We propose to model relative attributes1 that capture the relationships between images and objects in terms of human-nameable visual properties. For example, the models can captur...
Adaptive tracking-by-detection methods are widely used in computer vision for tracking arbitrary objects. Current approaches treat the tracking problem as a classification task a...
Structured outputs such as multidimensional vectors or graphs are frequently encountered in real world pattern recognition applications such as computer vision, natural language pr...
In Proc. of IEEE Conf. on CVPR'2000, Vol.I, pp.222-227, Hilton Head Island, SC, 2000 In many vision applications, the practice of supervised learning faces several difficulti...
Graph-based methods for semi-supervised learning have recently been shown to be promising for combining labeled and unlabeled data in classification problems. However, inference f...