Sciweavers

112 search results - page 5 / 23
» Segmenting Motion Capture Data into Distinct Behaviors
Sort
View
ICMCS
2005
IEEE
172views Multimedia» more  ICMCS 2005»
14 years 1 months ago
A Study of Synthesizing New Human Motions from Sampled Motions Using Tensor Decomposition
This paper applies an algorithm, based on Tensor Decomposition, to a new synthesis application: by using sampled motions of people of different ages under different emotional stat...
Rovshan Kalanov, Jieun Cho, Jun Ohya
ICML
2009
IEEE
14 years 8 months ago
Unsupervised hierarchical modeling of locomotion styles
This paper describes an unsupervised learning technique for modeling human locomotion styles, such as distinct related activities (e.g. running and striding) or variations of the ...
Wei Pan, Lorenzo Torresani
MMM
2007
Springer
107views Multimedia» more  MMM 2007»
14 years 1 months ago
Hierarchical Indexing Structure for 3D Human Motions
Content-based retrieval of 3D human motion capture data has significant impact in different fields such as physical medicine, rehabilitation, and animation. This paper develops ...
Gaurav N. Pradhan, Chuanjun Li, Balakrishnan Prabh...
MIG
2009
Springer
14 years 2 months ago
Exploiting Motion Capture to Enhance Avoidance Behaviour in Games
Abstract. Realistic simulation of interacting virtual characters is essential in computer games, training and simulation applications. The problem is very challenging since people ...
Ben J. H. van Basten, Sander E. M. Jansen, Ioannis...
IDEAL
2004
Springer
14 years 1 months ago
Combining Local and Global Models to Capture Fast and Slow Dynamics in Time Series Data
Many time series exhibit dynamics over vastly different time scales. The standard way to capture this behavior is to assume that the slow dynamics are a “trend”, to de-trend t...
Michael Small