We propose a model for classification and detection of object classes where the number of classes may be large and where multiple instances of object classes may be present in an i...
Many previous works on photometric stereo have shown how to recover the shape and reflectance properties of an object using multiple images taken under a fixed viewpoint and variab...
We present a method for efficiently tracking objects represented as constellations of parts by integrating out the shape of the model. Parts-based models have been successfully ap...
Most of behavior recognition methods proposed so far share the limitations of bottom-up analysis, and singleobject assumption; the bottom-up analysis can be confused by erroneous ...
This paper presents a novel approach to single-frame pedestrian classification and orientation estimation. Unlike previous work which addressed classification and orientation sepa...