We present two machine learning approaches to information extraction from semi-structured documents that can be used if no annotated training data are available, but there does ex...
We present an active learning framework to simultaneously learn appearance and contextual models for scene understanding tasks (multi-class classification). Existing multi-class a...
We propose a new coherent framework for joint object detection, 3D layout estimation, and object supporting region segmentation from a single image. Our approach is based on the m...
Computer vision tasks such as learning, recognition, classification or segmentation applied to spatial data often requires spatial normalization of repeated features and structure...
This paper considers the use of the EM-algorithm, combined with mean field theory, for parameter estimation in Markov random field models from unlabelled data. Special attention ...