Sciweavers

1164 search results - page 102 / 233
» Steerable Random Fields
Sort
View
ECCV
2006
Springer
16 years 2 months ago
Fast Memory-Efficient Generalized Belief Propagation
Generalized Belief Propagation (gbp) has proven to be a promising technique for performing inference on Markov random fields (mrfs). However, its heavy computational cost and large...
M. Pawan Kumar, Philip H. S. Torr
126
Voted
ICIP
2008
IEEE
16 years 2 months ago
Modeling spatial patterns of shapes
We introduce a framework for modeling spatial patterns of shapes formed by multiple objects in an image. Our approach is graph-based where each node denotes an object and attribut...
Anuj Srivastava, Wei Liu, Shantanu H. Joshi
ICIP
2007
IEEE
16 years 2 months ago
Fast Detection of Independent Motion in Crowds Guided by Supervised Learning
Different from appearance-based methods, clustering feature points only by their motion coherence is an emerging category of approach to detecting and tracking individuals among c...
Yuan Li, Haizhou Ai
ICIP
2000
IEEE
16 years 2 months ago
Texture-Based Segmentation of Satellite Weather Imagery
Unsupervised segmentation of weather images into features that correspond to physical storms is a fundamental and difficult problem. Treating an infrared satellite image as a Mark...
V. Lakshmanan, Victor E. DeBrunner, R. Rabin
98
Voted
ICIP
1998
IEEE
16 years 2 months ago
Reducing the Computational Complexity of a Map Post-Processing Algorithm for Video Sequences
Maximum a posteriori (MAP) filtering using the HuberMarkov random field (HMRF) image model has been shown in the past to be an effective method of reducing compression artifacts i...
Mark A. Robertson, Robert L. Stevenson