Human-nameable visual attributes offer many advantages when used as mid-level features for object recognition, but existing techniques to gather relevant attributes can be ineffici...
Recently the "bag of words" model becomes popular in the approaches to object recognition. These approaches model an image as a collection of local patches called "...
— This paper proposes an approach allowing indoor environment supervised learning to recognize relevant features for environment understanding. Stochastic preprocessing methods i...
In this paper, a geometric approach for global selflocalization based on a world-model and active stereo vision is introduced. The method uses class specific object recognition a...
David Israel Gonzalez-Aguirre, Tamim Asfour, Eduar...
— A novel framework to context modeling, based on the probability of co-occurrence of objects and scenes is proposed. The modeling is quite simple, and builds upon the availabili...