Sciweavers

318 search results - page 24 / 64
» Selecting relevant features for human motion recognition
Sort
View
ICCV
2009
IEEE
13 years 5 months ago
Fast realistic multi-action recognition using mined dense spatio-temporal features
Within the field of action recognition, features and descriptors are often engineered to be sparse and invariant to transformation. While sparsity makes the problem tractable, it ...
Andrew Gilbert, John Illingworth, Richard Bowden
ICCV
2009
IEEE
15 years 20 days ago
Detection of Human Actions From A Single Example
We present an algorithm for detecting human actions based upon a single given video example of such actions. The proposed method is unsupervised, does not require learning, segm...
Hae Jong Seo, Peyman Milanfar
KDD
2003
ACM
195views Data Mining» more  KDD 2003»
14 years 8 months ago
Visualizing changes in the structure of data for exploratory feature selection
Using visualization techniques to explore and understand high-dimensional data is an efficient way to combine human intelligence with the immense brute force computation power ava...
Elias Pampalk, Werner Goebl, Gerhard Widmer
JMLR
2010
120views more  JMLR 2010»
13 years 2 months ago
Effective Wrapper-Filter hybridization through GRASP Schemata
Of all of the challenges which face the selection of relevant features for predictive data mining or pattern recognition modeling, the adaptation of computational intelligence tec...
Mohamed Amir Esseghir
GECCO
2004
Springer
14 years 1 months ago
GA-Facilitated Knowledge Discovery and Pattern Recognition Optimization Applied to the Biochemistry of Protein Solvation
Abstract. The authors present a GA optimization technique for cosinebased k-nearest neighbors classification that improves predictive accuracy in a class-balanced manner while sim...
Michael R. Peterson, Travis E. Doom, Michael L. Ra...