Sciweavers

419 search results - page 82 / 84
» cvpr 2010
Sort
View
CVPR
2010
IEEE
14 years 2 months ago
Improving State-of-the-Art OCR through High-Precision Document-Specific Modeling
Optical character recognition (OCR) remains a difficult problem for noisy documents or documents not scanned at high resolution. Many current approaches rely on stored font models...
Andrew Kae, Gary Huang, Erik Learned-miller, Carl ...
CVPR
2010
IEEE
14 years 2 months ago
Action Unit Detection with Segment-based SVMs
Automatic facial action unit (AU) detection from video is a long-standing problem in computer vision. Two main approaches have been pursued: (1) static modeling--typically posed a...
Tomas Simon, Nguyen Minh, Fernando De la Torre, Je...
CVPR
2010
IEEE
2187views Computer Vision» more  CVPR 2010»
14 years 2 months ago
3D Scene Priors for Road Detection
Vision-based road detection is important in different areas of computer vision such as autonomous driving, car collision warning and pedestrian crossing detection. However, curre...
Jose M. Alvarez, Theo Gevers, Antonio M. Lopez
CVPR
2010
IEEE
14 years 1 months ago
The chains model for detecting parts by their context
Detecting an object part relies on two sources of information - the appearance of the part itself, and the context supplied by surrounding parts. In this paper we consider problem...
Leonid Karlinsky, Michael Dinerstein, Daniel Harar...
CVPR
2010
IEEE
14 years 1 months ago
Visual Event Recognition in Videos by Learning from Web Data
We propose a visual event recognition framework for consumer domain videos by leveraging a large amount of loosely labeled web videos (e.g., from YouTube). First, we propose a new...
Lixin Duan, Dong Xu, Wai-Hung Tsang, Jiebo Luo