Sciweavers

6087 search results - page 794 / 1218
» Knowledge discovery methods
Sort
View
CORR
2010
Springer
237views Education» more  CORR 2010»
15 years 4 months ago
Featureless 2D-3D Pose Estimation by Minimising an Illumination-Invariant Loss
The problem of identifying the 3D pose of a known object from a given 2D image has important applications in Computer Vision ranging from robotic vision to image analysis. Our pro...
Srimal Jayawardena, Marcus Hutter, Nathan Brewer
CVPR
2011
IEEE
15 years 2 months ago
Learning Temporally Consistent Rigidities
We present a novel probabilistic framework for rigid tracking and segmentation of shapes observed from multiple cameras. Most existing methods have focused on solving each of thes...
Jean-Sebastien Franco, Edmond Boyer
MTA
2011
263views Hardware» more  MTA 2011»
15 years 1 months ago
Event detection and recognition for semantic annotation of video
Research on methods for detection and recognition of events and actions in videos is receiving an increasing attention from the scientific community, because of its relevance for ...
Lamberto Ballan, Marco Bertini, Alberto Del Bimbo,...
PAMI
2010
146views more  PAMI 2010»
15 years 1 months ago
A Hierarchical Visual Model for Video Object Summarization
We propose a novel method for removing irrelevant frames from a video given user-provided frame-level labeling for a very small number of frames. We first hypothesize a number of w...
David Liu, Gang Hua, Tsuhan Chen
CVPR
2011
IEEE
14 years 10 months ago
Using Specular Highlights as Pose Invariant Features for 2D-3D Pose Estimation
We address the problem of 2D-3D pose estimation in difficult viewing conditions, such as low illumination, cluttered background, and large highlights and shadows that appear on t...
Aaron Netz, Margarita Osadchy