This paper describes a new algorithm for recovering the
3D shape and motion of deformable and articulated objects
purely from uncalibrated 2D image measurements using an
iterati...
We address the problem of learning object class models and object segmentations from unannotated images. We introduce LOCUS (Learning Object Classes with Unsupervised Segmentation...
The ability to construct CAD or other object models from edge and range data has a fundamental meaning in building a recognition and positioning system. While the problem of model...
We present a discriminative part-based approach for human action recognition from video sequences using motion features. Our model is based on the recently proposed hidden conditi...
Understanding and modifying the effects of arbitrary illumination on human faces in a realistic manner is a challenging problem both for face synthesis and recognition. Recent res...