Discriminative-Element-Aware Sparse Representation for Action Recognition

Human action recognition has become one of the most important and challenging problems in computer vision. Sparse representation which encodes the local features with over-complete bases has shown excellent performance for action recognition. Traditional methods treat each feature and dictionary atom equally in the dictionary learning and classification phases respectively. However, we find that: 1)the discriminativeness of different features is uneven; 2) the contribution of different dictionary atoms is uneven. To solve these problem, we proposed a novel method called the discriminative-element-aware sparse representation (DEASR) which considers their contributions and combines them while making a decision. We evaluate the proposed method on two challenging datasets: the 3D Online RGBD Action Dataset, and UCF-101 Dataset. Experimental results show that proposed method achieves state-of-the-art results.

[1]  Cristian Sminchisescu,et al.  The Moving Pose: An Efficient 3D Kinematics Descriptor for Low-Latency Action Recognition and Detection , 2013, 2013 IEEE International Conference on Computer Vision.

[2]  Tanaya Guha,et al.  Learning Sparse Representations for Human Action Recognition , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Yan Song,et al.  Combining RGB and depth features for action recognition based on sparse representation , 2015, ICIMCS '15.

[4]  Rama Chellappa,et al.  Sparse dictionary-based representation and recognition of action attributes , 2011, 2011 International Conference on Computer Vision.

[5]  Gang Yu,et al.  Discriminative Orderlet Mining for Real-Time Recognition of Human-Object Interaction , 2014, ACCV.

[6]  Janusz Konrad,et al.  Action Recognition Using Sparse Representation on Covariance Manifolds of Optical Flow , 2010, 2010 7th IEEE International Conference on Advanced Video and Signal Based Surveillance.

[7]  Jake K. Aggarwal,et al.  Spatio-temporal Depth Cuboid Similarity Feature for Activity Recognition Using Depth Camera , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[8]  M. Elad,et al.  $rm K$-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation , 2006, IEEE Transactions on Signal Processing.

[9]  Heng Wang.  LEAR-INRIA submission for the THUMOS workshop , 2013 .

[10]  Sheng Chen,et al.  Orthogonal least squares methods and their application to non-linear system identification , 1989 .

[11]  Rajat Raina,et al.  Efficient sparse coding algorithms , 2006, NIPS.

[12]  Cordelia Schmid,et al.  Action Recognition with Improved Trajectories , 2013, 2013 IEEE International Conference on Computer Vision.

[13]  A. Bruckstein,et al.  K-SVD : An Algorithm for Designing of Overcomplete Dictionaries for Sparse Representation , 2005 .

[14]  Andrew W. Fitzgibbon,et al.  Real-time human pose recognition in parts from single depth images , 2011, CVPR 2011.

[15]  Christian Jutten,et al.  Dictionary Learning for Sparse Representation: A Novel Approach , 2013, IEEE Signal Processing Letters.

[16]  K WardRabab,et al.  Learning Sparse Representations for Human Action Recognition , 2012 .

[17]  Jianxin Wu,et al.  Towards Good Practices for Action Video Encoding , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[18]  Shuicheng Yan,et al.  Body Surface Context: A New Robust Feature for Action Recognition From Depth Videos , 2014, IEEE Transactions on Circuits and Systems for Video Technology.

[19]  Mubarak Shah,et al.  UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild , 2012, ArXiv.

[20]  Xiaodong Yang,et al.  EigenJoints-based action recognition using Naïve-Bayes-Nearest-Neighbor , 2012, 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops.

[21]  Limin Wang,et al.  Bag of visual words and fusion methods for action recognition: Comprehensive study and good practice , 2014, Comput. Vis. Image Underst..

[22]  Leonidas J. Guibas,et al.  Human action recognition by learning bases of action attributes and parts , 2011, 2011 International Conference on Computer Vision.

[23]  Limin Wang,et al.  Multi-view Super Vector for Action Recognition , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[24]  Jiebo Luo,et al.  Recognizing realistic actions from videos “in the wild” , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[25]  James W. Davis,et al.  The Recognition of Human Movement Using Temporal Templates , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[26]  Changyin Sun,et al.  Supervised class-specific dictionary learning for sparse modeling in action recognition , 2012, Pattern Recognit..

[27]  Serge J. Belongie,et al.  Behavior recognition via sparse spatio-temporal features , 2005, 2005 IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance.

[28]  Ying Wu,et al.  Mining actionlet ensemble for action recognition with depth cameras , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.