正在加载图片...
第3期 孙倩茹,等:视频序列的人体运动描述方法综述 ·197. [16]WANG H,KLASER A,SCHMID C,et al.Action recogni- rea.2012:425-437. tion by dense trajectories[C]//IEEE Conference on Com- [29]COVER T M.The best two independent measurements are puter Vision and Pattern Recognition.Colorado Springs, not the two best[.IEEE Transactions on Systems,Man, USA,2011:3169-3176. and Cybernetics,1974,4(1):116-117 [17]RAPTIS M,KOKKINOS I,SOATTO S.Discovering dis- [30]JAIN A K.DUIN R P W,MAO J.Statistical pattern rec- criminative action parts from mid-level video representa- ognition:a review[J].IEEE Transactions on Pattern Anal- tions[C]//IEEE Conference on Computer Vision and Pat- ysis and Machine Intelligence,2000,22(1):4-37. tern Recognition.Providence,USA,2012:1242-1249. [31]GUYON I,ELISSEEF F.An introduction to variable and [18]HARRIS C,STEPHENS M.A combined comer and edge feature selection [J].Journal of Machine Learning Re- detector[C//Proceedings of the Fourth Alvey Vision Con- search,2003,3:1157-1182. ference.Manchester,UK,1988:147-151. [32]KIRA K,RENDELL L A.The feature selection problem: [19]LAPTEV I,LINDEBERG T.Space-time interest points traditional methods and a new algorithm[C]//Proceedings [C]//International Conference on Computer Vision. of the Tenth National Conference on Artificial Intelligence Nice,France,2003:432-439. San Jose,USA,1992:129-134. 20]DOLLAR P,RABAUD V,COTTRELL G,et al.Behavior [33]ZAFFALON M,HUTTER M.Robust feature selection by recognition via sparse spatiotemporal features[C]//IEEE mutual information distributions[C]//International Confer- International Workshop on Visual Surveillance and Per- ence on Uncertainty in Artificial Intelligence.Edmonton, formance Evaluation of Tracking and Surveillance.Beijing, Canada.2002:577-584. China,2005:65-72. [34]PENG H,LONG F,DING C.Feature selection based on [21]0IKONOMOPOULOS A,PATRAS I,PANTIC M.Spatio- mutual information:criteria of maxdependency,max-rele- temporal salient points for visual recognition of human ac- vance,and min-redundancy [J].IEEE Transactions on tions[J].IEEE Transactions on Systems,Man,and Cy- Pattern Analysis and Machine Intelligence,2005,27(8): bernetics,Part B:Cybernetics,2006,36(3):710-719. 1226-1238. [22]WONG S,CIPOLLA R.Extracting spatiotemporal interest [35]LIU J,LUO J,SHAH M.Recognizing realistic actions points using global information[C]//International Confer- from videos "in the wild"[C]//IEEE Conference on ence on Computer Vision.Rio de Janeiro,Brazil,2007:1- Computer Vision and Pattern Recognition.Miami,USA, 8. 2009:1996-2003. [23]SCHULDT C,LAPTEV I,CAPUTO B.Recognizing hu- [36]LIN Z,JIANG Z,DAVID L S.Recognizing actions by man actions:a local SVM approach [C]//International shape-motion prototype trees[C]//International Confer- Conference on Pattern Recognition.Cambridge,UK, ence on Computer Vision.Kyoto,Japan,2009:444-451. 2004:32-36. [37]SCHINDLER G,ZITNICK L,BROWN M.Internet video [24]SCOVANNER P,ALI S,SHAH M.A 3-dimensional SIFT category recognition[C]//IEEE Computer Society Confer- descriptor and its application to action recognition [C]// ence on Computer Vision and Pattern Recognition Work- Proceedings of the 15th International Conference on Multi- shops.Anchorage.USA,2008:1-7. media.Augsburg,Germany,2007:357-360. [38 ]SUN X,CHEN M,HAUPTMANN A.Action recognition [25]LOWE D G.Distinctive image features from scale-invariant via local descriptors and holistic features[C]//IEEE Con- keypoints[J].International Journal of Computer Vision, ference on Computer Vision and Pattern Recognition.Kyo- 2004,60(2):91-110. to,Japan,2009:58-65. [26]GILBERT A,ILLINGWORTH J,BOWDEN R.Fast real- [39]WANG H,ULLAH MM,KLASER A,et al.Evaluation of istic multi-action recognition using mined dense spatio-tem- local spatiotemporal features for action recognition[C// poral features[C]//International Conference on Computer British Machine Vision Conference.London,UK,2009: Vision.Kyoto,Japan,2009:925-931. 124.1-124.11. [27]NIEBLES J,WANG H,FEI-FEI L.Unsupervised learning [40]IKIZLER N,CINBIS R G,DUYGULU P.Human action of human action categories using spatial-temporal words recognition with line and flow histograms[C//Internation- [J].International Journal of Computer Vision,2008,79 al Conference on Pattern Recognition.Tampa,USA, (3):299-318. 2008:1-4 [28]SUN Qianru,LIU Hong.Action disambiguation analysis u- [41]ZHANG Z,HU Y,CHAN S,et al.Motion context:a new sing nommalized Google-like distance correlogram C]// representation for human action recognition[C]//European 11th Asian Conference on Computer Vision.Daejeon,Ko- Conference on Computer Vision.Marseille,France,2008:[16]WANG H, KLASER A, SCHMID C, et al. Action recogni⁃ tion by dense trajectories[C] / / IEEE Conference on Com⁃ puter Vision and Pattern Recognition. Colorado Springs, USA, 2011: 3169⁃3176. [17]RAPTIS M, KOKKINOS I, SOATTO S. Discovering dis⁃ criminative action parts from mid⁃level video representa⁃ tions[C] / / IEEE Conference on Computer Vision and Pat⁃ tern Recognition. Providence, USA, 2012: 1242⁃1249. [18]HARRIS C, STEPHENS M. A combined corner and edge detector[C] / / Proceedings of the Fourth Alvey Vision Con⁃ ference. Manchester, UK, 1988: 147⁃151. [19] LAPTEV I, LINDEBERG T. Space⁃time interest points [ C ] / / International Conference on Computer Vision. Nice, France, 2003: 432⁃439. [20]DOLLAR P, RABAUD V, COTTRELL G, et al. Behavior recognition via sparse spatiotemporal features [ C] / / IEEE International Workshop on Visual Surveillance and Per⁃ formance Evaluation of Tracking and Surveillance. Beijing, China, 2005: 65⁃72. [21]OIKONOMOPOULOS A, PATRAS I, PANTIC M. Spatio⁃ temporal salient points for visual recognition of human ac⁃ tions[ J]. IEEE Transactions on Systems, Man, and Cy⁃ bernetics, Part B: Cybernetics, 2006, 36(3): 710⁃719. [22]WONG S, CIPOLLA R. Extracting spatiotemporal interest points using global information[C] / / International Confer⁃ ence on Computer Vision. Rio de Janeiro, Brazil, 2007: 1⁃ 8. [23] SCHULDT C, LAPTEV I, CAPUTO B. Recognizing hu⁃ man actions: a local SVM approach [ C] / / International Conference on Pattern Recognition. Cambridge, UK, 2004: 32⁃36. [24]SCOVANNER P, ALI S, SHAH M. A 3⁃dimensional SIFT descriptor and its application to action recognition [ C] / / Proceedings of the 15th International Conference on Multi⁃ media. Augsburg, Germany, 2007: 357⁃360. [25]LOWE D G. Distinctive image features from scale⁃invariant keypoints[ J]. International Journal of Computer Vision, 2004, 60(2): 91⁃110. [26]GILBERT A, ILLINGWORTH J, BOWDEN R. Fast real⁃ istic multi⁃action recognition using mined dense spatio⁃tem⁃ poral features[C] / / International Conference on Computer Vision. Kyoto, Japan, 2009: 925⁃931. [27]NIEBLES J, WANG H, FEI⁃FEI L. Unsupervised learning of human action categories using spatial⁃temporal words [J]. International Journal of Computer Vision, 2008, 79 (3): 299⁃318. [28]SUN Qianru, LIU Hong. Action disambiguation analysis u⁃ sing normalized Google⁃like distance correlogram [ C] / / 11th Asian Conference on Computer Vision. Daejeon, Ko⁃ rea, 2012: 425⁃437. [29]COVER T M. The best two independent measurements are not the two best[J]. IEEE Transactions on Systems, Man, and Cybernetics, 1974, 4(1): 116⁃117. [30]JAIN A K, DUIN R P W, MAO J. Statistical pattern rec⁃ ognition: a review[J]. IEEE Transactions on Pattern Anal⁃ ysis and Machine Intelligence, 2000, 22(1): 4⁃37. [31] GUYON I, ELISSEEF F. An introduction to variable and feature selection [ J]. Journal of Machine Learning Re⁃ search, 2003, 3: 1157⁃1182. [32]KIRA K, RENDELL L A. The feature selection problem: traditional methods and a new algorithm[C] / / Proceedings of the Tenth National Conference on Artificial Intelligence. San Jose, USA, 1992: 129⁃134. [33] ZAFFALON M, HUTTER M. Robust feature selection by mutual information distributions[C] / / International Confer⁃ ence on Uncertainty in Artificial Intelligence. Edmonton, Canada, 2002: 577⁃584. [34]PENG H, LONG F, DING C. Feature selection based on mutual information: criteria of maxdependency, max⁃rele⁃ vance, and min⁃redundancy [ J ]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(8): 1226⁃1238. [35] LIU J, LUO J, SHAH M. Recognizing realistic actions from videos “ in the wild ” [ C] / / IEEE Conference on Computer Vision and Pattern Recognition. Miami, USA, 2009: 1996⁃2003. [36] LIN Z, JIANG Z, DAVID L S. Recognizing actions by shape⁃motion prototype trees [ C] / / International Confer⁃ ence on Computer Vision. Kyoto, Japan, 2009: 444⁃451. [37] SCHINDLER G, ZITNICK L, BROWN M. Internet video category recognition[C] / / IEEE Computer Society Confer⁃ ence on Computer Vision and Pattern Recognition Work⁃ shops. Anchorage, USA, 2008: 1⁃7. [38] SUN X, CHEN M, HAUPTMANN A. Action recognition via local descriptors and holistic features[C] / / IEEE Con⁃ ference on Computer Vision and Pattern Recognition. Kyo⁃ to, Japan, 2009: 58⁃65. [39]WANG H, ULLAH M M, KLASER A, et al. Evaluation of local spatiotemporal features for action recognition [ C] / / British Machine Vision Conference. London, UK, 2009: 124.1⁃124.11. [40]IKIZLER N, CINBIS R G, DUYGULU P. Human action recognition with line and flow histograms[C] / / Internation⁃ al Conference on Pattern Recognition. Tampa, USA, 2008: 1⁃4. [41]ZHANG Z, HU Y, CHAN S, et al. Motion context: a new representation for human action recognition[C] / / European Conference on Computer Vision. Marseille, France, 2008: 第 3 期 孙倩茹,等:视频序列的人体运动描述方法综述 ·197·
<<向上翻页向下翻页>>
©2008-现在 cucdc.com 高等教育资讯网 版权所有