In this paper we examine a novel approach to the difficult problem of querying video databases using visual topics with few examples. Typically with visual topics, the examples a...
Jelena Tesic, Apostol Natsev, Lexing Xie, John R. ...
— Localization and context interpretation are two key competences for mobile robot systems. Visual place recognition, as opposed to purely geometrical models, holds promise of hi...
Muhammad Muneeb Ullah, Andrzej Pronobis, Barbara C...
Abstract-- This paper introduces Evolutionary Pursuit (EP) as a novel and adaptive representation method for image encoding and classification. In analogy to projection pursuit met...
In this paper, we present a new co-training strategy that makes use of unlabelled data. It trains two predictors in parallel, with each predictor labelling the unlabelled data for...
In order to help users navigate an image search system, one could provide explicit information on a small set of images as to which of them are relevant or not to their task. Thes...