Sciweavers

521 search results - page 64 / 105
» Foreground Object Detection Using Two Successive Images
Sort
View
ECCV
2006
Springer
16 years 4 months ago
PoseCut: Simultaneous Segmentation and 3D Pose Estimation of Humans Using Dynamic Graph-Cuts
Abstract. We present a novel algorithm for performing integrated segmentation and 3D pose estimation of a human body from multiple views. Unlike other related state of the art tech...
Matthieu Bray, Pushmeet Kohli, Philip H. S. Torr
110
Voted
ICRA
2009
IEEE
111views Robotics» more  ICRA 2009»
15 years 9 months ago
Interactive learning of the acoustic properties of household objects
— Human beings can perceive object properties such as size, weight, and material type based solely on the sounds that the objects make when an action is performed on them. In ord...
Jivko Sinapov, Mark Wiemer, Alexander Stoytchev
138
Voted
VMV
2003
163views Visualization» more  VMV 2003»
15 years 4 months ago
Real-Time Volumetric Intersections of Deforming Objects
We present a new algorithm for the computation of volumetric intersections of geometrically complex objects, which can be used for the efficient detection of collisions. Our appr...
Bruno Heidelberger, Matthias Teschner, Markus H. G...
111
Voted
ICPR
2010
IEEE
15 years 16 days ago
Improving Classification Accuracy by Comparing Local Features through Canonical Correlations
Classifying images using features extracted from densely sampled local patches has enjoyed significant success in many detection and recognition tasks. It is also well known that ...
Mert Dikmen, Thomas S. Huang
146
Voted
PAMI
2012
13 years 5 months ago
A Tree-Based Context Model for Object Recognition
—There has been a growing interest in exploiting contextual information in addition to local features to detect and localize multiple object categories in an image. A context mod...
Myung Jin Choi, Antonio Torralba, Alan S. Willsky