Mengmeng Li. 2016. A generative model for recognizing mixed group activities in still images. In IJCAI .   Zheng Zhou Kan Li Xiangjian He and Mengmeng Li. 2016. A generative model for recognizing mixed group activities in still images. In IJCAI ."}],"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\/3240508.3240572","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3240508.3240572","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:57:33Z","timestamp":1750193853000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3240508.3240572"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,10,15]]},"references-count":43,"alternative-id":["10.1145\/3240508.3240572","10.1145\/3240508"],"URL":"https:\/\/doi.org\/10.1145\/3240508.3240572","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"}}]}}