Ideally pattern recognition machines provide constant output when the inputs are transformed under a group G of desired invariances. These invariances can be achieved by enhancing...
Abstract. In this paper, we present an extensive study of the cuttingplane algorithm (CPA) applied to structural kernels for advanced text classification on large datasets. In par...
The task of 2-D articulated human pose estimation in natural images is extremely challenging due to the high level of variation in human appearance. These variations arise from di...
For two consecutive frames in a video, we identify which pixels in the first frame become occluded in the second. Such general-purpose detection of occlusion regions is difficul...
We propose structured models for image labeling that take into account the dependencies among the image labels explicitly. These models are more expressive than independent label ...