{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:33:06Z","timestamp":1750221186962,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":35,"publisher":"ACM","license":[{"start":{"date-parts":[[2018,11,17]],"date-time":"2018-11-17T00:00:00Z","timestamp":1542412800000},"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":[[2018,11,17]]},"DOI":"10.1145\/3297097.3297107","type":"proceedings-article","created":{"date-parts":[[2019,2,5]],"date-time":"2019-02-05T20:44:12Z","timestamp":1549399452000},"page":"12-17","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Recurrent Spatiotemporal Feature Learning for Action Recognition"],"prefix":"10.1145","author":[{"given":"Ze","family":"Chen","sequence":"first","affiliation":[{"name":"Key Laboratory of Shanghai Education Commission for Intelligence Interaction and Cognitive Engineering, Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, PR China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongtao","family":"Lu","sequence":"additional","affiliation":[{"name":"Key Laboratory of Shanghai Education Commission for Intelligence Interaction and Cognitive Engineering, Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, PR China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2018,11,17]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"ISCAS 2008","author":"Lin Weiyao","year":"2008","unstructured":"Lin , Weiyao , Sun , Ming-Ting , Poovandran , Radha , and Zhang , Zhengyou . Human activity recognition for video surveillance . In ISCAS 2008 . ( 2008 ), 2737--2740. Lin, Weiyao, Sun, Ming-Ting, Poovandran, Radha, and Zhang, Zhengyou. Human activity recognition for video surveillance. In ISCAS 2008. (2008), 2737--2740."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-006-0009-9"},{"key":"e_1_3_2_1_3_1","volume-title":"Advances in neural information processing systems","author":"Krizhevsky Alex","year":"2012","unstructured":"Krizhevsky , Alex , Sutskever , Ilya , and Hinton , Geoffrey E. Imagenet classification with deep convolutional neural networks . In Advances in neural information processing systems ( 2012 ), 1097--1105. Krizhevsky, Alex, Sutskever, Ilya, and Hinton, Geoffrey E. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems (2012), 1097--1105."},{"key":"e_1_3_2_1_4_1","volume-title":"Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556","author":"Simonyan Karen","year":"2014","unstructured":"Simonyan , Karen and Zisserman , Andrew . Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 ( 2014 ). Simonyan, Karen and Zisserman, Andrew. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Szegedy Christian Liu Wei Jia Yangqing et al. Going deeper with convolutions. (2015).  Szegedy Christian Liu Wei Jia Yangqing et al. Going deeper with convolutions. (2015).","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"e_1_3_2_1_8_1","volume-title":"Advances in neural information processing systems","author":"Simonyan Karen","year":"2014","unstructured":"Simonyan , Karen and Zisserman , Andrew . Two-stream convolutional networks for action recognition in videos . In Advances in neural information processing systems ( 2014 ), 568--576. Simonyan, Karen and Zisserman, Andrew. Two-stream convolutional networks for action recognition in videos. In Advances in neural information processing systems (2014), 568--576."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299176"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.65"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.5555\/1888028.1888059"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2013.2295753"},{"key":"e_1_3_2_1_13_1","volume-title":"Long short-term memory. Neural computation, 9","author":"Hochreiter Sepp","year":"1997","unstructured":"Hochreiter , Sepp and Schmidhuber , J\u00fcrgen . Long short-term memory. Neural computation, 9 ( 1997 ), 1735--1780. Hochreiter, Sepp and Schmidhuber, J\u00fcrgen. Long short-term memory. Neural computation, 9 (1997), 1735--1780."},{"key":"e_1_3_2_1_14_1","volume-title":"Acoustics, speech and signal processing (icassp)","author":"Graves Alex","year":"2013","unstructured":"Graves , Alex , Mohamed , Abdel-rahman, and Hinton , Geoffrey . Speech recognition with deep recurrent neural networks . In Acoustics, speech and signal processing (icassp) , 2013 ieee international conference on (2013), 6645--6649. Graves, Alex, Mohamed, Abdel-rahman, and Hinton, Geoffrey. Speech recognition with deep recurrent neural networks. In Acoustics, speech and signal processing (icassp), 2013 ieee international conference on (2013), 6645--6649."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-343"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299101"},{"key":"e_1_3_2_1_18_1","volume-title":"Advances in neural information processing systems","author":"Xingjian S. H. I.","year":"2015","unstructured":"Xingjian , S. H. I. , Chen , Zhourong , Wang , Hao , Yeung , Dit-Yan , Wong , Wai-Kin , and Woo , Wang-chun. Convolutional LSTM network: A machine learning approach for precipitation nowcasting . In Advances in neural information processing systems ( 2015 ), 802--810. Xingjian, S. H. I., Chen, Zhourong, Wang, Hao, Yeung, Dit-Yan, Wong, Wai-Kin, and Woo, Wang-chun. Convolutional LSTM network: A machine learning approach for precipitation nowcasting. In Advances in neural information processing systems (2015), 802--810."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.10.011"},{"key":"e_1_3_2_1_20_1","volume-title":"Lattice long short-term memory for human action recognition. arXiv preprint arXiv:1708.03958","author":"Sun Lin","year":"2017","unstructured":"Sun , Lin , Jia , Kui , Chen , Kevin , Yeung , Dit Yan , Shi , Bertram E., and Savarese , Silvio . Lattice long short-term memory for human action recognition. arXiv preprint arXiv:1708.03958 ( 2017 ). Sun, Lin, Jia, Kui, Chen, Kevin, Yeung, Dit Yan, Shi, Bertram E., and Savarese, Silvio. Lattice long short-term memory for human action recognition. arXiv preprint arXiv:1708.03958 (2017)."},{"key":"e_1_3_2_1_21_1","volume-title":"Advances in neural information processing systems","author":"Feichtenhofer Christoph","year":"2016","unstructured":"Feichtenhofer , Christoph , Pinz , Axel , and Wildes , Richard . Spatiotemporal residual networks for video action recognition . In Advances in neural information processing systems ( 2016 ), 3468--3476. Feichtenhofer, Christoph, Pinz, Axel, and Wildes, Richard. Spatiotemporal residual networks for video action recognition. In Advances in neural information processing systems (2016), 3468--3476."},{"key":"e_1_3_2_1_22_1","volume-title":"Advances in Neural Information Processing Systems","author":"Wang Jinzhuo","year":"2016","unstructured":"Wang , Jinzhuo , Wang , Wenmin , Wang , Ronggang , Gao , Wen , and others. Deep alternative neural network: Exploring contexts as early as possible for action recognition . In Advances in Neural Information Processing Systems ( 2016 ), 811--819. Wang, Jinzhuo, Wang, Wenmin, Wang, Ronggang, Gao, Wen, and others. Deep alternative neural network: Exploring contexts as early as possible for action recognition. In Advances in Neural Information Processing Systems (2016), 811--819."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.787"},{"volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016)","author":"Feichtenhofer Christoph","key":"e_1_3_2_1_24_1","unstructured":"Feichtenhofer , Christoph , Pinz , Axel , and Zisserman , Andrew . Convolutional two-stream network fusion for video action recognition . In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016) , 1933--1941. Feichtenhofer, Christoph, Pinz, Axel, and Zisserman, Andrew. Convolutional two-stream network fusion for video action recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016), 1933--1941."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"e_1_3_2_1_30_1","volume-title":"Karen et al. The kinetics human action video dataset. arXiv preprint arXiv:1705.06950","author":"Kay Will","year":"2017","unstructured":"Kay , Will , Carreira , Joao , Simonyan , Karen et al. The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 ( 2017 ). Kay, Will, Carreira, Joao, Simonyan, Karen et al. The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/72.279181"},{"key":"e_1_3_2_1_32_1","volume-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167","author":"Ioffe Sergey","year":"2015","unstructured":"Ioffe , Sergey and Szegedy , Christian . Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167 ( 2015 ). Ioffe, Sergey and Szegedy, Christian. Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167 (2015)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.5555\/1771530.1771554"},{"key":"e_1_3_2_1_34_1","volume-title":"UCF101: A dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402","author":"Soomro Khurram","year":"2012","unstructured":"Soomro , Khurram , Zamir , Amir Roshan , and Shah , Mubarak . UCF101: A dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402 ( 2012 ). Soomro, Khurram, Zamir, Amir Roshan, and Shah, Mubarak. UCF101: A dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402 (2012)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"}],"event":{"name":"ICRAI 2018: 2018 4th International Conference on Robotics and Artificial Intelligence","sponsor":["Guangdong University of Technology Guangdong University of Technology"],"location":"Guangzhou China","acronym":"ICRAI 2018"},"container-title":["Proceedings of the 2018 4th International Conference on Robotics and Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3297097.3297107","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3297097.3297107","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T01:39:08Z","timestamp":1750210748000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3297097.3297107"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,11,17]]},"references-count":35,"alternative-id":["10.1145\/3297097.3297107","10.1145\/3297097"],"URL":"https:\/\/doi.org\/10.1145\/3297097.3297107","relation":{},"subject":[],"published":{"date-parts":[[2018,11,17]]},"assertion":[{"value":"2018-11-17","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}