In this work we present a method to perform a complete audiovisual source separation without need of previous information. This method is based on the assumption that sounds are c...
Anna Llagostera Casanovas, Gianluca Monaci, Pierre...
Abstract—The idea of an online visual vocabulary is proposed. In contrast to the accepted strategy of generating vocabularies offline, using the k-means clustering over all the ...
This work presents a framework driven by parcellation of brain gray matter in standard normalized space to classify the neuronal fibers obtained from diffusion tensor imaging (DTI)...
Yan Xia, And U. Turken, Susan L. Whitfield-Gabriel...
—Motion information is an important cue for a robot to separate foreground moving objects from the static background world. Based on the observation that the motion of the backgr...
Embedding generic shape information into probabilistic spatiotemporal video object segmentation is of pivotal importance to achieving better segmentation, since it provides valuab...