Active Learning for Human Action Recognition with Gaussian Processes

Publisher:
IEEE
Publication Type:
Conference Proceeding
Citation:
Proceedings of 2011 International Conference on Image Processing, 2011, pp. 3253 - 3256
Issue Date:
2011-01
Full metadata record
Files in This Item:
Filename Description Size
Thumbnail2011001952OK.pdf1.82 MB
Adobe PDF
This paper presents an active learning approach for recognizing human actions in videos based on multiple kernel combined method. We design the classifier based on Multiple Kernel Learning (MKL) through Gaussian Processes (GP) regression. This classifier is then trained in an active learning approach. In each iteration, one optimal sample is selected to be interactively annotated and incorporated into training set. The selection of the sample is based on the heuristic feedback of the GP classifier. To our knowledge, GP regression MKL based active learning methods have not been applied to address the human action recognition yet. We test this approach on standard benchmarks. This approach outperforms the state-of-the-art techniques in accuracy while requires significantly less training samples.
Please use this identifier to cite or link to this item: