Learning 3D action models from a few 2D videos for view invariant action recognition

Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

Volumn , Issue , 2010, Pages 2006-2013

  Natarajan, Pradeep ^a   Singh, Vivek Kumar ^b   Nevatia, Ram ^b  

^a BBN TECHNOLOGIES   (United States)

^b UNIVERSITY OF SOUTHERN CALIFORNIA   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

2D VIDEO; ACTION MODELS; ACTION RECOGNITION; DATA SETS; FEATURE WEIGHT; GROCERY STORES; HUMAN ACTIONS; KEYPOSES; LOW-LEVEL FEATURES; MODEL LEARNING; MULTI-VIEWS; NOVEL ALGORITHM; PERCEPTRON ALGORITHMS; PRIMITIVE ACTIONS; TRAINING DATA; VIDEO TRAINING; VIEW INVARIANTS;

ALGORITHMS; COMPUTER VISION; CURVE FITTING; FEATURE EXTRACTION; GESTURE RECOGNITION; STATISTICAL TESTS; THREE DIMENSIONAL;

THREE DIMENSIONAL COMPUTER GRAPHICS;

EID: 77956000175     PISSN: 10636919     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/CVPR.2010.5539876     Document Type: Conference Paper

References (22)

1. M. Bregonzio, S. Gong, and T. Xiang. Recognising action as clouds of space-time interest points. In CVPR, 2009. 6
2. M. Collins. Discriminative training methods for hidden markov models: theory and experiments with perceptron algorithms. In EMNLP, pages 1-8, 2002. 2, 5
3. D. DiFranco, T. Cham, and J. Rehg. Reconstruction of 3d figure motion from 2d correspondences. In CVPR, pages I:307-314, 2001. 2
4. T. Duong, H. Bui, D. Phung, and S. Venkatesh. Activity recognition and abnormality detection with the switching hidden semi-markov model. CVPR, 1:838-845, 2005. 1
5. A. Fathi and G. Mori. Action recognition by learning mid-level motion features. In CVPR, 2008. 1, 6
6. L. Gorelick, M. Blank, E. Shechtman, M. Irani, and R. Basri. Actions as space-time shapes. T-PAMI, 29(12):2247-2253, December 2007. 2, 6, 7
7. A. Hutchinson and G.Balanchine. Labanotation: The System of Analyzing and Recording Movement. ISBN: 0878305270, 1987. 2, 5
8. N. Ikizler and D. A. Forsyth. Searching video for complex activities with finite state models. In CVPR, 2007. 1, 2
9. H. Jhuang, T. Serre, L. Wolf, and T. Poggio. A biologically inspired system for action recognition. In ICCV, 2007. 6
10. Y. Ke, R. Sukthankar, and M. Hebert. Event detection in crowded videos. In ICCV, 2007. 1
11. L. Lamport. The temporal logic of actions. ACM Transactions on Programming Languages and Systems, 16(3):872-923, 1994. 2
12. I. Laptev. On space-time interest points. IJCV, 64(2-3):107-123, 2005. 1
13. B. Limketkai, D. Fox, and L. Liao. Crf-filters: Discriminative particle filters for sequential state estimation. In ICRA, pages 3142-3147, 2007. 3
14. F. Lv and R. Nevatia. Single view human action recognition using key pose matching and viterbi path searching. In CVPR, 2007. 1, 2, 4
15. L.-P. Morency, A. Quattoni, and T. Darrell. Latent-dynamic discriminative models for continuous gesture recognition. In CVPR, 2007. 1
16. P. Natarajan and R. Nevatia. View and scale invariant action recognition using multiview shape-flow models. In CVPR, 2008. 1, 2
17. V. Shet, S. N. Prasad, A. Elgammal, Y. Yacoob, and L. Davis. Multi-cue exemplar-based nonparametric model for gesture recognition. In ICVGIP, 2004. 1
18. C. Sminchisescu, A. Kanaujia, Z. Li, and D. Metaxas. Conditional random fields for contextual human motion recognition. In ICCV, pages 1808-1815, 2005. 1
19. J. Sullivan and S. Carlsson. Recognizing and tracking human action. In ECCV (1), pages 629-644, 2002. 2
20. X. Sun, M. Chen, and A. Hauptmann. Action recognition via local descriptors and holistic features. In CVRPW, pages 58-65, 2009. 6
21. C. J. Taylor. Reconstruction of articulated objects from point correspondences in a single uncalibrated image. In CVIU, volume 80, pages 349-363, 2000. 4
22. D.Weinland, R. Ronfard, and E. Boyer. Automatic discovery of action taxonomies from multiple views. In CVPR, pages II: 1639-1645, 2006. 1