Nonlinear Cross-View Sample Enrichment for Action Recognition

详细信息    查看全文

• 作者：Ling Wang (16)
  Hichem Sahbi (16)
  
  16. Institut Mines-T茅l茅com ; T茅l茅com ParisTech ; CNRS LTCI ; Paris ; France
  
• 关键词：Action recognition ; Kernel methods ; Canonical correlation analysis ; Viewpoint knowledge transfer ; Sample enrichment
• 刊名：Lecture Notes in Computer Science
• 出版年：2015
• 出版时间：2015
• 年：2015
• 卷：8927
• 期：1
• 页码：47-62
• 全文大小：1,655 KB
• 参考文献：1. Ashraf, N, Shen, Y, Cao, X, Foroosh, H (2013) View invariant action recognition using weighted fundamental ratios. Computer Vision and Image Understanding 117: pp. 587-602 CrossRef
  2. Boughorbel, S., Tarel, J.P., Boujemaa, N.: Generalized histogram intersection kernel for image recognition. In: ICIP (2005)
  3. Farhadi, A, Tabrizi, MK Learning to Recognize Activities from the Wrong View Point. In: Forsyth, D, Torr, P, Zisserman, A eds. (2008) Computer Vision 鈥?ECCV 2008. Springer, Heidelberg, pp. 154-166 CrossRef
  4. Gaidon, A., Harchaoui, Z., Schmid, C.: A time series kernel for action recognition. In: BMVC (2011)
  5. Gaidon, A, Harchaoui, Z, Schmid, C (2013) Activity representation with motion hierarchies. Int. J. Comput. Vision 107: pp. 219-238 CrossRef
  6. Golub, GH, Loan, CF (1996) Matrix Computations. Johns Hopkins University Press, Baltimore, MD, USA
  7. Gorelick, L, Blank, M, Shechtman, E, Irani, M, Basri, R (2007) Actions as Space-Time Shapes. IEEE Trans. Pattern Anal. Mach. Intell. 29: pp. 2247-2253 CrossRef
  8. Gupta, A., Martinez, J., Little, J.J., Woodham, R.J.: 3D Pose from Motion for Cross-view Action Recognition via Non-linear Circulant Temporal Encoding. In: CVPR (2014)
  9. Hardoon, DR, Szedmak, SR, Shawe-taylor, JR (2004) Canonical Correlation Analysis: An Overview with Application to Learning Methods. Neural Comput. 16: pp. 2639-2664 CrossRef
  10. Hassner, T.: A Critical Review of Action Recognition Benchmarks. In: 1st IEEE International Workshop on Action Similarity in Unconstrained Videos (ACTS) at the IEEE Conf. on Computer Vision and Pattern Recognition (CVPR) (2013)
  11. Holte, M.B., Tran, C., Trivedi, M.M., Moeslund, T.B.: Human Action Recognition Using Multiple Views: A Comparative Perspective on Recent Developments. In: Proceedings of the 2011 Joint ACM Workshop on Human Gesture and Behavior Understanding (2011)
  12. Hotelling, H (1936) Relations Between Two Sets of Variates. Biometrika 28: pp. 321-377 CrossRef
  13. Huang, C.H., Yeh, Y.R., Wang, Y.C.F.: Recognizing Actions across Cameras by Exploring the Correlated Subspace. In: ECCV Workshops (1) (2012)
  14. Jiang, Z, Lin, Z, Davis, L (2012) Recognizing Human Actions by Learning and Matching Shape-Motion Prototype Trees. IEEE Trans. Pattern Anal. Mach. Intell. 34: pp. 533-547 CrossRef
  15. Junejo, IN, Dexter, E, Laptev, I, P茅rez, P Cross-View Action Recognition from Temporal Self-similarities. In: Forsyth, D, Torr, P, Zisserman, A eds. (2008) Computer Vision 鈥?ECCV 2008. Springer, Heidelberg, pp. 293-306 CrossRef
  16. Kliper-Gross, O, Hassner, T, Wolf, L (2012) The Action Similarity Labeling Challenge. IEEE Trans. Pattern Anal. Mach. Intell. 34: pp. 615-621 CrossRef
  17. Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., Serre, T.: HMDB: A Large Video Database for Human Motion Recognition. In: ICCV (2011)
  18. Lan, T., Wang, Y., Mori, G.: Discriminative Figure-Centric Models for Joint Action Localization and Recognition. In: ICCV (2011)
  19. Laptev, I., Marsza艂ek, M., Schmid, C., Rozenfeld, B.: Learning Realistic Human Actions from Movies. In: CVPR (2008)
  20. Le, Q.V., Zou, W.Y., Yeung, S.Y., Ng, A.Y.: Learning hierarchical invariant spatio-temporal features for action recognition with independent subspace analysis. In: CVPR (2011)
  21. Li, R., Zickler, T.: Discriminative virtual views for cross-view action recognition. In: CVPR (2012)
  22. Liang, X., Lin, L., Cao, L.: Learning Latent Spatio-temporal Compositional Model for Human Action Recognition. In: Proceedings of the 21st ACM International Conference on Multimedia (2013)
  23. Liu, J., Shah, M., Kuipers, B., Savarese, S.: Cross-view action recognition via view knowledge transfer. In: CVPR (2011)
  24. Liu, Y, Dai, Q, Xu, W (2010) A Point-Cloud-Based Multiview Stereo Algorithm for Free-Viewpoint Video. IEEE Trans. Vis. Comput. Graph. 16: pp. 407-418 CrossRef
  25. Lowe, DG (2004) Distinctive Image Features from Scale-Invariant Keypoints. Int. J. Comput. Vision 60: pp. 91-110 CrossRef
  26. Pan, Sinno Jialin and Yang, Qiang: A Survey on Transfer Learning. IEEE Trans. on Knowl. and Data Eng. 22(10), 1345鈥?359 (2010)
  27. Rodriguez, M.D., Ahmed, J., Shah, M.: Action MACH: A Spatio-temporal Maximum Average Correlation Height Filter for Action Recognition. In: CVPR (2008)
  28. Sadanand, S., Corso, J.J.: Action Bank: A High-Level Representation of Activity in Video. In: CVPR (2012)
  29. Schlkopf, B., Smola, A.J., M眉ller, K.R.: Kernel principal component analysis. Advances in Kernel Methods: Support Vector Learning, pp. 327鈥?52 (1999)
  30. Soomro, K., Roshan Zamir, A., Shah, M.: UCF101: A dataset of 101 human actions classes from videos in the wild. In: CRCV-TR-12-01 (2012)
  31. Wang, H, Kl盲ser, A, Schmid, C, Liu, CL (2013) Dense Trajectories and Motion Boundary Descriptors for Action Recognition. Int. J. Comput. Vision 103: pp. 60-79 CrossRef
  32. Wang, J., Nie, X., Xia, Y., Wu, Y., Zhu, S.C.: Cross-view Action Modeling, Learning and Recognition. In: CVPR (2014)
  33. Wang, L., Sahbi, H.: Directed Acyclic Graph Kernels for Action Recognition. In: ICCV (2013)
  34. Weinland, D, 脰zuysal, M, Fua, P Making Action Recognition Robust to Occlusions and Viewpoint Changes. In: Daniilidis, K, Maragos, P, Paragios, N eds. (2010) Computer Vision 鈥?ECCV 2010. Springer, Heidelberg, pp. 635-648 CrossRef
  35. Weinland, D, Ronfard, R, Boyer, E (2006) Free viewpoint action recognition using motion history volumes. Computer Vision and Image Understanding 104: pp. 249-257 CrossRef
  36. Wu, X., Wang, H., Liu, C., Jia, Y.: Cross-view Action Recognition over Heterogeneous Feature Spaces. In: ICCV (2013)
  37. Yang, Y, Saleemi, I, Shah, M (2013) Discovering Motion Primitives for Unsupervised Grouping and One-Shot Learning of Human Actions, Gestures, and Expressions. IEEE Trans. Pattern Anal. Mach. Intell. 35: pp. 1635-1648 CrossRef
  38. Zhang, Z., Wang, C., Xiao, B., Zhou, W., Liu, S., Shi, C.: Cross-View Action Recognition via a Continuous Virtual Path. In: CVPR (2013)
  39. Zheng, J., Jiang, Z., Phillips, P.J., Chellappa, R.: Cross-View Action Recognition via a Transferable Dictionary Pair. In: BMVC (2012)
  
• 作者单位：Computer Vision - ECCV 2014 Workshops
• 丛书名：978-3-319-16198-3
• 刊物类别：Computer Science
• 刊物主题：Artificial Intelligence and Robotics
  Computer Communication Networks
  Software Engineering
  Data Encryption
  Database Management
  Computation by Abstract Devices
  Algorithm Analysis and Problem Complexity
  
• 出版者：Springer Berlin / Heidelberg
• ISSN：1611-3349

文摘

Advanced action recognition methods are prone to limited generalization performances when trained on insufficient amount of data. This limitation results from the high expense to label training samples and their insufficiency to capture enough variability due to viewpoint changes. In this paper, we propose a solution that enriches training data by transferring their features across views. The proposed method is motivated by the fact that cross-view features of the same actions are highly correlated. First, we use kernel-based canonical correlation analysis (CCA) to learn nonlinear feature mappings that take multi-view data from their original feature spaces into a common latent space. Then, we transfer training samples from source to target views by back-projecting their CCA features from latent to view-dependent spaces. We experiment this cross-view sample enrichment process for action classification and we study the impact of several factors including kernel choices as well as the dimensionality of the latent spaces.