Sciweavers

267 search results - page 9 / 54
» Conditional models for contextual human motion recognition
Sort
View
ICML
2009
IEEE
14 years 9 months ago
Factored conditional restricted Boltzmann Machines for modeling motion style
The Conditional Restricted Boltzmann Machine (CRBM) is a recently proposed model for time series that has a rich, distributed hidden state and permits simple, exact inference. We ...
Graham W. Taylor, Geoffrey E. Hinton
ICIP
2005
IEEE
14 years 2 months ago
Recognition of human activities using space dependent switched dynamical models
This paper describes a new algorithm for the recognition of human activities. These activities are modelled using banks of switched dynamical models, each of which is tailored to ...
Jacinto C. Nascimento, Mário A. T. Figueire...
ICCV
2007
IEEE
14 years 10 months ago
Conditional State Space Models for Discriminative Motion Estimation
We consider the problem of predicting a sequence of real-valued multivariate states from a given measurement sequence. Its typical application in computer vision is the task of mo...
Minyoung Kim, Vladimir Pavlovic
DICTA
2009
13 years 9 months ago
Modeling Image Context Using Object Centered Grid
Abstract--Context plays a valuable role in any image understanding task confirmed by numerous studies which have shown the importance of contextual information in computer vision t...
Sobhan Naderi Parizi, Ivan Laptev, Alireza Tavakol...
ICPR
2010
IEEE
14 years 1 months ago
The Human Action Image
Recognizing a person’s motion is intuitive for humans but represents a challenging problem in machine vision. In this paper, we present a multi-disciplinary framework for recogn...
Ricky Sethi, Amit Roy-Chowdhury