Sciweavers

103 search results - page 12 / 21
» Duality for Labelled Markov Processes
Sort
View
77
Voted
ICIP
2005
IEEE
15 years 11 months ago
Joint feature-spatial-measure space: a new approach to highly efficient probabilistic object tracking
In this paper we present a probabilistic framework for tracking objects based on local dynamic segmentation. We view the segn to be a Markov labeling process and abstract it as a ...
Feng Chen, XiaoTong Yuan, ShuTang Yang
ICIP
2002
IEEE
15 years 11 months ago
Robust video text segmentation and recognition with multiple hypotheses
A method for segmenting and recognizing text embedded in video and images is proposed in this paper. In the method, multiple segmentation of the same text region is performed, thu...
Jean-Marc Odobez, Datong Chen
ICDAR
2011
IEEE
13 years 9 months ago
Co-training for Handwritten Word Recognition
—To cope with the tremendous variations of writing styles encountered between different individuals, unconstrained automatic handwriting recognition systems need to be trained on...
Volkmar Frinken, Andreas Fischer, Horst Bunke, Ali...
114
Voted
CVPR
2012
IEEE
13 years 1 days ago
RALF: A reinforced active learning formulation for object class recognition
Active learning aims to reduce the amount of labels required for classification. The main difficulty is to find a good trade-off between exploration and exploitation of the lab...
Sandra Ebert, Mario Fritz, Bernt Schiele
DAGM
2008
Springer
14 years 11 months ago
MAP-Inference for Highly-Connected Graphs with DC-Programming
The design of inference algorithms for discrete-valued Markov Random Fields constitutes an ongoing research topic in computer vision. Large state-spaces, none-submodular energy-fun...
Jörg H. Kappes, Christoph Schnörr