Sciweavers

725 search results - page 29 / 145
» Invariances in kernel methods: From samples to objects
Sort
View
ICB
2007
Springer
176views Biometrics» more  ICB 2007»
13 years 11 months ago
A Novel Null Space-Based Kernel Discriminant Analysis for Face Recognition
The symmetrical decomposition is a powerful method to extract features for image recognition. It reveals the significant discriminative information from the mirror image of symmetr...
Tuo Zhao, Zhizheng Liang, David Zhang, Yahui Liu
NIPS
2004
13 years 9 months ago
A Three Tiered Approach for Articulated Object Action Modeling and Recognition
Visual action recognition is an important problem in computer vision. In this paper, we propose a new method to probabilistically model and recognize actions of articulated object...
Le Lu, Gregory D. Hager, Laurent Younes
AMFG
2003
IEEE
126views Biometrics» more  AMFG 2003»
14 years 1 months ago
Rank Constrained Recognition under Unknown Illuminations
Recognition under illumination variations is a challenging problem. The key is to successfully separate the illumination source from the observed appearance. Once separated, what ...
Shaohua Kevin Zhou, Rama Chellappa
PRL
2007
99views more  PRL 2007»
13 years 7 months ago
Polygonal shape description for recognition of partially occluded objects
We introduce a new method for the recognition of partially occluded objects represented only by their contours. Object description, which stems from the inflection point detectio...
Filip Krolupper, Jan Flusser
DIS
2008
Springer
13 years 9 months ago
Unsupervised Classifier Selection Based on Two-Sample Test
We propose a well-founded method of ranking a pool of m trained classifiers by their suitability for the current input of n instances. It can be used when dynamically selecting a s...
Timo Aho, Tapio Elomaa, Jussi Kujala