Sciweavers

334 search results - page 13 / 67
» Scene carving: Scene consistent image retargeting
Sort
View
ICIP
2010
IEEE
14 years 7 months ago
Multi-view object and human body part detection utilizing 3D scene information
The aim of this paper is to present a new method for multiview object or human body (or body part) detection. The basic idea consists of using a single view detector in every view...
Georgios Sfiris, Nikolaos Nikolaidis, Ioannis Pita...
CGF
1999
70views more  CGF 1999»
14 years 9 months ago
Modelling and Rendering Graphics Scenes Composed of Multiple Volumetric Datasets
This paper presents a method for modelling graphics scenes consisting of multiple volumetric objects. A twolevel hierarchical representation is employed, which enables the reducti...
Adrian Leu, Min Chen
ICPR
2010
IEEE
15 years 4 months ago
Typographical Features for Scene Text Recognition
Scene text images feature an abundance of font style variety but a dearth of data in any given query. Recognition methods must be robust to this variety or adapt to the query data...
Jerod Weinman
PAMI
2008
190views more  PAMI 2008»
14 years 9 months ago
Scene Classification Using a Hybrid Generative/Discriminative Approach
We investigate whether dimensionality reduction using a latent generative model is beneficial for the task of weakly supervised scene classification. In detail we are given a set ...
Anna Bosch, Andrew Zisserman, Xavier Muñoz
CGF
2008
117views more  CGF 2008»
14 years 9 months ago
Video Relighting Using Infrared Illumination
Inappropriate lighting is often responsible for poor quality video. In most offices and homes, lighting is not designed for video conferencing. This can result in unevenly lit fac...
Oliver Wang, James Davis, Erika Chuang, Ian Rickar...