메뉴 건너뛰기




Volumn , Issue , 2011, Pages 113-120

Action recognition in cluttered dynamic scenes using pose-specific part models

Author keywords

[No Author keywords available]

Indexed keywords

ACTION MODELS; ACTION RECOGNITION; COMPLEX BACKGROUND; DATA SETS; DYNAMIC BACKGROUND; DYNAMIC SCENES; HUMAN ACTIONS; JOINT TRACKING AND RECOGNITION; KEYPOSES; MULTIPLE VIEWPOINTS; OCCLUSION CONSTRAINT; TRAINING DATA; TRANSFORMATION MATRICES; TREE-STRUCTURE;

EID: 84856661036     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICCV.2011.6126232     Document Type: Conference Paper
Times cited : (33)

References (31)
  • 1
    • 70450203723 scopus 로고    scopus 로고
    • Pictorial structures revisited: People detection and articulated pose estimation
    • 1, 2, 4, 5
    • M. Andriluka, S. Roth, and B. Schiele. Pictorial structures revisited: People detection and articulated pose estimation. In CVPR, pages 1014-1021, 2009. 1, 2, 4, 5
    • (2009) CVPR , pp. 1014-1021
    • Andriluka, M.1    Roth, S.2    Schiele, B.3
  • 2
    • 77955992058 scopus 로고    scopus 로고
    • Monocular 3d pose estimation and tracking by detection
    • 2
    • M. Andriluka, S. Roth, and B. Schiele. Monocular 3d pose estimation and tracking by detection. In CVPR, pages 623 -630, 2010. 2
    • (2010) CVPR , pp. 623-630
    • Andriluka, M.1    Roth, S.2    Schiele, B.3
  • 3
    • 85127836544 scopus 로고    scopus 로고
    • Discriminative training methods for hidden markov models: Theory and experiments with perceptron algorithms
    • 3
    • M. Collins. Discriminative training methods for hidden markov models: Theory and experiments with perceptron algorithms. In EMNLP, 2002. 3
    • (2002) EMNLP
    • Collins, M.1
  • 4
    • 4644354464 scopus 로고    scopus 로고
    • Pictorial structures for object recognition
    • 1, 2, 4, 5, 6
    • P. F. Felzenszwalb and D. P. Huttenlocher. Pictorial structures for object recognition. IJCV, 61(1):55-79, 2005. 1, 2, 4, 5, 6
    • (2005) IJCV , vol.61 , Issue.1 , pp. 55-79
    • Felzenszwalb, P.F.1    Huttenlocher, D.P.2
  • 6
    • 77953194241 scopus 로고    scopus 로고
    • Action detection in complex scenes with spatial and temporal ambiguities
    • 2
    • Y. Hu, L. Cao, F. Lv, S. Yan, Y. Gong, and T. Huang. Action detection in complex scenes with spatial and temporal ambiguities. In ICCV, pages 128 -135, 2009. 2
    • (2009) ICCV , pp. 128-135
    • Hu, Y.1    Cao, L.2    Lv, F.3    Yan, S.4    Gong, Y.5    Huang, T.6
  • 7
    • 77955987470 scopus 로고    scopus 로고
    • High performance object detection by collaborative learning of joint ranking of granules features
    • 3
    • C. Huang and R. Nevatia. High performance object detection by collaborative learning of joint ranking of granules features. In CVPR, pages 41-48, 2010. 3
    • (2010) CVPR , pp. 41-48
    • Huang, C.1    Nevatia, R.2
  • 8
    • 34948857983 scopus 로고    scopus 로고
    • Searching video for complex activities with finite state models
    • 2
    • N. Ikizler and D. A. Forsyth. Searching video for complex activities with finite state models. In CVPR, 2007. 2
    • (2007) CVPR
    • Ikizler, N.1    Forsyth, D.A.2
  • 9
    • 51949102800 scopus 로고    scopus 로고
    • Global pose estimation using non-tree models
    • 1, 2, 4
    • H. Jiang and D. Martin. Global pose estimation using non-tree models. In CVPR, 2008. 1, 2, 4
    • (2008) CVPR
    • Jiang, H.1    Martin, D.2
  • 10
    • 0030407592 scopus 로고    scopus 로고
    • Cardboard people: A parameterized model of articulated image motion
    • 4
    • S. X. Ju, M. J. Black, and Y. Yacoob. Cardboard people: A parameterized model of articulated image motion. In FG, 1996. 4
    • (1996) FG
    • Ju, S.X.1    Black, M.J.2    Yacoob, Y.3
  • 12
    • 33745939723 scopus 로고    scopus 로고
    • Beyond trees: Common-factor models for 2d human pose recovery
    • 2
    • X. Lan and D. P. Huttenlocher. Beyond trees: Common-factor models for 2d human pose recovery. ICCV, 2005. 2
    • (2005) ICCV
    • Lan, X.1    Huttenlocher, D.P.2
  • 14
    • 34948833676 scopus 로고    scopus 로고
    • Single view human action recognition using key pose matching and viterbi path searching
    • 2, 3
    • F. Lv and R. Nevatia. Single view human action recognition using key pose matching and viterbi path searching. In CVPR, 2007. 2, 3
    • (2007) CVPR
    • Lv, F.1    Nevatia, R.2
  • 15
    • 77953182943 scopus 로고    scopus 로고
    • Activity recognition using the velocity histories of tracked keypoints
    • 2
    • R. Messing, C. Pal, and H. Kautz. Activity recognition using the velocity histories of tracked keypoints. In ICCV, 2009. 2
    • (2009) ICCV
    • Messing, R.1    Pal, C.2    Kautz, H.3
  • 16
    • 34948881770 scopus 로고    scopus 로고
    • Latent-dynamic discriminative models for continuous gesture recognition
    • 2
    • L.-P. Morency, A. Quattoni, and T. Darrell. Latent-dynamic discriminative models for continuous gesture recognition. In CVPR, 2007. 2
    • (2007) CVPR
    • Morency, L.-P.1    Quattoni, A.2    Darrell, T.3
  • 17
    • 51949112298 scopus 로고    scopus 로고
    • View and scale invariant action recognition using multiview shape-flow models
    • 1, 2, 6, 7, 8
    • P. Natarajan and R. Nevatia. View and scale invariant action recognition using multiview shape-flow models. In CVPR, 2008. 1, 2, 6, 7, 8
    • (2008) CVPR
    • Natarajan, P.1    Nevatia, R.2
  • 18
    • 77956000175 scopus 로고    scopus 로고
    • Learning 3d action models from a few 2d videos for view invariant action recognition
    • 1, 2, 6, 7, 8
    • P. Natarajan, V. K. Singh, and R. Nevatia. Learning 3d action models from a few 2d videos for view invariant action recognition. In CVPR, 2010. 1, 2, 6, 7, 8
    • (2010) CVPR
    • Natarajan, P.1    Singh, V.K.2    Nevatia, R.3
  • 19
    • 56749132994 scopus 로고    scopus 로고
    • Latent pose estimator for continuous action recognition
    • 2
    • H. Ning,W. Xu, Y. Gong, and T. S. Huang. Latent pose estimator for continuous action recognition. In ECCV (2), 2008. 2
    • (2008) ECCV , Issue.2
    • Ning, H.1    Xu, W.2    Gong, Y.3    Huang, T.S.4
  • 20
    • 84864046033 scopus 로고    scopus 로고
    • Learning to parse images of articulated bodies
    • 1, 2, 4, 6
    • D. Ramanan. Learning to parse images of articulated bodies. In NIPS, pages 1129-1136, 2007. 1, 2, 4, 6
    • (2007) NIPS , pp. 1129-1136
    • Ramanan, D.1
  • 21
    • 0033682438 scopus 로고    scopus 로고
    • Inferring body pose without tracking body parts
    • 2
    • R. Rosales and S. Sclaroff. Inferring body pose without tracking body parts. In CVPR, 2000. 2
    • (2000) CVPR
    • Rosales, R.1    Sclaroff, S.2
  • 22
    • 75149186907 scopus 로고    scopus 로고
    • Combined discriminative and generative articulated pose and non-rigid shape estimation
    • 2, 3
    • L. Sigal, A. O. Balan, and M. J. Black. Combined discriminative and generative articulated pose and non-rigid shape estimation. In NIPS, 2007. 2, 3
    • (2007) NIPS
    • Sigal, L.1    Balan, A.O.2    Black, M.J.3
  • 23
    • 33845575116 scopus 로고    scopus 로고
    • Measure locally, reason globally: Occlusion-sensitive articulated pose estimation
    • 2, 6
    • L. Sigal and M. J. Black. Measure locally, reason globally: Occlusion-sensitive articulated pose estimation. In CVPR, pages 2041-2048, 2006. 2, 6
    • (2006) CVPR , pp. 2041-2048
    • Sigal, L.1    Black, M.J.2
  • 24
    • 33745893539 scopus 로고    scopus 로고
    • Conditional random fields for contextual human motion recognition
    • 2
    • C. Sminchisescu, A. Kanaujia, Z. Li, and D. Metaxas. Conditional random fields for contextual human motion recognition. In ICCV, pages 1808-1815, 2005. 2
    • (2005) ICCV , pp. 1808-1815
    • Sminchisescu, C.1    Kanaujia, A.2    Li, Z.3    Metaxas, D.4
  • 25
    • 84944381866 scopus 로고    scopus 로고
    • Recognizing and tracking human action
    • 3
    • J. Sullivan and S. Carlsson. Recognizing and tracking human action. In ECCV (1), pages 629-644, 2002. 3
    • (2002) ECCV , Issue.1 , pp. 629-644
    • Sullivan, J.1    Carlsson, S.2
  • 26
    • 24644449766 scopus 로고    scopus 로고
    • Dynamic conditional random fields: Factorized probabilistic models for labeling and segmenting sequence data
    • 3
    • C. Sutton, K. Rohanimanesh, and A. McCallum. Dynamic conditional random fields: factorized probabilistic models for labeling and segmenting sequence data. In ICML, page 99, 2004. 3
    • (2004) ICML , pp. 99
    • Sutton, C.1    Rohanimanesh, K.2    McCallum, A.3
  • 27
    • 77955994777 scopus 로고    scopus 로고
    • Fast globally optimal 2d human detection with loopy graph models
    • 1, 2, 4
    • T.-P. Tian and S. Sclaroff. Fast globally optimal 2d human detection with loopy graph models. In CVPR, 2010. 1, 2, 4
    • (2010) CVPR
    • Tian, T.-P.1    Sclaroff, S.2
  • 28
    • 33845583192 scopus 로고    scopus 로고
    • 3d people tracking with gaussian process dynamical models
    • 2
    • R. Urtasun, D. J. Fleet, and P. Fua. 3d people tracking with gaussian process dynamical models. In CVPR, 2006. 2
    • (2006) CVPR
    • Urtasun, R.1    Fleet, D.J.2    Fua, P.3
  • 29
    • 77951190698 scopus 로고    scopus 로고
    • Multiple tree models for occlusion and spatial constraints in human pose estimation
    • 2
    • Y.Wang and G. Mori. Multiple tree models for occlusion and spatial constraints in human pose estimation. In ECCV, 2008. 2
    • (2008) ECCV
    • Wang, Y.1    Mori, G.2
  • 30
    • 79957443678 scopus 로고    scopus 로고
    • Modeling 3d human poses from uncalibrated monocular images
    • 3, 6
    • X. K. Wei and J. Chai. Modeling 3d human poses from uncalibrated monocular images. In ICCV, pages 1873-1880, 2009. 3, 6
    • (2009) ICCV , pp. 1873-1880
    • Wei, X.K.1    Chai, J.2
  • 31
    • 50649108934 scopus 로고    scopus 로고
    • Action recognition from arbitrary views using 3d exemplars
    • D. Weinland, E. Boyer, and R. Ronfard. Action recognition from arbitrary views using 3d exemplars. In ICCV, 2007. 2
    • (2007) ICCV , pp. 2
    • Weinland, D.1    Boyer, E.2    Ronfard, R.3


* 이 정보는 Elsevier사의 SCOPUS DB에서 KISTI가 분석하여 추출한 것입니다.