Sciweavers

209 search results - page 13 / 42
» Appearance-based object recognition using optimal feature tr...
Sort
View
NIPS
2004
14 years 11 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
ICASSP
2011
IEEE
14 years 1 months ago
Front-end feature transforms with context filtering for speaker adaptation
Feature-space transforms such as feature-space maximum likelihood linear regression (FMLLR) are very effective speaker adaptation technique, especially on mismatched test data. In...
Jing Huang, Karthik Visweswariah, Peder A. Olsen, ...
CVPR
2000
IEEE
15 years 11 months ago
Representation and Optimal Recognition of Human Activities
Towards the goal of realizing a generic automatichuman activity recognition system, a new formalism is proposed. Activities are described by a chained hierarchical representation ...
François Brémond, Ramakant Nevatia, ...
ECAI
2008
Springer
14 years 11 months ago
Learning to Select Object Recognition Methods for Autonomous Mobile Robots
Selecting which algorithms should be used by a mobile robot computer vision system is a decision that is usually made a priori by the system developer, based on past experience and...
Reinaldo A. C. Bianchi, Arnau Ramisa, Ramon L&oacu...
TCSV
2002
292views more  TCSV 2002»
14 years 9 months ago
Document image segmentation using wavelet scale-space features
In this paper, an efficient and computationally fast method for segmenting text and graphics part of document images based on textural cues is presented. We assume that the graphic...
Mausumi Acharyya, Malay K. Kundu