KSII Transactions on Internet and Information Systems (TIIS)

Korean Society for Internet Information (한국인터넷정보학회)
권호 표지
DOI QR코드

DOI QR Code

Recognizing Actions from Different Views by Topic Transfer

  • Liu, Jia (Department of Electronic Technology, Engineering University of CAPF)
  • Received : 2016.08.23
  • Accepted : 2017.02.17
  • Published : 2017.04.30
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we describe a novel method for recognizing human actions from different views via view knowledge transfer. Our approach is characterized by two aspects: 1) We propose a unsupervised topic transfer model (TTM) to model two view-dependent vocabularies, where the original bag of visual words (BoVW) representation can be transferred into a bag of topics (BoT) representation. The higher-level BoT features, which can be shared across views, can connect action models for different views. 2) Our features make it possible to obtain a discriminative model of action under one view and categorize actions in another view. We tested our approach on the IXMAS data set, and the results are promising, given such a simple approach. In addition, we also demonstrate a supervised topic transfer model (STTM), which can combine transfer feature learning and discriminative classifier learning into one framework.

Keywords

References

  1. Laptev, I., "On space-time interest points," International Journal of Computer Vision, 64(2-3):pp. 107-123, 2005. https://doi.org/10.1007/s11263-005-1838-7
  2. Dollar, P.R., V. Cottrell, and G. Belongie, S., "Behavior recognition via sparse spatio-temporal features," in Proc. of IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance, pp. 1-8. 2005.
  3. Fengjun, L and Nevatia, R., "Single view human action recognition using key pose matching and Viterbi path searching," in Proc. of IEEE Conference on Computer Vision and Pattern Recognition, p. 1304-1311, 2007.
  4. Parameswaran, V.C., R., "View invariance for human action recognition," International Journal of Computer Vision, 66(1): p. 83-101, 2006. https://doi.org/10.1007/s11263-005-3671-4
  5. Weinland, D., E. Boyer, and R. Ronfard, "Action recognition from arbitrary views using 3D exemplars," in Proc. of IEEE International Conference on Computer Vision, pp. 170-176. 2007.
  6. Pingkun, Y.K., S. M. and Shah, M., "Learning 4D action feature models for arbitrary view action recognition," in Proc. of IEEE Conference on Computer Vision and Pattern Recognition, pp. 7-15, 2008.
  7. R. Li, T.T., and S. Sclaroff, "Simultaneous learning of nonlinear manifold and dynamical models for high-dimensional time series," in Proc. of International Conference of Computer Vision, pp. 1-8, 2007.
  8. D. Weinland, M. Ozuysal, and P. Fua, "Making action recognition robust to occlusions and viewpoint changes," in Proc. of Europe Conference on Computer Vision, pp. 635-648, 2010.
  9. IN. Junejo, E Dexter, I. Laptev and P. Perez, "Cross-View Action Recognition from Temporal Self-similarities," in Proc. of Europe Conference on Computer Vision, pp. 293-306. 2008.
  10. A. Farhadi, M. Tabrizi, I. Endres, and D. Forsyth, "A latent model of discriminative aspect," in Proc. of International Conference of Computer Vision, pp. 948-955, 2009.
  11. Farhadi, A.F., D. White, R., "Transfer learning in sign language," in Proc. of IEEE Conference on Computer Vision and Pattern Recognition, pp. 2909-2916, 2007.
  12. Liu, J.G.S., M. Kuipers and B. Savarese, S., "Cross-View Action Recognition via View Knowledge Transfer," in Proc. of IEEE Conference on Computer Vision and Pattern Recognition 2011, IEEE: New York. pp. 3209-3216, 2011.
  13. Sinno Jialin, and P.Q., Yang, "A Survey on Transfer Learning," IEEE Transactions on Knowledge and Data Engineering, 22(10): pp. 1345-1359, 2010. https://doi.org/10.1109/TKDE.2009.191
  14. J.C. Niebles, H-C. Wang and F.F. Li, "Unsupervised learning of human action categories using spatial-temporal words," International Journal of Computer Vision 79 (3), pp.299-318, 2008. https://doi.org/10.1007/s11263-007-0122-4
  15. S-F. Wong, T-K. Kim and R. Cipolla, "Learning motion categories using both semantic and structural information," in Proc. of IEEE Conference on Computer Vision and Pattern Recognition, pp.18-23 2007.
  16. J.G. Zhang and S.H. Gong, "Action categorization by structural probabilistic latent semantic analysis," Computer Vision and Image Understanding. 114(8), pp. 857-864, 2010. https://doi.org/10.1016/j.cviu.2010.04.006
  17. Y. Wang and G. Mori, "Human Action Recognition by Semi-latent Topic Models," IEEE Trans. Pattern Anal. Mach. Intell. 31(10), pp.1762-1774, 2010. https://doi.org/10.1109/TPAMI.2009.43
  18. Bian, W, Tao, D. C. and Rui, Y., "Cross-Domain Human Action Recognition," IEEE Transactions on Systems Man and Cybernetics Part B-Cybernetics, 42(2): pp. 298-307. 2012. https://doi.org/10.1109/TSMCB.2011.2166761
  19. Du Tran and Alexander Sorokin, "Human activity recognition with metric learning," in Proc. of European Conference on Computer Vision, pp. 548-561, 2008.
  20. Blei, D.M. Ng., A. Y. and Jordan, M. I., "Latent Dirichlet allocation," Journal of Machine Learning Research, 3(4-5): pp. 993-1022, 2003.
  21. David M. Blei and Jon D. McAuliffe, "Supervised topic models," in Proc. of Advances in Neural Information Processing Systems, pp. 1-8. 2007.
  22. R. Li and T. Zickler, "Discriminative virtual views for cross-view action recognition," in Proc. of IEEE Conference on Computer Vision and Pattern Recognition, pp. 1-8. 2012.
  23. Z. Zhang, C. Wang, B. Xiao, W. Zhou, S. Liu, and C. Shi, "Cross-view action recognition via a continuous virtual path," in Proc. of IEEE Conference on Computer Vision and Pattern Recognition,, pp. 1-8. 2013.
  24. J. Zheng and Z. Jiang, "Learning view-invariant sparse representations for cross-view action recognition," in Proc. of IEEE International Conference on Computer Vision, pp. 1-8, 2013.
  25. B. Li, O. Camps, and M. Sznaier, "Cross-view activity recognition using hankelets," in Proc. of IEEE International Conference on Computer Vision, pp. 1-8, 2012.
  26. A. Gupta , J. Martinez , J. Little and J. Woodham, "3D Pose from Motion for Cross-view Action Recognition via Non-linear Circulant Temporal Encoding," in Proc. of IEEE Conference on Computer Vision and Pattern Recognition, pp. 1-8, 2014.
  27. H. Rahmani, A. Mian, "Learning a Non-linear Knowledge Transfer Model for Cross-View Action Recognition," in Proc. of IEEE International Conference on Computer Vision, pp. 1-8, 2015.
  28. M. Liu, H Liu and Q Sun, "Action classification by exploring directional co-occurrence of weighted STIPS," in Proc. of IEEE International Conference on Image Processing. pp. 1460-1464, 2014.
  29. M. Liu, H. Liu, C Chen and M Najafian, "Energy-based Global Ternary Image for Action Recognition Using Sole Depth Sequences," in Proc. of International Conference on 3d Vision ,pp. 1-5, 2016.
  30. C. Chen, R. Jafari and N.Kehtarnavaz., "Action recognition from depth sequences using depth motion maps-based local binary patterns," in Proc. of the IEEE Winter Conference on Applications of Computer Vision, pp. 1092-1099, 2015.
  31. H. Liu, M. Liu, and Q Sun, "Learning directional cooccurrence for human action classification," in Proc. of International Conference on Acoustics, Speech and Signal Processing, pp. 1244-1248, 2014.