Sciweavers

140 search results - page 9 / 28
» A New Bayesian Framework for Object Recognition
Sort
View
ECCV
2002
Springer
14 years 9 months ago
Probabilistic Search for Object Segmentation and Recognition
Abstract. The problem of searching for a model-based scene interpretation is analyzed within a probabilistic framework. Object models are formulated as generative models for range ...
Ulrich Hillenbrand, Gerd Hirzinger
CVPR
2000
IEEE
14 years 10 months ago
Representation and Optimal Recognition of Human Activities
Towards the goal of realizing a generic automatichuman activity recognition system, a new formalism is proposed. Activities are described by a chained hierarchical representation ...
François Brémond, Ramakant Nevatia, ...
IJCAI
2007
13 years 9 months ago
Incremental Learning of Perceptual Categories for Open-Domain Sketch Recognition
Most existing sketch understanding systems require a closed domain to achieve recognition. This paper describes an incremental learning technique for opendomain recognition. Our s...
Andrew M. Lovett, Morteza Dehghani, Kenneth D. For...
CVPR
2005
IEEE
14 years 10 months ago
Shape Matching and Object Recognition Using Low Distortion Correspondences
We approach recognition in the framework of deformable shape matching, relying on a new algorithm for finding correspondences between feature points. This algorithm sets up corres...
Alexander C. Berg, Tamara L. Berg, Jitendra Malik
GECCO
2009
Springer
194views Optimization» more  GECCO 2009»
14 years 2 months ago
Combining evolution strategy and gradient descent method for discriminative learning of bayesian classifiers
The optimization method is one of key issues in discriminative learning of pattern classifiers. This paper proposes a hybrid approach of the Covariance Matrix Adaptation Evolution...
Xuefeng Chen, Xiabi Liu, Yunde Jia