Sciweavers

563 search results - page 51 / 113
» Feature Space Trajectory Methods for Active Computer Vision
Sort
View
ICPR
2008
IEEE
14 years 3 months ago
Video caption duration extraction
Caption detection in the video is an active research topic in recent years. In the conventional methods, one of most difficult problems is to effectively and quickly extract the ...
Hongliang Bai, Jun Sun 0004, Satoshi Naoi, Yutaka ...
ICPR
2010
IEEE
14 years 2 months ago
Pairwise Features for Human Action Recognition
Existing action recognition approaches mainly rely on the discriminative power of individual local descriptors extracted from spatio-temporal interest points (STIP), while the geo...
Anh Phuong Ta, Christian Wolf, Guillaume Lavoue, A...
ICPR
2008
IEEE
14 years 3 months ago
An evaluation of bi-modal facial appearance+facial expression face biometrics
This paper introduces a framework that employs the Fisher linear discriminant model (FLDM) and classifier (FLDC) on integrated facial appearance and facial expression features. T...
Pohsiang Tsai, Tich Phuoc Tran, Tom Hintz, Tony Ja...
ICPR
2000
IEEE
14 years 1 months ago
Feature Learning for Recognition with Bayesian Networks
Many realistic visual recognition tasks are “open” in the sense that the number and nature of the categories to be learned are not initially known, and there is no closed set ...
Justus H. Piater, Roderic A. Grupen
ICPR
2008
IEEE
14 years 10 months ago
Kernel oriented discriminant analysis for speaker-independent phoneme spaces
Speaker independent feature extraction is a critical problem in speech recognition. Oriented principal component analysis (OPCA) is a potential solution that can find a subspace r...
Heeyoul Choi, Ricardo Gutierrez-Osuna, Seungjin Ch...