While crowds of various subjects may offer applicationspecific cues to detect individuals, we demonstrate that for the general case, motion itself contains more information than p...
This paper addresses the problem of detecting and segmenting partially occluded objects of a known category. We first define a part labelling which densely covers the object. Our ...
We address the problem of estimating human pose in video sequences, where rough location has been determined. We exploit both appearance and motion information by defining suitabl...
Linear Discriminant Analysis (LDA) is one of the wellknown methods for supervised dimensionality reduction. Over the years, many LDA-based algorithms have been developed to cope w...
This paper addresses the problem of segmenting an image into regions consistent with user-supplied seeds (e.g., a sparse set of broad brush strokes). We view this task as a statis...