Abstract. Multiple-instance learning (MIL) allows for training classifiers from ambiguously labeled data. In computer vision, this learning paradigm has been recently used in many ...
Shape matching has many applications in computer vision, such as shape classification, object recognition, object detection, and localization. In 2D cases, shape instances are 2D c...
Mobile privacy concerns are central to Ubicomp and yet remain poorly understood. We advocate a diversified approach, enabling the cross-interpretation of data from complementary m...
Clara Mancini, Keerthi Thomas, Yvonne Rogers, Blai...
A new approach to the recognition of temporal behaviors and activities is presented. The fundamental idea, inspired by work in speech recognition, is to divide the inference probl...
In this paper, we present a novel approach to solving the supervised dimensionality reduction problem by encoding an image object as a general tensor of 2nd or higher order. First...
Shuicheng Yan, Dong Xu, Qiang Yang, Lei Zhang, Xia...