·972· 智能系统学报 第13卷 36-58. IEEE International Conference on Computer Vision.San- LI Hang.Statistical learning method[M].Beijing:Tsinghua tiago,.Chile,2015:1080-1088 University Press.2012:36-58. [14]KHAN F S,VAN DE WEIJER J,ANWER R M,et al [4]张文达，许悦雷，倪嘉成，等.基于多尺度分块卷积神经 Semantic pyramids for gender and action recognition[]. 网络的图像目标识别算法[).计算机应用，2016,36(4)： IEEE transactions on image processing,2014,23(8): 1033-1038 3633-3645. ZHANG Wenda,XU Yuelei,NI Jiacheng,et al.Image tar- [15]FEICHTENHOFER C,PINZ A,WILDES R P.Spati- get recognition method based on multi-scale block convo- otemporal multiplier networks for video action recogni- lutional neural network[J].Journal of computer applica- tion[C]//Proceedings of 2017 IEEE Conference on Com- tions,.2016.36(4):1033-1038 puter Vision and Pattern Recognition.Honolulu,USA, [5]GIRSHICK R.Fast R-CNN[C]//Proceedings of 2015 IEEE 2017:7445-7454. International Conference on Computer Vision.Santiago, [16]GKIOXARI G,GIRSHICK R,MALIK J.Actions and at- Chile,.2015:1440-1448. tributes from wholes and parts[C]//Proceedings of 2015 [6]REN Shaoqing,HE Kaiming,GIRSHICK R,et al.Faster IEEE International Conference on Computer Vision.San- R-CNN:towards real-time object detection with region tiago,.Chile,2015:2470-2478. proposal networks[C]//Proceedings of the 28th Internation- [17]KAR A,RAI N,SIKKA K,et al.Adascan:adaptive scan al Conference on Neural Information Processing Systems. pooling in deep convolutional neural networks for human Montreal,Canada,2015:91-99. action recognition in videos[C]//Proceedings of 2017 [7]HE Kaiming,ZHANG Xiangyu,REN Shaoqing,et al.Spa- IEEE Conference on Computer Vision and Pattern Recog- tial pyramid pooling in deep convolutional networks for nition.Honolulu,USA,2017:5699-5708. visual recognition[C]//Proceedings of the 13th European [18]FEICHTENHOFER C,PINZ A,WILDES R P.Spati- Conference on Computer Vision.Zurich,Switzerland, otemporal residual networks for video action recognition 2014:346-361. [C]//Proceedings of the 30th Conference on Neural In- [8]JI Shuiwang,XU Wei,YANG Ming,et al.3D convolu- formation Processing Systems.Barcelona,Spain,2016: tional neural networks for automatic human action recogni- 3468-3476. tion[P].USA:8345984,2013 [9]KARPATHY A,TODERICI G,SHETTY S,et al.Large- [19]HERATH S,HARANDI M,PORIKLI F.Going deeper scale video classification with convolutional neural net- into action recognition:a survey[J].Image and vision computing,2017,60:4-21. works[Cl//Proceedings of 2014 IEEE Conference on Com- [20]邓利群.三维人体动作识别及其在交互舞蹈系统上的 puter Vision and Pattern Recognition.Columbus,USA, 2014:1725-1732 应用D].合肥：中国科学技术大学，2012 [10]SUN Lin,JIA Kui,CHAN T H,et al.DL-SFA:deeply- DENG Liqun.3D mocap data recognition and its applica- learned slow feature analysis for action recognition[C]/ tion on interactive dancing game[D].Hefei:University of Proceedings of 2014 IEEE Conference on Computer Vis- Science and Technology of China,2012 ion and Pattern Recognition.Columbus,USA,2014: [21]申晓霞，张桦，高赞，等.基于深度信息和RGB图像的 2625-2632. 行为识别算法[J.模式识别与人工智能，2013,26(8)： [11]DONAHUE J,HENDRICKS L A,GUADARRAMA S, 722-728 et al.Long-term recurrent convolutional networks for SHEN Xiaoxia,ZHANG Hua,GAO Zan,et al.Behavior visual recognition and description[C]//Proceedings of recognition algorithm based on depth information and 2015 IEEE Conference on Computer Vision and Pattern RGB image[J].Pattern recognition and artificial intelli- Recognition.Boston,USA,2015:2625-2634. gence,.2013,26(8):722-728. [12]GKIOXARI G,HARIHARAN B,GIRSHICK R,et al.R- [22]王忠民，曹洪江，范琳.一种基于卷积神经网络深度学 CNNs for pose estimation and action detection[J].Com- 习的人体行为识别方法).计算机科学，2016,43(11A): puter science,2014,12(8):1221-1229 56-58.87 [13]GKIOXARI G.GIRSHICK R,MALIK J.Contextual ac- WANG Zhongmin,CAO Hongjiang,FAN Lin.Method tion recognition with R*CNN[C]//Proceedings of 2015 on human activity recognition based on convolutional36–58. LI Hang. Statistical learning method[M]. Beijing: Tsinghua University Press, 2012: 36–58. 张文达, 许悦雷, 倪嘉成, 等. 基于多尺度分块卷积神经 网络的图像目标识别算法[J]. 计算机应用, 2016, 36(4): 1033–1038. ZHANG Wenda, XU Yuelei, NI Jiacheng, et al. Image tar￾get recognition method based on multi-scale block convo￾lutional neural network[J]. Journal of computer applica￾tions, 2016, 36(4): 1033–1038. [4] GIRSHICK R. Fast R-CNN[C]//Proceedings of 2015 IEEE International Conference on Computer Vision. Santiago, Chile, 2015: 1440–1448. [5] REN Shaoqing, HE Kaiming, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[C]//Proceedings of the 28th Internation￾al Conference on Neural Information Processing Systems. Montreal, Canada, 2015: 91–99. [6] HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Spa￾tial pyramid pooling in deep convolutional networks for visual recognition[C]//Proceedings of the 13th European Conference on Computer Vision. Zurich, Switzerland, 2014: 346–361. [7] JI Shuiwang, XU Wei, YANG Ming, et al. 3D convolu￾tional neural networks for automatic human action recogni￾tion[P]. USA: 8345984, 2013. [8] KARPATHY A, TODERICI G, SHETTY S, et al. Large￾scale video classification with convolutional neural net￾works[C]//Proceedings of 2014 IEEE Conference on Com￾puter Vision and Pattern Recognition. Columbus, USA, 2014: 1725–1732. [9] SUN Lin, JIA Kui, CHAN T H, et al. DL-SFA: deeply￾learned slow feature analysis for action recognition[C]// Proceedings of 2014 IEEE Conference on Computer Vis￾ion and Pattern Recognition. Columbus, USA, 2014: 2625–2632. [10] DONAHUE J, HENDRICKS L A, GUADARRAMA S, et al. Long-term recurrent convolutional networks for visual recognition and description[C]//Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition. Boston, USA, 2015: 2625–2634. [11] GKIOXARI G, HARIHARAN B, GIRSHICK R, et al. R￾CNNs for pose estimation and action detection[J]. Com￾puter science, 2014, 12(8): 1221–1229. [12] GKIOXARI G, GIRSHICK R, MALIK J. Contextual ac￾tion recognition with R*CNN[C]//Proceedings of 2015 [13] IEEE International Conference on Computer Vision. San￾tiago, Chile, 2015: 1080–1088. KHAN F S, VAN DE WEIJER J, ANWER R M, et al. Semantic pyramids for gender and action recognition[J]. IEEE transactions on image processing, 2014, 23(8): 3633–3645. [14] FEICHTENHOFER C, PINZ A, WILDES R P. Spati￾otemporal multiplier networks for video action recogni￾tion[C]//Proceedings of 2017 IEEE Conference on Com￾puter Vision and Pattern Recognition. Honolulu, USA, 2017: 7445–7454. [15] GKIOXARI G, GIRSHICK R, MALIK J. Actions and at￾tributes from wholes and parts[C]//Proceedings of 2015 IEEE International Conference on Computer Vision. San￾tiago, Chile, 2015: 2470–2478. [16] KAR A, RAI N, SIKKA K, et al. Adascan: adaptive scan pooling in deep convolutional neural networks for human action recognition in videos[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recog￾nition. Honolulu, USA, 2017: 5699–5708. [17] FEICHTENHOFER C, PINZ A, WILDES R P. Spati￾otemporal residual networks for video action recognition [C]//Proceedings of the 30th Conference on Neural In￾formation Processing Systems. Barcelona, Spain, 2016: 3468–3476. [18] HERATH S, HARANDI M, PORIKLI F. Going deeper into action recognition: a survey[J]. Image and vision computing, 2017, 60: 4–21. [19] 邓利群. 三维人体动作识别及其在交互舞蹈系统上的 应用[D]. 合肥: 中国科学技术大学, 2012. DENG Liqun. 3D mocap data recognition and its applica￾tion on interactive dancing game[D]. Hefei: University of Science and Technology of China, 2012. [20] 申晓霞, 张桦, 高赞, 等. 基于深度信息和 RGB 图像的 行为识别算法[J]. 模式识别与人工智能, 2013, 26(8): 722–728. SHEN Xiaoxia, ZHANG Hua, GAO Zan, et al. Behavior recognition algorithm based on depth information and RGB image[J]. Pattern recognition and artificial intelli￾gence, 2013, 26(8): 722–728. [21] 王忠民, 曹洪江, 范琳. 一种基于卷积神经网络深度学 习的人体行为识别方法[J]. 计算机科学, 2016, 43(11A): 56–58, 87. WANG Zhongmin, CAO Hongjiang, FAN Lin. Method on human activity recognition based on convolutional [22] ·972· 智 能 系 统 学 报 第 13 卷