Categorizing multiple objects in images is essentially a structured prediction problem: the label of an object is in general dependent on the labels of other objects in the image....
Qinfeng Shi, Luping Zhou, Li Cheng, Dale Schuurman...
Abstract. The original purpose of Web metadata was to protect endusers from possible harmful content and to simplify search and retrieval. However they can also be exploited in mor...
In this paper, a Bayesian LBP operator is proposed. This operator is formulated in a novel Filtering, Labeling and Statistic (FLS) framework for texture descriptors. In the framew...
Abstract. In cartography and computational geometry, concepts and techniques for automated label placement have been developed for twodimensional maps. Less is known whether these ...
Abstract. We present a discriminatively trained model for joint modelling of object class labels (e.g. “person”, “dog”, “chair”, etc.) and their visual attributes (e.g....