Sciweavers

121 search results - page 20 / 25
» Learning and Incorporating Top-Down Cues in Image Segmentati...
Sort
View
CVPR
2005
IEEE
14 years 1 months ago
Mapping Low-Level Features to High-Level Semantic Concepts in Region-Based Image Retrieval
In this a novel supervised learning method is proposed to map low-level visualfeatures to high-level semantic conceptsfor region-based image retrieval. The contributions of thispa...
Wei Jiang, Kap Luk Chan, Mingjing Li, HongJiang Zh...
CVPR
2009
IEEE
15 years 2 months ago
Joint Depth and Alpha Matte Optimization via Fusion of Stereo and Time-of-Flight Sensor
We present a new approach to iteratively estimate both high-quality depth map and alpha matte from a single image or a video sequence. Scene depth, which is invariant to illumin...
Jiejie Zhu (University of Kentucky), Miao Liao (Un...
CVPR
2009
IEEE
1453views Computer Vision» more  CVPR 2009»
14 years 11 months ago
Learning Photometric Invariance From Diversified Color Model Ensembles
Color is a powerful visual cue for many computer vision applications such as image segmentation and object recognition. However, most of the existing color models depend on the i...
Jose M. Alvarez, Theo Gevers, Antonio M. Lopez
MM
2010
ACM
169views Multimedia» more  MM 2010»
13 years 7 months ago
CO3 for ultra-fast and accurate interactive segmentation
This paper presents an interactive image segmentation framework which is ultra-fast and accurate. Our framework, termed "CO3", consists of three components: COupled repr...
Yibiao Zhao, Song Chun Zhu, Siwei Luo
ICPR
2010
IEEE
14 years 2 months ago
Typographical Features for Scene Text Recognition
Scene text images feature an abundance of font style variety but a dearth of data in any given query. Recognition methods must be robust to this variety or adapt to the query data...
Jerod Weinman