Sciweavers

234 search results - page 33 / 47
» Tracking Objects to Detect Feature Dependencies
Sort
View
CVPR
2010
IEEE
14 years 3 months ago
Online Multiple Instance Learning with No Regret
Multiple instance (MI) learning is a recent learning paradigm that is more flexible than standard supervised learning algorithms in the handling of label ambiguity. It has been u...
Li Mu, James Kwok, Lu Bao-liang
IJCV
2007
134views more  IJCV 2007»
13 years 7 months ago
Multi-sensory and Multi-modal Fusion for Sentient Computing
This paper presents an approach to multi-sensory and multi-modal fusion in which computer vision information obtained from calibrated cameras is integrated with a large-scale sent...
Christopher Town
ICCV
2007
IEEE
14 years 9 months ago
Gradient Feature Selection for Online Boosting
Boosting has been widely applied in computer vision, especially after Viola and Jones's seminal work [23]. The marriage of rectangular features and integral-imageenabled fast...
Ting Yu, Xiaoming Liu 0002
ECCV
2010
Springer
13 years 7 months ago
Efficient Computation of Scale-Space Features for Deformable Shape Correspondences
Abstract. With the rapid development of fast data acquisition techniques, 3D scans that record the geometric and photometric information of deformable objects are routinely acquire...
Tingbo Hou, Hong Qin
ECCV
2010
Springer
14 years 10 days ago
Detecting ground shadows in outdoor consumer photographs
Detecting shadows from images can significantly improve the performance of several vision tasks such as object detection and tracking. Recent approaches have mainly used illuminat...