Sciweavers

224 search results - page 6 / 45
» Learning in Computer Vision: Some Thoughts
Sort
View
ICPR
2006
IEEE
14 years 8 months ago
A maximum margin discriminative learning algorithm for temporal signals
We propose a new maximum margin discriminative learning algorithm here for classification of temporal signals. It is superior to conventional HMM in the sense that it does not nee...
Wenjie Xu, Jiankang Wu, Zhiyong Huang
ACIVS
2006
Springer
13 years 11 months ago
Interactive Learning of Scene Context Extractor Using Combination of Bayesian Network and Logic Network
The vision-based scene understanding technique that infers scene-interpreting contexts from real-world vision data has to not only deal with various uncertain environments but also...
Keum-Sung Hwang, Sung-Bae Cho
SIAMCOMP
2008
107views more  SIAMCOMP 2008»
13 years 7 months ago
Holographic Algorithms
Leslie Valiant recently proposed a theory of holographic algorithms. These novel algorithms achieve exponential speed-ups for certain computational problems compared to naive algo...
Leslie G. Valiant
ICCV
2009
IEEE
1184views Computer Vision» more  ICCV 2009»
15 years 10 days ago
Learning Based Digital Matting
We cast some new insights into solving the digital matting problem by treating it as a semi-supervised learning task in machine learning. A local learning based approach and a g...
Yuanjie Zheng, Chandra Kambhamettu
ICCV
2011
IEEE
12 years 7 months ago
Perturb-and-MAP Random Fields: Using Discrete Optimization\\to Learn and Sample from Energy Models
We propose a novel way to induce a random field from an energy function on discrete labels. It amounts to locally injecting noise to the energy potentials, followed by finding t...
George Papandreou, Alan L. Yuille