In this paper, an ontology-driven approach for the semantic analysis of video is proposed. This approach builds on an ontology infrastructure and in particular a multimedia ontolog...
An industrial vision system is presented which is designed general enough not only to recognize parts but also to evaluate their quality, inspect the environment, and control a se...
Abstract. This paper presents a novel framework for detecting abnormal pedestrian and vehicle behaviour by modelling cross-correlation among different co-occurring objects both loc...
We study the task of object part extraction and labeling, which seeks to understand objects beyond simply identifiying their bounding boxes. We start from bottom-up segmentation of...
Abstract Computer vision is full of problems elegantly expressed in terms of energy minimization. We characterize a class of energies with hierarchical costs and propose a novel hi...
Andrew Delong, Lena Gorelick, Olga Veksler, Yuri B...