Sciweavers

42 search results - page 2 / 9
» Modelling Multi-object Activity by Gaussian Processes
Sort
View
ICCV
2007
IEEE
14 years 6 months ago
Real-time Body Tracking Using a Gaussian Process Latent Variable Model
In this paper, we present a tracking framework for capturing articulated human motions in real-time, without the need for attaching markers onto the subject's body. This is a...
Shaobo Hou, Aphrodite Galata, Fabrice Caillette, N...
GECCO
2007
Springer
148views Optimization» more  GECCO 2007»
13 years 11 months ago
Exploring the behavior of building blocks for multi-objective variation operator design using predator-prey dynamics
In this paper, we utilize a predator-prey model in order to identify characteristics of single-objective variation operators in the multi-objective problem domain. In detail, we a...
Christian Grimme, Joachim Lepping, Alexander Papas...
ICIP
2005
IEEE
14 years 6 months ago
Signal estimation using multiple-wavelet representations and Gaussian models
Signal processing using over-complete representations has been an active research field in recent years. In this article, we study the following two related problems: (1) given tw...
Guang Deng
HUMO
2007
Springer
13 years 11 months ago
Modeling Human Locomotion with Topologically Constrained Latent Variable Models
Abstract. Learned, activity-specific motion models are useful for human pose and motion estimation. Nevertheless, while the use of activityspecific models simplifies monocular t...
Raquel Urtasun, David J. Fleet, Neil D. Lawrence
ICCV
2011
IEEE
12 years 4 months ago
Gaussian Process Regression Flow for Analysis of Motion Trajectories
Recognition of motions and activities of objects in videos requires effective representations for analysis and matching of motion trajectories. In this paper, we introduce a new r...
Kihwan Kim, Dongryeol Lee, Irfan Essa