Sciweavers

2962 search results - page 258 / 593
» The Bunch-Active Shape Model
Sort
View
IROS
2009
IEEE
118views Robotics» more  IROS 2009»
16 years 1 months ago
Data-driven grasping with partial sensor data
— To grasp a novel object, we can index it into a database of known 3D models and use precomputed grasp data for those models to suggest a new grasp. We refer to this idea as dat...
Corey Goldfeder, Matei T. Ciocarlie, Jaime Peretzm...
GBRPR
2005
Springer
16 years 6 days ago
Coarse-to-Fine Object Recognition Using Shock Graphs
Shock graphs have emerged as a powerful generic 2-D shape representation. However, most approaches typically assume that the silhouette has been correctly segmented. In this paper,...
Aurelie Bataille, Sven J. Dickinson
CVPR
2003
IEEE
16 years 8 months ago
Practical Non-parametric Density Estimation on a Transformation Group for Vision
It is now common practice in machine vision to define the variability in an object's appearance in a factored manner, as a combination of shape and texture transformations. I...
Erik G. Miller, Christophe Chefd'Hotel
CVPR
2004
IEEE
16 years 8 months ago
3D Human Pose from Silhouettes by Relevance Vector Regression
We describe a learning based method for recovering 3D human body pose from single images and monocular image sequences. Our approach requires neither an explicit body model nor pr...
Ankur Agarwal, Bill Triggs
CVPR
2005
IEEE
16 years 8 months ago
Learning to Estimate Human Pose with Data Driven Belief Propagation
We propose a statistical formulation for 2-D human pose estimation from single images. The human body configuration is modeled by a Markov network and the estimation problem is to...
Gang Hua, Ming-Hsuan Yang, Ying Wu