Sciweavers

610 search results - page 91 / 122
» Markov Random Topic Fields
Sort
View
CVPR
2007
IEEE
14 years 9 months ago
Simultaneous Detection and Segmentation of Pedestrians using Top-down and Bottom-up Processing
We present a method for the simultaneous detection and segmentation of people from static images. The proposed technique requires no manual segmentation during training, and explo...
Vinay Sharma, James W. Davis
CVPR
2007
IEEE
14 years 9 months ago
Face Re-Lighting from a Single Image under Harsh Lighting Conditions
In this paper, we present a new method to change the illumination condition of a face image, with unknown face geometry and albedo information. This problem is particularly diffic...
Yang Wang, Zicheng Liu, Gang Hua, Zhen Wen, Zhengy...
CVPR
2007
IEEE
14 years 9 months ago
Iterative MAP and ML Estimations for Image Segmentation
Image segmentation plays an important role in computer vision and image analysis. In this paper, the segmentation problem is formulated as a labeling problem under a probability m...
Shifeng Chen, Liangliang Cao, Jianzhuang Liu, Xiao...
CVPR
2008
IEEE
14 years 9 months ago
Who killed the directed model?
Prior distributions are useful for robust low-level vision, and undirected models (e.g. Markov Random Fields) have become a central tool for this purpose. Though sometimes these p...
Justin Domke, Alap Karapurkar, Yiannis Aloimonos
ICCV
2007
IEEE
14 years 9 months ago
Integrating Appearance and Motion Cues for Simultaneous Detection and Segmentation of Pedestrians
We present a unified method for simultaneously acquiring both the location and the silhouette shape of people in outdoor scenes. The proposed algorithm integrates top-down and bot...
Vinay Sharma, James W. Davis