·490· 智能系统学报 第15卷 al.Accurate activity recognition in a home setting[C]//Pro- lands,.2011:29-39 ceedings of the 10th International Conference on Ubiquit- [17]SZEGEDY C,LIU Wei,JIA Yangqing,et al.Going deep- ous Computing.Seoul,South Korea,2008:1-9. er with convolutions[C]//Proceedings of 2015 IEEE Con- [8]CHUNG P C.LIU C D.A daily behavior enabled hidden ference on Computer Vision and Pattern Recognition.Bo- Markov model for human behavior understanding[J].Pat- ston.USA,2015:1-9. tern recognition,2008,41(5):1572-1580. [18]SZEGEDY C.VANHOUCKE V.IOFFE S,et al.Re- [9]TANG K,LI Feifei,KOLLER D.Learning latent temporal thinking the inception architecture for computer vision[Cl// structure for complex event detection[C]//Proceedings of Proceedings of 2016 IEEE Conference on Computer Vis- 2012 IEEE Conference on Computer Vision and Pattern ion and Pattern Recognition.Las Vegas,USA,2016: Recognition.Providence,USA,2012:1025-1257. 2818-2826. [10]LAFFERTY J D,MCCALLUM A,PEREIRA F C N. [19]RYOO M S,AGGARWAL J K.Spatio-temporal relation- Conditional random fields:probabilistic models for seg- ship match:video structure comparison for recognition of menting and labeling sequence data[C]//Proceedings of the 18th International Conference on Machine Learning. complex human activities[C]//Proceedings of 2009 IEEE San Francisco.USA.2001:282-289. 12th International Conference on Computer Vision. [11]ZHANG Jianguo,GONG Shaogang.Action categoriza- Kyoto,Japan,2009:1593-1600. tion with modified hidden conditional random field [J]. 作者简介： Pattern recognition,2010,43(1):197-203. 姬晓飞，副教授，博士，主要研究 [12]SONG Yale.MORENCY L P,DAVIS R.Action recogni- 方向为视频分析与处理、模式识别理 tion by hierarchical sequence summarization[C]//EEE 论。承担国家自然科学基金、辽宁省 Conference on Computer Vision and Pattern Recognition. 自然科学基金等多项课题研究。发表 Portland,USA,2013:3563-3569. 学术论文40余篇，参与编著英文专 著2部。 [13]KE Qiuhong,BENNAMOUN M,AN Senjian,et al.Hu- man interaction prediction using deep temporal features [C]//Proceedings of European Conference on Computer 谢旋，硕土研究生，主要研究方向 Vision.Amsterdam.The Netherlands,2016:403-414. 为生物特征识别与行为分析技术。 [14]SIMONYAN K,ZISSERMAN A.Two-stream convolu- tional networks for action recognition in videos[C]//Pro- ceedings of the 27th International Conference on Neural Information Processing Systems.Montreal,Canada,2014: 568-576 [15]HOCHREITER S,SCHMIDHUBER J.Long short-term 任艳，讲师，博士，主要研究方向 为基于公理化模糊集的知识发现与表 memory[J].Neural computation,1997,9(8):1735-1780. 示、图像语义特征提取。承担国家自 [16]BACCOUCHE M,MAMALET F,WOLF C,et al.Se- 然科学基金、航空基金、辽宁省自然科 quential deep learning for human action recognition[C]// 学基金等课题研究。发表学术论文 Proceedings of the 2nd International Workshop on Hu- 25篇。 man Behavior Understanding.Amsterdam,The Nether-al. Accurate activity recognition in a home setting[C]//Pro￾ceedings of the 10th International Conference on Ubiquit￾ous Computing. Seoul, South Korea, 2008: 1−9. CHUNG P C, LIU C D. A daily behavior enabled hidden Markov model for human behavior understanding[J]. Pat￾tern recognition, 2008, 41(5): 1572–1580. [8] TANG K, LI Feifei, KOLLER D. Learning latent temporal structure for complex event detection[C]//Proceedings of 2012 IEEE Conference on Computer Vision and Pattern Recognition. Providence, USA, 2012: 1025−1257. [9] LAFFERTY J D, MCCALLUM A, PEREIRA F C N. Conditional random fields: probabilistic models for seg￾menting and labeling sequence data[C]//Proceedings of the 18th International Conference on Machine Learning. San Francisco, USA, 2001: 282−289. [10] ZHANG Jianguo, GONG Shaogang. Action categoriza￾tion with modified hidden conditional random field[J]. Pattern recognition, 2010, 43(1): 197–203. [11] SONG Yale, MORENCY L P, DAVIS R. Action recogni￾tion by hierarchical sequence summarization[C]//IEEE Conference on Computer Vision and Pattern Recognition. Portland, USA, 2013: 3563−3569. [12] KE Qiuhong, BENNAMOUN M, AN Senjian, et al. Hu￾man interaction prediction using deep temporal features [C]//Proceedings of European Conference on Computer Vision. Amsterdam, The Netherlands, 2016: 403−414. [13] SIMONYAN K, ZISSERMAN A. Two-stream convolu￾tional networks for action recognition in videos[C]//Pro￾ceedings of the 27th International Conference on Neural Information Processing Systems. Montreal, Canada, 2014: 568−576. [14] HOCHREITER S, SCHMIDHUBER J. Long short-term memory[J]. Neural computation, 1997, 9(8): 1735–1780. [15] BACCOUCHE M, MAMALET F, WOLF C, et al. Se￾quential deep learning for human action recognition[C]// Proceedings of the 2nd International Workshop on Hu￾man Behavior Understanding. Amsterdam, The Nether- [16] lands, 2011: 29−39. SZEGEDY C, LIU Wei, JIA Yangqing, et al. Going deep￾er with convolutions[C]//Proceedings of 2015 IEEE Con￾ference on Computer Vision and Pattern Recognition. Bo￾ston, USA, 2015: 1−9. [17] SZEGEDY C, VANHOUCKE V, IOFFE S, et al. Re￾thinking the inception architecture for computer vision[C]// Proceedings of 2016 IEEE Conference on Computer Vis￾ion and Pattern Recognition. Las Vegas, USA, 2016: 2818−2826. [18] RYOO M S, AGGARWAL J K. Spatio-temporal relation￾ship match: video structure comparison for recognition of complex human activities[C]//Proceedings of 2009 IEEE 12th International Conference on Computer Vision. Kyoto, Japan, 2009: 1593−1600. [19] 作者简介： 姬晓飞，副教授，博士，主要研究 方向为视频分析与处理、模式识别理 论。承担国家自然科学基金、辽宁省 自然科学基金等多项课题研究。发表 学术论文 40 余篇，参与编著英文专 著 2 部。 谢旋，硕士研究生，主要研究方向 为生物特征识别与行为分析技术。 任艳，讲师，博士，主要研究方向 为基于公理化模糊集的知识发现与表 示、图像语义特征提取。承担国家自 然科学基金、航空基金、辽宁省自然科 学基金等课题研究。发表学术论文 25 篇。 ·490· 智 能 系 统 学 报 第 15 卷