Sciweavers

782 search results - page 104 / 157
» Modelling Profiles with a Mixture of Gaussians
Sort
View
ICANN
2009
Springer
14 years 18 days ago
Switching Hidden Markov Models for Learning of Motion Patterns in Videos
Abstract. Building on the current understanding of neural architecture of the visual cortex, we present a graphical model for learning and classification of motion patterns in vid...
Matthias Höffken, Daniel Oberhoff, Marina Kol...
ICASSP
2008
IEEE
14 years 2 months ago
Blind audiovisual separation based on redundant representations
In this work we present a method to perform a complete audiovisual source separation without need of previous information. This method is based on the assumption that sounds are c...
Anna Llagostera Casanovas, Gianluca Monaci, Pierre...
ICMCS
2006
IEEE
215views Multimedia» more  ICMCS 2006»
14 years 2 months ago
Experiential Sampling based Foreground/Background Segmentation for Video Surveillance
Segmentation of foreground and background has been an important research problem arising out of many applications including video surveillance. A method commonly used for segmenta...
Pradeep K. Atrey, Vinay Kumar, Anurag Kumar, Mohan...
NIPS
2004
13 years 9 months ago
Parametric Embedding for Class Visualization
In this paper, we propose a new method, Parametric Embedding (PE), for visualizing the posteriors estimated over a mixture model. PE simultaneously embeds both objects and their c...
Tomoharu Iwata, Kazumi Saito, Naonori Ueda, Sean S...
ICCV
2003
IEEE
14 years 10 months ago
Bayesian Clustering of Optical Flow Fields
We present a method for unsupervised learning of classes of motions in video. We project optical flow fields to a complete, orthogonal, a-priori set of basis functions in a probab...
Jesse Hoey, James J. Little