Sciweavers

23 search results - page 1 / 5
» Recognizing Shapes in Video Sequences Using Multi-class Boos...
Sort
View
AVSS
2008
IEEE
13 years 11 months ago
Recognizing Shapes in Video Sequences Using Multi-class Boosting
We model the spatio-temporal variations of the shape of objects in a video sequence using a unique SVD-like decomposition. The decomposition is used to compute shape features, whi...
Naresh P. Cuntoor, Matt Welborn
ECCV
2006
Springer
13 years 6 months ago
Recognition and Segmentation of 3-D Human Action Using HMM and Multi-class AdaBoost
Our goal is to automatically segment and recognize basic human actions, such as stand, walk and wave hands, from a sequence of joint positions or pose angles. Such recognition is d...
Fengjun Lv, Ramakant Nevatia
ICCV
2009
IEEE
14 years 9 months ago
Recognizing Actions by Shape-Motion Prototype Trees
A prototype-based approach is introduced for action recognition. The approach represents an action as a se- quence of prototypes for efficient and flexible action match- ing in ...
Zhe Lin, Zhuolin Jiang, Larry S. Davis
IIHMSP
2006
IEEE
136views Multimedia» more  IIHMSP 2006»
13 years 11 months ago
Boosted String Representation and Its Application to Video Surveillance
This paper presents a new behavior classification system for analyzing human movements directly from video sequences. First of all, we propose a triangulation-based method to tran...
Yung-Tai Hsu, Jun-Wei Hsieh
FGR
2004
IEEE
231views Biometrics» more  FGR 2004»
13 years 8 months ago
A Boosted Classifier Tree for Hand Shape Detection
The ability to detect a persons unconstrained hand in a natural video sequence has applications in sign language, gesture recognition and HCI. This paper presents a novel, unsuper...
Eng-Jon Ong, Richard Bowden