Recent research has shown that collective classification in relational data often exhibit significant performance gains over conventional approaches that classify instances indi...
Abstract--Image segmentation plays an important role in computer vision and image analysis. In this paper, image segmentation is formulated as a labeling problem under a probabilit...
This paper addresses the novel problem of automatically synthesizing an output image from a large collection of different input images. The synthesized image, called a digital tap...
Carsten Rother, Sanjiv Kumar, Vladimir Kolmogorov,...
— This paper attempts to recognize spontaneous agreement and disagreement based only on nonverbal multimodal cues. Related work has mainly used verbal and prosodic cues. We demon...
The max-sum classifier predicts n-tuple of labels from n-tuple of observable variables by maximizing a sum of quality functions defined over neighbouring pairs of labels and obser...