Sciweavers

942 search results - page 92 / 189
» Structure From Motion for Scenes Without Features
Sort
View
TOG
2012
208views Communications» more  TOG 2012»
13 years 14 days ago
Video-based 3D motion capture through biped control
Marker-less motion capture is a challenging problem, particularly when only monocular video is available. We estimate human motion from monocular video by recovering three-dimensi...
Marek Vondrak, Leonid Sigal, Jessica K. Hodgins, O...
CGF
2006
123views more  CGF 2006»
14 years 10 months ago
Dancing-to-Music Character Animation
In computer graphics, considerable research has been conducted on realistic human motion synthesis. However, most research does not consider human emotional aspects, which often s...
Takaaki Shiratori, Atsushi Nakazawa, Katsushi Ikeu...
ICIP
2005
IEEE
15 years 3 months ago
Robust highlight extraction using multi-stream hidden Markov models for baseball video
This paper proposes a robust statistical framework to extract highlights from a baseball broadcast video. We applied multistream Hidden Markov Models (HMMs) to control the weights...
Nguyen Huu Bach, Koichi Shinoda, Sadaoki Furui
CVPR
2007
IEEE
16 years 1 days ago
Differential Camera Tracking through Linearizing the Local Appearance Manifold
The appearance of a scene is a function of the scene contents, the lighting, and the camera pose. A set of n-pixel images of a non-degenerate scene captured from different perspec...
Hua Yang, Marc Pollefeys, Greg Welch, Jan-Michael ...
ECCV
2010
Springer
15 years 1 months ago
Discovering Multipart Appearance Models from Captioned Images
Abstract. Even a relatively unstructured captioned image set depicting a variety of objects in cluttered scenes contains strong correlations between caption words and repeated visu...