Sciweavers

1546 search results - page 267 / 310
» Computing Pose Sequences Directly from Videos
Sort
View
DAGSTUHL
2010
13 years 10 months ago
Towards Automatic Feature-based Visualization
Visualizations are well suited to communicate large amounts of complex data. With increasing resolution in the spatial and temporal domain simple imaging techniques meet their lim...
Heike Jänicke, Gerik Scheuermann
TOG
2012
199views Communications» more  TOG 2012»
11 years 11 months ago
Tracking surfaces with evolving topology
We present a method for recovering a temporally coherent, deforming triangle mesh with arbitrarily changing topology from an incoherent sequence of static closed surfaces. We solv...
Morten Bojsen-Hansen, Hao Li, Chris Wojtan
ICCV
1999
IEEE
14 years 10 months ago
Single View Metrology
We describe how 3D affine measurements may be computed from a single perspective view of a scene given only minimal geometric information determined from the image. This minimal i...
Antonio Criminisi, Ian D. Reid, Andrew Zisserman
ICCV
2009
IEEE
15 years 1 months ago
Non-Negative Matrix Factorization of Partial Track Data for Motion Segmentation
This paper addresses the problem of segmenting lowlevel partial feature point tracks belonging to multiple motions. We show that the local velocity vectors at each instant of th...
Anil M. Cheriyadat and Richard J. Radke
CVPR
2004
IEEE
14 years 10 months ago
A Discriminative Feature Space for Detecting and Recognizing Faces
In this paper, we introduce a novel discriminative feature space which is efficient not only for face detection but also for recognition. The face representation is based on local...
Abdenour Hadid, Matti Pietikäinen, Timo Ahone...