iwitincvpr 2011 - 1st IEEE Workshop on Information Theory in Computer Vision and Pattern Recognition

Topics
THEORY/MODELS

IT-inspired divergences for shapes, images and graphs
MDL, Maximum Entropy, Minimax Entropy and other IT principles
Estimation of entropy and of other IT measures
Information projection
Information geometry
IT kernels and kernel machines
Integration with Bayesian/probabilistic models through IT
The role of IT in the integration of bottom-up/top-down processes
Alternative/complementary IT-like theories

APPLICATIONS

Feature Extraction
Early Vision, Attention and Context
Image Segmentation
Image Parsing and Recognition
Image Registration
Object Recognition and Categorization
Cognitive Models for Perception
Pattern Recognition with Grammars and Graphs
Shape Matching and Learning
Analysis of High-Dimensional Data
Classifiers and I-Divergences
Classification and Compression
Active and on-Line Learning
Learning Graphical Models
Manifold Learning
Unsupervised and Semi-Supervised Learning
Clustering Ensembles and Consensus Methods
Feature Transformation and Selection
Quantification of Pattern Complexity
Natural Images Statistics
Domains: Biomedical Data, Remote Sensing, Multi-Media, 3D Shape Analysis, Robotics.