Action recognition using multilevel features and latent structural SVM

IEEE Transactions on Circuits and Systems for Video Technology

Volumn 23, Issue 8, 2013, Pages 1422-1431

  Wu, Xinxiao ^a   Xu, Dong ^b   Duan, Lixin ^c   Luo, Jiebo ^d   Jia, Yunde ^a  

^a BEIJING INSTITUTE OF TECHNOLOGY   (China)

^b NANYANG TECHNOLOGICAL UNIVERSITY   (Singapore)

^c SAP Next Business and Technology   (Singapore)

^d University of Rochester   (United States)

Author keywords

Action recognition; action scene interaction; latent structural SVM; multilevel features

Indexed keywords

ACTION RECOGNITION; ACTION-SCENE INTERACTION; CO-OCCURRENCE RELATIONSHIPS; LATENT STRUCTURAL SVM; MULTILEVEL FEATURES; SPATIO-TEMPORAL RELATIONSHIPS; STATE-OF-THE-ART METHODS; UNIVERSAL BACKGROUND MODEL;

FACE RECOGNITION; GESTURE RECOGNITION; IMAGE SEGMENTATION; SEMANTICS;

MOTION ESTIMATION;

EID: 84881455497     PISSN: 10518215     EISSN: None     Source Type: Journal    
DOI: 10.1109/TCSVT.2013.2244794     Document Type: Article

References (42)

1. C. Fanti, L. Zelnik-manor, and P. Perona, "Hybrid models for human motion recognition," in Proc. IEEE CVPR, pp. 1166-1173 Jun. 2005. (Pubitemid 43897324)
2. A. Yilmaz, "Recognizing human actions in videos acquired by uncali-brated moving cameras," in Proc. IEEE ICCV, pp. 150-157 Oct. 2005. (Pubitemid 44054953)
3. L. Gorelick, M. Blank, E. Shechtman, M. Irani, and R. Basri, "Actions as space-time shapes," IEEE Trans. Pattern Anal. Mach. Intell., vol. 29, no. 12, pp. 2247-2253, Dec. 2007. (Pubitemid 350124072)
4. A. Yilmaz and M. Shah, "Actions sketch: A novel action representation," in Proc. IEEE CVPR, pp. 984-989, Jun. 2005. (Pubitemid 43897299)
5. X. Wu, Y. Jia, and W. Liang, "Incremental discriminant-analysis of canonical correlations for action recognition," Pattern Recognit., vol. 43, no. 12, pp. 4190-4197, Dec. 2010.
6. P. Dollár, V. Rabaud, G. Cottrell, and S. Belongie, "Behavior recognition via sparse spatio-temporal features," in Proc. IEEE Int. Workshop PETS, pp. 65-72 Jun. 2005. (Pubitemid 46178025)
7. C. Schuldt, I. Laptev, and B. Caputo, "Recognizing human actions: A local SVM approach," in Proc. ICPR, pp. 32-36, Aug. 2004.
8. J. C. Niebles, H. Wang, and L. Fei-fei, "Unsupervised learning of human action categories using spatial-temporal words," Int. J. Comput. Vision, vol. 79, no. 3, pp. 299-318, Sep. 2008.
9. X. Wu, D. Xu, L. Duan, and J. Luo, "Action recognition using context and appearance distribution features," in Proc. IEEE CVPR, pp. 489-496, Jun. 2011.
10. D. G. Lowe, "Distinctive image features from scale-invariant keypoints," Int. J. Comput. Vision, vol. 60, no. 2, pp. 91-110, Nov. 2004.
11. M. Marszaek, I. Laptev, and C. Schmid, "Actions in context," in Proc. IEEE CVPR, pp. 2929-2936, Jun. 2009.
12. N. Ikizler-Cinbis and S. Sclaroff, "Object, scene and actions: Combining multiple features for human action recognition," in Proc. ECCV, pp. 494-507, Sep. 2010.
13. J. Aggarwal and M. Ryoo, "Human activity analysis: A review," ACM Comput. Surveys, vol. 43, no. 3, pp. 16:1-16:43, Apr. 2011.
14. A. Kovashka and K. Grauman, "Learning a hierarchy of discriminative space-time neighborhood features for human action recognition," in Proc. IEEE CVPR, pp. 2046-2053, Jun. 2010.
15. S. Savarese, A. Delpozo, J. C. Niebles, and L. Fei-fei, "Spatial-temporal correlatons for unsupervised action classification," in IEEE Workshop on Motion and video Computing, pp. 1-8, Jan. 2008.
16. M. Ryoo and J. Aggarwal, "Spatio-temporal relationship match: Video structure comparison for recognition of complex human activities," in Proc. IEEE ICCV, pp. 1593-1600, Sep. 2009.
17. M. Bregonzio, S. Gong, and T. Xiang, "Recognising action as clouds of space-time interest points," in Proc. IEEE CVPR, pp. 1984-1955, Jun. 2009.
18. Z. Zhang, Y. Hu, S. Chan, and L.-T. Chia, "Motion context: A new representation for human action recognition," in Proc. ECCV, pp. 817-829, Oct. 2008.
19. I. R. Vega and S. Sarkar, "Statistical motion model based on the change of feature relationships: Human gait-based recognition," IEEE Trans. Pattern Anal. Mach. Intell., vol. 25, no. 10, pp. 1323-1328, Oct. 2003.
20. S. Nayak, S. Sarkar, and B. L. Loeding, "Distribution-based dimensionality reduction applied to articulated motion recognition," IEEE Trans. Pattern Anal. Mach. Intell., vol. 31, no. 5, pp. 795-810, May 2009.
21. D. Xu and S.-F. Chang, "Video event recognition using kernel methods with multilevel temporal alignment," IEEE Trans. Pattern Anal. Mach. Intell., vol. 30, no. 11, pp. 1985-1997, Nov. 2008.
22. A. Farhadi, I. Endres, D. Hoiem, and D. Forsyth, "Describing objects by their attributes," in Proc. IEEE CVPR, pp. 1778-1785, Jun. 2009.
23. J. Liu, B. Kuipers, and S. Savarese, "Recognizing human actions by attributes," in Proc. IEEE CVPR, pp. 3337-3344, Jun. 2011.
24. D. Parikh and K. Grauman, "Relative attributes," in Proc. IEEE ICCV, pp. 503-510, Nov. 2011.
25. S. Sadanand and J. J. Corso, "Action bank: A high-level representation of activity in video," in Proc. IEEE CVPR, pp. 1234-1241, Jun. 2012.
26. D. Xu, Y. Huang, Z. Zeng, and X. Xu, "Human gait recognition using patch distribution feature and locality-constrained group sparse representation," IEEE Trans. Image Process., vol. 21, no. 1, pp. 316-326, Jan. 2012.
27. H. Wang, A. Klaer, C. Schmid, and C.-L. Liu, "Action recognition by dense trajectories," in Proc. IEEE CVPR, pp. 3169-3176, Jun. 2011.
28. L. Duan, D. Xu, I. Tsang, and J. Luo, "Visual event recognition in videos by learning from web data," IEEE Trans. Pattern Anal. Mach. Intell., vol. 34, no. 9, pp. 1667-1680, Sep. 2012.
29. P. F. Felzenszwalb, R. B. Girshick, D. A. McAllester, and D. Ramanan, "Object detection with discriminatively trained part-based models." IEEE Trans. Pattern Anal. Mach. Intell., vol. 32, no. 9, pp. 1627-1645, Sep. 2010.
30. C.-N. J. Yu and T. Joachims, "Learning structural svms with latent variables," in Proc. ICML, pp. 1169-1176, Jun. 2009.
31. T. A. T.-M.-T. Do, "Large margin training for hidden markov models with partially observed states," in Proc. ICML, pp. 265-272, Jun. 2009.
32. M. D. Rodriguez, J. Ahmed, and M. Shah, "Action mach a spatiotemporal maximum average correlation height filter for action recognition," in Proc. IEEE CVPR, pp. 1-8, Jun. 2008.
33. H. Wang, M. M. Ullah, A. Klaer, I. Laptev, and C. Schmid, "Evaluation of local spatio-temporal features for action recognition," in Proc. BMVC, pp. 1-11, Sep. 2009.
34. J. Liu, J. Luo, and M. Shah, "Recognizing realistic actions from videos in the wild," in Proc. IEEE CVPR, pp. 1996-2003, Jun. 2009.
35. Q. V. Le, W. Y. Zhou, S. Y. Yeung, and A. Y. Ng, "Learning hierarchical invariant spatio-temporal features for action recognition with independent subspace analysis," in Proc. IEEE CVPR, pp. 3361-3368, Jun. 2011.
36. A. H. Shabani, D. A. Clausi, and J. S. Zelek, "Improved spatio-temporal salient feature detection for action recognition," in Proc. BMVC, pp. 1-12, Sep. 2011.
37. L. Yeffet and L. Wolf, "Local trinary patterns for human action recognition," in Proc. IEEE ICCV, pp. 492-497, Sep. 2009.
38. S. Wu, O. Oreifej, and M. Shah, "Action recognition in videos acquired by a moving camera using motion decomposition of Lagrangian particle trajectories," in Proc. IEEE ICCV, pp. 1419-1426, Nov. 2011.
39. M. Bregonzio, J. Li, and S. Gong, "Discriminative topics modelling for action feature selection and recognition," in Proc. BMVC, pp. 1-11, Oct. 2010.
40. B. Chakraborty, B. M. Holte, T. B. Moeslund, and J. Gonzalez, "Selective spatio-temporal interet points," Comput. Vision Image Understanding, vol. 116, no. 3, pp. 396-410, Mar. 2012.
41. A. Oliva and A. Torralba, "Modeling the shape of the scene: A holistic representation of the spatial envelope," Int. J. Comput. Vision, vol. 42, no. 3, pp. 145-175, May-Jun. 2001. (Pubitemid 32680801)
42. I. Laptev, "On space-time interest points," Int. J. Comput. Vision, vol. 64, no. 2-3, pp. 107-123, Sep. 2005. (Pubitemid 41314645)