Sciweavers

1119 search results - page 194 / 224
» Hypercube Algorithms for Image Transformations
Sort
View
HUMO
2007
Springer
15 years 6 months ago
Multi-activity Tracking in LLE Body Pose Space
We present a method to simultaneously estimate 3d body pose and action categories from monocular video sequences. Our approach learns a lowdimensional embedding of the pose manifol...
Tobias Jaeggli, Esther Koller-Meier, Luc J. Van Go...
SIGGRAPH
1993
ACM
15 years 3 months ago
Frequency domain volume rendering
The Fourier projection-slice theorem allows projections of volume data to be generated in O(n2 log n) time for a volume of size n3 . The method operates by extracting and inverse ...
Takashi Totsuka, Marc Levoy
SDM
2007
SIAM
201views Data Mining» more  SDM 2007»
15 years 1 months ago
Fast Best-Match Shape Searching in Rotation Invariant Metric Spaces
Object recognition and content-based image retrieval systems rely heavily on the accurate and efficient identification of shapes. A fundamental requirement in the shape analysis ...
Dragomir Yankov, Eamonn J. Keogh, Li Wei, Xiaopeng...
CGF
2008
127views more  CGF 2008»
14 years 12 months ago
Viewfinder Alignment
The viewfinder of a digital camera has traditionally been used for one purpose: to display to the user a preview of what is seen through the camera's lens. High quality camer...
Andrew Adams, Natasha Gelfand, Kari Pulli
ICMCS
2009
IEEE
133views Multimedia» more  ICMCS 2009»
14 years 9 months ago
View indepedent human movement recognition from multi-view video exploiting a circular invariant posture representation
In this paper a novel method for view independent human movement representation and recognition, exploiting the rich information contained in multi-view videos, is proposed. The bi...
Nikolaos Gkalelis, Nikos Nikolaidis, Ioannis Pitas