Non-rigid structure from motion (NRSFM) is a difficult, underconstrained problem in computer vision. The standard approach in NRSFM constrains 3D shape deformation using a linear...
The motion field of a scene can be used for object segmentation and to provide features for classification tasks like action recognition. Scene flow is the full 3D motion fiel...
Visual tracking plays an important role in many computer vision tasks. A common assumption in previous methods is that the video frames are blur free. In reality, motion blurs are...
We present an active learning approach to choose image annotation requests among both object category labels and the objects’ attribute labels. The goal is to solicit those labe...
Weakly supervised discovery of common visual structure in highly variable, cluttered images is a key problem in recognition. We address this problem using deformable part-based mo...