Today's category-level object recognition systems largely focus on fronto-parallel views of objects with characteristic texture patterns. To overcome these limitations, we pr...
We describe a method of representing human activities that allows a collection of motions to be queried without examples, using a simple and effective query language. Our approach...
Object models based on bag-of-words representations can achieve state-of-the-art performance for image classification and object localization tasks. However, as they consider obje...
Strong lighting is common in natural scenes yet is often viewed as a nuisance for object pose estimation and tracking. In human shape and pose estimation, cast shadows can be conf...
Alexandru O. Balan, Michael J. Black, Horst W. Hau...
We present an evaluation methodology and data for large scale video-based 3D reconstruction. We evaluate the effects of several parameters and draw conclusions that can be useful ...
Paul Merrell, Philippos Mordohai, Jan-Michael Frah...