There Is More Than One Way to Get Out of a Car: Automatic Mode Finding for Action Recognition in the Wild
Oshin, O, Gilbert, A and Bowden, R (2011) There Is More Than One Way to Get Out of a Car: Automatic Mode Finding for Action Recognition in the Wild In: 5th IbPRIA 2011, 2011-06-08 - 2011-06-10, Las Palmas de Gran Canaria, Spain.
Available under License : See the attached licence file.
Official URL: http://dx.doi.org/10.1007/978-3-642-21257-4_6
Actions in the wild” is the term given to examples of human motion that are performed in natural settings, such as those harvested from movies  or the Internet . State-of-the-art approaches in this domain are orders of magnitude lower than in more contrived settings. One of the primary reasons being the huge variability within each action class. We propose to tackle recognition in the wild by automatically breaking complex action categories into multiple modes/group, and training a separate classifier for each mode. This is achieved using RANSAC which identifies and separates the modes while rejecting outliers. We employ a novel reweighting scheme within the RANSAC procedure to iteratively reweight training examples, ensuring their inclusion in the final classification model. Our results demonstrate the validity of the approach, and for classes which exhibit multi-modality, we achieve in excess of double the performance over approaches that assume single modality.
|Item Type:||Conference or Workshop Item (Paper)|
|Additional Information:||The original publication is available at http://www.springerlink.com|
|Uncontrolled Keywords:||Computer Science|
|Divisions:||Faculty of Engineering and Physical Sciences > Electronic Engineering > Centre for Vision Speech and Signal Processing|
|Deposited By:||Symplectic Elements|
|Deposited On:||11 Jun 2012 16:30|
|Last Modified:||16 Feb 2013 16:39|
Repository Staff Only: item control page