Self-Organizing Kernel-based Convolutional Echo State Network for Human Actions Recognition

We propose a deterministic initialization of the Echo State Network reservoirs to ensure that the activation of its internal echo state representations reflects similar topological qualities of the input signal which should lead to a self-organizing reservoir. Human actions encoded as a multivariate time series signal are clustered before using the clustered nodes and interconnectivity matrices for initializing the S-ConvESN reservoirs. The capability of S-ConvESN is evaluated using several 3Dskeleton-based action recognition datasets.

[1]  Teuvo Kohonen,et al.  The self-organizing map , 1990, Neurocomputing.

[2]  Yin Wang,et al.  Efficient Temporal Sequence Comparison and Classification Using Gram Matrix Embeddings on a Riemannian Manifold , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Wanqing Li,et al.  Action recognition based on a bag of 3D points , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Workshops.

[4]  Chu Kiong Loo,et al.  A Kernel Bayesian Adaptive Resonance Theory with A Topological Structure , 2019, Int. J. Neural Syst..

[5]  Rama Chellappa,et al.  Human Action Recognition by Representing 3D Skeletons as Points in a Lie Group , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[6]  Osonde Osoba,et al.  Noise-enhanced clustering and competitive learning algorithms , 2013, Neural Networks.

[7]  Tsuyoshi Murata,et al.  {m , 1934, ACML.

[8]  C. Nelson.  Neural plasticity and human development: the role of early experience in sculpting memory systems , 2000 .

[9]  Fernando José Von Zuben,et al.  Self-organization and lateral interaction in echo state network reservoirs , 2014, Neurocomputing.

[10]  Marco La Cascia,et al.  Hankelet-based dynamical systems modeling for 3D action recognition , 2015, Image Vis. Comput..

[11]  Garrison W. Cottrell,et al.  WALKING WALKing walking: Action Recognition from Action Echoes , 2017, IJCAI.

[12]  Herbert Jaeger,et al.  The''echo state''approach to analysing and training recurrent neural networks , 2001 .

[13]  Ernest Fokoué,et al.  On the Statistical Challenges of Echo State Networks and Some Potential Remedies , 2018, ArXiv.

[14]  Marwan Torki,et al.  Human Action Recognition Using a Temporal Hierarchy of Covariance Descriptors on 3D Joint Locations , 2013, IJCAI.

[15]  Alberto Del Bimbo,et al.  Recognizing Actions from Depth Cameras as Weakly Aligned Multi-part Bag-of-Poses , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops.