Sciweavers

17 search results - page 1 / 4
» How close are we to solving the problem of automated visual ...
Sort
View
MVA
2008
201views Computer Vision» more  MVA 2008»
13 years 4 months ago
How close are we to solving the problem of automated visual surveillance?
The problem of automated visual surveillance has spawned a lively research area, with 2005 seeing three conferences or workshops and special issues of two major journals devoted to...
Hannah M. Dee, Sergio A. Velastin
JAIR
2007
124views more  JAIR 2007»
13 years 4 months ago
Closed-Loop Learning of Visual Control Policies
In this paper we present a general, flexible framework for learning mappings from images to actions by interacting with the environment. The basic idea is to introduce a feature-...
Sébastien Jodogne, Justus H. Piater
ECML
2006
Springer
13 years 8 months ago
Approximate Policy Iteration for Closed-Loop Learning of Visual Tasks
Abstract. Approximate Policy Iteration (API) is a reinforcement learning paradigm that is able to solve high-dimensional, continuous control problems. We propose to exploit API for...
Sébastien Jodogne, Cyril Briquet, Justus H....
IEEEVAST
2010
12 years 11 months ago
An exploratory study of co-located collaborative visual analytics around a tabletop display
Co-located collaboration can be extremely valuable during complex visual analytics tasks. This paper presents an exploratory study of a system designed to support collaborative vi...
Petra Isenberg, Danyel Fisher, Meredith Ringel Mor...
ISCAS
2008
IEEE
136views Hardware» more  ISCAS 2008»
13 years 11 months ago
Spatial-temporal consistent labeling for multi-camera multi-object surveillance systems
Abstract—For an intelligent multi-camera multi-object surveillance system, object correspondence across time and space is important to many smart visual applications. In this pap...
Jing-Ying Chang, Tzu-Heng Wang, Shao-Yi Chien, Lia...