1 / 7

Data Driven Attributes for Action Recognition

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.

omana
Download Presentation

Data Driven Attributes for Action Recognition

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. Data Driven Attributes for Action Recognition Week 9 Presented by Christina Peterson

  2. Recognition Accuracies on UCF Sports data set

  3. 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

  4. 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

  5. Standard Linear vs. Exemplar

  6. 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

  7. 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.

More Related