{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:35:28Z","timestamp":1750221328251,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":59,"publisher":"ACM","license":[{"start":{"date-parts":[[2017,10,23]],"date-time":"2017-10-23T00:00:00Z","timestamp":1508716800000},"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":[[2017,10,23]]},"DOI":"10.1145\/3126686.3126705","type":"proceedings-article","created":{"date-parts":[[2017,10,23]],"date-time":"2017-10-23T19:20:32Z","timestamp":1508786432000},"page":"287-295","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Spatiotemporal Multi-Task Network for Human Activity Understanding"],"prefix":"10.1145","author":[{"given":"Yao","family":"Liu","sequence":"first","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianqiang","family":"Huang","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chang","family":"Zhou","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Deng","family":"Cai","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xian-Sheng","family":"Hua","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2017,10,23]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.331"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_43"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_5_1","volume-title":"Ali Mohammad Pazandeh, and Luc Van Gool","author":"Diba Ali","year":"2016","unstructured":"Ali Diba , Ali Mohammad Pazandeh, and Luc Van Gool . 2016 . Efficient Two- Stream Motion and Appearance 3D CNNs for Video Classification . arXiv preprint arXiv:1608.08851 (2016). Ali Diba, Ali Mohammad Pazandeh, and Luc Van Gool. 2016. Efficient Two- Stream Motion and Appearance 3D CNNs for Video Classification. arXiv preprint arXiv:1608.08851 (2016)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"e_1_3_2_1_7_1","volume-title":"Convolutional Two-Stream Network Fusion for Video Action Recognition. arXiv preprint arXiv:1604.06573","author":"Feichtenhofer Christoph","year":"2016","unstructured":"Christoph Feichtenhofer , Axel Pinz , and Andrew Zisserman . 2016. Convolutional Two-Stream Network Fusion for Video Action Recognition. arXiv preprint arXiv:1604.06573 ( 2016 ). Christoph Feichtenhofer, Axel Pinz, and Andrew Zisserman. 2016. Convolutional Two-Stream Network Fusion for Video Action Recognition. arXiv preprint arXiv:1604.06573 (2016)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299176"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995646"},{"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":"10.1109\/ICCV.2015.169"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298676"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10578-9_23"},{"key":"e_1_3_2_1_14_1","volume-title":"Deep residual learning for image recognition. arXiv preprint arXiv:1512.03385","author":"He Kaiming","year":"2015","unstructured":"Kaiming He , Xiangyu Zhang , Shaoqing Ren , and Jian Sun . 2015. Deep residual learning for image recognition. arXiv preprint arXiv:1512.03385 ( 2015 ). Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2015. Deep residual learning for image recognition. arXiv preprint arXiv:1512.03385 (2015)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.100"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"e_1_3_2_1_18_1","volume-title":"ECCV THUMOS Workshop","volume":"1","author":"Karaman Svebor","year":"2014","unstructured":"Svebor Karaman , Lorenzo Seidenari , and Alberto Del Bimbo . 2014 . Fast saliency based pooling of Fisher encoded dense trajectories . In ECCV THUMOS Workshop , Vol. 1 . 6. Svebor Karaman, Lorenzo Seidenari, and Alberto Del Bimbo. 2014. Fast saliency based pooling of Fisher encoded dense trajectories. In ECCV THUMOS Workshop, Vol. 1. 6."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"e_1_3_2_1_20_1","unstructured":"Alex Krizhevsky Ilya Sutskever and Geoffrey E Hinton. 2012. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems. 1097--1105.   Alex Krizhevsky Ilya Sutskever and Geoffrey E Hinton. 2012. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems. 1097--1105."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-005-1838-7"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/2911996.2912001"},{"key":"e_1_3_2_1_23_1","volume-title":"Online Human Action Detection using Joint Classification- Regression Recurrent Neural Networks. arXiv preprint arXiv:1604.05633","author":"Li Yanghao","year":"2016","unstructured":"Yanghao Li , Cuiling Lan , Junliang Xing , Wenjun Zeng , Chunfeng Yuan , and Jiaying Liu . 2016. Online Human Action Detection using Joint Classification- Regression Recurrent Neural Networks. arXiv preprint arXiv:1604.05633 ( 2016 ). Yanghao Li, Cuiling Lan, Junliang Xing, Wenjun Zeng, Chunfeng Yuan, and Jiaying Liu. 2016. Online Human Action Detection using Joint Classification- Regression Recurrent Neural Networks. arXiv preprint arXiv:1604.05633 (2016)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.5555\/1888028.1888059"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.228"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.326"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.376"},{"key":"e_1_3_2_1_28_1","volume-title":"Detecting events and key actors in multiperson videos. arXiv preprint arXiv:1511.02917","author":"Ramanathan Vignesh","year":"2015","unstructured":"Vignesh Ramanathan , Jonathan Huang , Sami Abu-El-Haija , Alexander Gorban , Kevin Murphy , and Li Fei-Fei . 2015. Detecting events and key actors in multiperson videos. arXiv preprint arXiv:1511.02917 ( 2015 ). Vignesh Ramanathan, Jonathan Huang, Sami Abu-El-Haija, Alexander Gorban, Kevin Murphy, and Li Fei-Fei. 2015. Detecting events and key actors in multiperson videos. arXiv preprint arXiv:1511.02917 (2015)."},{"key":"e_1_3_2_1_29_1","volume-title":"Hyperface: A deep multi-task learning framework for face detection, landmark localization, pose estimation, and gender recognition. arXiv preprint arXiv:1603.01249","author":"Ranjan Rajeev","year":"2016","unstructured":"Rajeev Ranjan , Vishal M Patel , and Rama Chellappa . 2016 . Hyperface: A deep multi-task learning framework for face detection, landmark localization, pose estimation, and gender recognition. arXiv preprint arXiv:1603.01249 (2016). Rajeev Ranjan, Vishal M Patel, and Rama Chellappa. 2016. Hyperface: A deep multi-task learning framework for face detection, landmark localization, pose estimation, and gender recognition. arXiv preprint arXiv:1603.01249 (2016)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.5555\/2354409.2354938"},{"key":"e_1_3_2_1_31_1","unstructured":"Shaoqing Ren Kaiming He Ross Girshick and Jian Sun. 2015. Faster R-CNN: Towards real-time object detection with region proposal networks. In Advances in neural information processing systems. 91--99.   Shaoqing Ren Kaiming He Ross Girshick and Jian Sun. 2015. Faster R-CNN: Towards real-time object detection with region proposal networks. In Advances in neural information processing systems. 91--99."},{"key":"e_1_3_2_1_32_1","unstructured":"Zheng Shou Dongang Wang and Shih-Fu Chang. Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs. (????).  Zheng Shou Dongang Wang and Shih-Fu Chang. Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs. (????)."},{"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 Advances in Neural Information Processing Systems. 568--576.   Karen Simonyan and Andrew Zisserman. 2014. Two-stream convolutional networks for action recognition in videos. In Advances in Neural Information Processing Systems. 568--576."},{"key":"e_1_3_2_1_34_1","volume-title":"Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman . 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 ( 2014 ). Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.5555\/2919332.2919828"},{"key":"e_1_3_2_1_36_1","unstructured":"K. Soomro A. Roshan Zamir and M. Shah. 2012. UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild. In CRCV-TR-12-01.  K. Soomro A. Roshan Zamir and M. Shah. 2012. UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild. In CRCV-TR-12-01."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.522"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"e_1_3_2_1_39_1","volume-title":"Rethinking the inception architecture for computer vision. arXiv preprint arXiv:1512.00567","author":"Szegedy Christian","year":"2015","unstructured":"Christian Szegedy , Vincent Vanhoucke , Sergey Ioffe , Jonathon Shlens , and Zbigniew Wojna . 2015. Rethinking the inception architecture for computer vision. arXiv preprint arXiv:1512.00567 ( 2015 ). Christian Szegedy, Vincent Vanhoucke, Sergey Ioffe, Jonathon Shlens, and Zbigniew Wojna. 2015. Rethinking the inception architecture for computer vision. arXiv preprint arXiv:1512.00567 (2015)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"e_1_3_2_1_41_1","volume-title":"Long-term Temporal Convolutions for Action Recognition. arXiv preprint arXiv:1604.04494","author":"Varol G\u00fcl","year":"2016","unstructured":"G\u00fcl Varol , Ivan Laptev , and Cordelia Schmid . 2016. Long-term Temporal Convolutions for Action Recognition. arXiv preprint arXiv:1604.04494 ( 2016 ). G\u00fcl Varol, Ivan Laptev, and Cordelia Schmid. 2016. Long-term Temporal Convolutions for Action Recognition. arXiv preprint arXiv:1604.04494 (2016)."},{"key":"e_1_3_2_1_42_1","volume-title":"International journal of computer vision 103, 1","author":"Kl\u00e4ser Alexander","year":"2013","unstructured":"HengWang, Alexander Kl\u00e4ser , Cordelia Schmid , and Cheng-Lin Liu . 2013. Dense trajectories and motion boundary descriptors for action recognition . International journal of computer vision 103, 1 ( 2013 ), 60--79. HengWang, Alexander Kl\u00e4ser, Cordelia Schmid, and Cheng-Lin Liu. 2013. Dense trajectories and motion boundary descriptors for action recognition. International journal of computer vision 103, 1 (2013), 60--79."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"key":"e_1_3_2_1_44_1","volume-title":"Action recognition and detection by combining motion and appearance features. THUMOS14 Action Recognition Challenge 1","author":"Wang Limin","year":"2014","unstructured":"Limin Wang , Yu Qiao , and Xiaoou Tang . 2014. Action recognition and detection by combining motion and appearance features. THUMOS14 Action Recognition Challenge 1 ( 2014 ), 2. Limin Wang, Yu Qiao, and Xiaoou Tang. 2014. Action recognition and detection by combining motion and appearance features. THUMOS14 Action Recognition Challenge 1 (2014), 2."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2013.2295753"},{"key":"e_1_3_2_1_46_1","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 4305--4314","author":"Qiao Yu","year":"2015","unstructured":"LiminWang, Yu Qiao , and Xiaoou Tang . 2015 . Action recognition with trajectorypooled deep-convolutional descriptors . In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 4305--4314 . LiminWang, Yu Qiao, and Xiaoou Tang. 2015. Action recognition with trajectorypooled deep-convolutional descriptors. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 4305--4314."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"e_1_3_2_1_48_1","volume-title":"Temporal pyramid pooling based convolutional neural networks for action recognition. arXiv preprint arXiv:1503.01224","author":"Wang Peng","year":"2015","unstructured":"Peng Wang , Yuanzhouhan Cao , Chunhua Shen , Lingqiao Liu , and Heng Tao Shen . 2015. Temporal pyramid pooling based convolutional neural networks for action recognition. arXiv preprint arXiv:1503.01224 ( 2015 ). Peng Wang, Yuanzhouhan Cao, Chunhua Shen, Lingqiao Liu, and Heng Tao Shen. 2015. Temporal pyramid pooling based convolutional neural networks for action recognition. arXiv preprint arXiv:1503.01224 (2015)."},{"key":"e_1_3_2_1_49_1","volume-title":"Fusing Multi-Stream Deep Networks for Video Classification. arXiv preprint arXiv:1509.06086","author":"Wu Zuxuan","year":"2015","unstructured":"Zuxuan Wu , Yu-Gang Jiang , Xi Wang , Hao Ye , Xiangyang Xue , and Jun Wang . 2015. Fusing Multi-Stream Deep Networks for Video Classification. arXiv preprint arXiv:1509.06086 ( 2015 ). Zuxuan Wu, Yu-Gang Jiang, Xi Wang, Hao Ye, Xiangyang Xue, and Jun Wang. 2015. Fusing Multi-Stream Deep Networks for Video Classification. arXiv preprint arXiv:1509.06086 (2015)."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298789"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.512"},{"key":"e_1_3_2_1_52_1","volume-title":"End-to-end Learning of Action Detection from Frame Glimpses in Videos. arXiv preprint arXiv:1511.06984","author":"Yeung Serena","year":"2015","unstructured":"Serena Yeung , Olga Russakovsky , Greg Mori , and Li Fei-Fei . 2015. End-to-end Learning of Action Detection from Frame Glimpses in Videos. arXiv preprint arXiv:1511.06984 ( 2015 ). Serena Yeung, Olga Russakovsky, Greg Mori, and Li Fei-Fei. 2015. End-to-end Learning of Action Detection from Frame Glimpses in Videos. arXiv preprint arXiv:1511.06984 (2015)."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299101"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.5555\/1771530.1771554"},{"key":"e_1_3_2_1_55_1","volume-title":"Exploiting image-trained cnn architectures for unconstrained video classification. arXiv preprint arXiv:1503.04144","author":"Zha Shengxin","year":"2015","unstructured":"Shengxin Zha , Florian Luisier , Walter Andrews , Nitish Srivastava , and Ruslan Salakhutdinov . 2015. Exploiting image-trained cnn architectures for unconstrained video classification. arXiv preprint arXiv:1503.04144 ( 2015 ). Shengxin Zha, Florian Luisier, Walter Andrews, Nitish Srivastava, and Ruslan Salakhutdinov. 2015. Exploiting image-trained cnn architectures for unconstrained video classification. arXiv preprint arXiv:1503.04144 (2015)."},{"key":"e_1_3_2_1_56_1","volume-title":"Realtime Action Recognition with Enhanced Motion Vector CNNs. arXiv preprint arXiv:1604.07669","author":"Zhang Bowen","year":"2016","unstructured":"Bowen Zhang , Limin Wang , Zhe Wang , Yu Qiao , and Hanli Wang . 2016. Realtime Action Recognition with Enhanced Motion Vector CNNs. arXiv preprint arXiv:1604.07669 ( 2016 ). Bowen Zhang, Limin Wang, Zhe Wang, Yu Qiao, and Hanli Wang. 2016. Realtime Action Recognition with Enhanced Motion Vector CNNs. arXiv preprint arXiv:1604.07669 (2016)."},{"key":"e_1_3_2_1_57_1","volume-title":"ECCV Workshop proceedings","author":"Zhang Chen-Lin","year":"2016","unstructured":"Chen-Lin Zhang , Hao Zhang , Xiu-ShenWei, and JianxinWu. 2016 . Deep Bimodal Regression for Apparent Personality Analysis?. In ChaLearn Looking at People Workshop on Apparent Personality Analysis , ECCV Workshop proceedings , p. in press. Springer Science+ Business Media. Chen-Lin Zhang, Hao Zhang, Xiu-ShenWei, and JianxinWu. 2016. Deep Bimodal Regression for Apparent Personality Analysis?. In ChaLearn Looking at People Workshop on Apparent Personality Analysis, ECCV Workshop proceedings, p. in press. Springer Science+ Business Media."},{"key":"e_1_3_2_1_58_1","volume-title":"Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks. arXiv preprint arXiv:1604.02878","author":"Zhang Kaipeng","year":"2016","unstructured":"Kaipeng Zhang , Zhanpeng Zhang , Zhifeng Li , and Yu Qiao . 2016. Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks. arXiv preprint arXiv:1604.02878 ( 2016 ). Kaipeng Zhang, Zhanpeng Zhang, Zhifeng Li, and Yu Qiao. 2016. Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks. arXiv preprint arXiv:1604.02878 (2016)."},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.219"}],"event":{"name":"MM '17: ACM Multimedia Conference","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Mountain View California USA","acronym":"MM '17"},"container-title":["Proceedings of the on Thematic Workshops of ACM Multimedia 2017"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3126686.3126705","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3126686.3126705","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T02:14:05Z","timestamp":1750212845000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3126686.3126705"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,10,23]]},"references-count":59,"alternative-id":["10.1145\/3126686.3126705","10.1145\/3126686"],"URL":"https:\/\/doi.org\/10.1145\/3126686.3126705","relation":{},"subject":[],"published":{"date-parts":[[2017,10,23]]},"assertion":[{"value":"2017-10-23","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}