70 likes | 176 Views
Data Driven Attributes for Action Recognition. Week 9 Presented by Christina Peterson. Recognition Accuracies on UCF Sports data set. Confusion Matrix: Standard Multi-Class SVM. Di. Go. Ki. Li. Ho. Ru. Sk. Sb. Ss. Wa. Diving. Golf. Kick. Lift. Horse-Ride. Run. Skateboard.
E N D
Data Driven Attributes for Action Recognition Week 9 Presented by Christina Peterson
Confusion Matrix: Standard Multi-Class SVM Di Go Ki Li Ho Ru Sk Sb Ss Wa Diving Golf Kick Lift Horse-Ride Run Skateboard Swing-bench Swing-side Walk
Confusion Matrix: Combined Exemplar-SVM Di Go Ki Li Ho Ru Sk Sb Ss Wa Diving Golf Kick Lift Horse-Ride Run Skateboard Swing-bench Swing-side Walk
Conclusions • Need to improve the method used to combine the exemplar scores • Currently, a multiclass-svm is trained on the decision values of the exemplars on the validation set • Possible Solution: • Create a strong action classifier using the boosting algorithm of Viola and Jones[8] • Treat the exemplar-svms as weak classifiers
References [1] M. D. Rodriguez, J. Ahmed, and M. Shah. Action mach: A spatio-temporal maximum average correlation height filter for action recognition. In CVPR, 2008. [2] Yeffet and L. Wolf. Local trinary patterns for human action recognition. In ICCV, 2009. [3] H. Wang, M. Ullah, A. Klaser, I. Laptev, and C. Schmid. Evaluation of local spatio-temporal features for action recognition. In BMVC, 2009. [4] Q. Le, W. Zou, S. Yeung, and A. Ng. Learning hierarchical invariant spatiotemporal features for action recognition with independent subspace analysis. In CVPR, 2011. [5] A. Kovashka and K. Grauman. Learning a hierarchy of discriminative spacetime neighborhood features for human action recognition. InCVPR, 2010. [6] X. Wu, D. Xu, L. Duan, and J. Luo. Action recognition using context and appearance distribution features. InCVPR, 2011. [7] S. Sadanand and J. J. Corso. Action bank: A high-level representation of activity in video. CVPR, 2012. [8] P. Viola and M. Jones. Robust real-time face detection. International Journal of Computer Vision, 57(2):137–154, May 2004.