Sketch recognition systems are currently being developed for many domains, but can be time consuming to build if they are to handle the intricacies of each domain. This paper pres...
This paper presents an approach for human activity recognition by representing the frames of the video sequence with the distribution of local motion features and their spatiotemp...
Deep Belief Networks (DBNs) are hierarchical generative models which have been used successfully to model high dimensional visual data. However, they are not robust to common vari...
Many people cooperate for creating something new. It is important for the team’s perfomance to build a trusting relationship. It is necessary for building the trusting relations...
We address document image classification by visual appearance. An image is represented by a variable-length list of visually salient features. A hierarchical Bayesian network is ...