A Generative Restricted Boltzmann Machine Based Method for High-Dimensional Motion Data Modeling
This work addresses computer vision applications like facial expression and action recognition, but it appears incremental as it builds on existing RBM frameworks.
The paper tackled modeling high-dimensional motion data by extending restricted Boltzmann machines (RBMs) to include local spatial interactions and a classification method, showing effectiveness in facial expression and human action recognition on benchmark databases.
Many computer vision applications involve modeling complex spatio-temporal patterns in high-dimensional motion data. Recently, restricted Boltzmann machines (RBMs) have been widely used to capture and represent spatial patterns in a single image or temporal patterns in several time slices. To model global dynamics and local spatial interactions, we propose to theoretically extend the conventional RBMs by introducing another term in the energy function to explicitly model the local spatial interactions in the input data. A learning method is then proposed to perform efficient learning for the proposed model. We further introduce a new method for multi-class classification that can effectively estimate the infeasible partition functions of different RBMs such that RBM is treated as a generative model for classification purpose. The improved RBM model is evaluated on two computer vision applications: facial expression recognition and human action recognition. Experimental results on benchmark databases demonstrate the effectiveness of the proposed algorithm.