In the last decade, graph-cut optimization has been popular for a variety of pixel labeling problems. Typically graph-cut methods are used to incorporate a smoothness prior on a l...
We propose Recursive Compositional Models (RCMs) for simultaneous multi-view multi-object detection and parsing (e.g. view estimation and determining the positions of the object s...
Long Zhu, Yuanhao Chen, Antonio Torralba, William ...
Current object class recognition systems typically target 2D bounding box localization, encouraged by benchmark data sets, such as Pascal VOC. While this seems suitable for the de...
Bojan Pepik, Michael Stark, Peter V. Gehler, Bernt...
This paper presents a method for measuringthe entire three dimensional (3D) shape of object, which is applicable for 3D digitizing into a solid modeling CAD. The method measures t...
We study the challenging problem of maneuvering object tracking with unknown dynamics, i.e., forces or torque. We investigate the underlying causes of object kinematics, and propo...