Traditional aspect graphs are topology-based and are impractical for articulated objects. In this work we learn a small number of aspects, or prototypical views, from video data. ...
Active learning and crowdsourcing are promising ways to efficiently build up training sets for object recognition, but thus far techniques are tested in artificially controlled ...
This paper describes a system for object segmentation and feature extraction for surveillance video. Segmentation is performed by a dynamic vision system that fuses information fr...
Photometric stereo algorithms use a Lambertian reflectance model with a varying albedo field and involve the appearances of only one object. This paper extends photometric stereo a...
Shaohua Kevin Zhou, Rama Chellappa, David W. Jacob...
We propose a framework for detecting and tracking multiple interacting objects, while explicitly handling the dual problems of fragmentation (an object may be broken into several ...