Sciweavers

1367 search results - page 256 / 274
» Learning Visual Representations using Images with Captions
Sort
View
ICRA
2010
IEEE
170views Robotics» more  ICRA 2010»
13 years 6 months ago
Categorizing object-action relations from semantic scene graphs
— In this work we introduce a novel approach for detecting spatiotemporal object-action relations, leading to both, action recognition and object categorization. Semantic scene g...
Eren Erdal Aksoy, Alexey Abramov, Florentin Wö...
CVPR
2004
IEEE
14 years 9 months ago
Tracking Loose-Limbed People
We pose the problem of 3D human tracking as one of inference in a graphical model. Unlike traditional kinematic tree representations, our model of the body is a collection of loos...
Leonid Sigal, Sidharth Bhatia, Stefan Roth, Michae...
ECCV
2010
Springer
13 years 5 months ago
Discriminative Nonorthogonal Binary Subspace Tracking
Visual tracking is one of the central problems in computer vision. A crucial problem of tracking is how to represent the object. Traditional appearance-based trackers are using inc...
Ang Li, Feng Tang, Yanwen Guo, Hai Tao
IVC
2007
109views more  IVC 2007»
13 years 7 months ago
Hierarchical building recognition
In urban areas, buildings are often used as landmarks for localization. Reliable and efficient recognition of buildings is crucial for enabling this functionality. Motivated by t...
Wei Zhang, Jana Kosecká
VIS
2005
IEEE
110views Visualization» more  VIS 2005»
14 years 8 months ago
Prefiltered Gaussian Reconstruction for High-Quality Rendering of Volumetric Data sampled on a Body-Centered Cubic Grid
In this paper a novel high-quality reconstruction scheme is presented. Although our method is mainly proposed to reconstruct volumetric data sampled on an optimal Body-Centered Cu...
Balázs Csébfalvi