Sciweavers

ICCV
2003
IEEE
14 years 6 months ago
Dominant Sets and Hierarchical Clustering
Dominant sets are a new graph-theoretic concept that has proven to be relevant in partitional (flat) clustering as well as image segmentation problems. However, in many computer v...
Massimiliano Pavan, Marcello Pelillo
ICCV
2003
IEEE
14 years 6 months ago
Background Modeling and Subtraction of Dynamic Scenes
Background modeling and subtraction is a core component in motion analysis. The central idea behind such module is to create a probabilistic representation of the static scene tha...
Antoine Monnet, Anurag Mittal, Nikos Paragios, Vis...
ICCV
2003
IEEE
14 years 6 months ago
Polarization-based Inverse Rendering from a Single View
This paper presents a method to estimate geometrical, photometrical, and environmental information of a singleviewed object in one integrated framework under fixed viewing positio...
Daisuke Miyazaki, Robby T. Tan, Kenji Hara, Katsus...
ICCV
2003
IEEE
14 years 6 months ago
Polarization-based Transparent Surface Modeling from Two Views
In this paper, we propose a novel method to recover the surface shape of transparent objects. The degree of polarization of the light reflected from the object surface depends on ...
Daisuke Miyazaki, Masataka Kagesawa, Katsushi Ikeu...
ICCV
2003
IEEE
14 years 6 months ago
Using Specularities for Recognition
Recognition systems have generally treated specular highlights as noise. We show how to use these highlights as a positive source of information that improves recognition of shiny...
Margarita Osadchy, David W. Jacobs, Ravi Ramamoort...
ICCV
2003
IEEE
14 years 6 months ago
Multiple-cue Illumination Estimation in Textured Scenes
In this paper, we present a method that integrates cues from shading, shadow and specular reflections for estimating directional illumination in a textured scene. Texture poses a ...
Yuanzhen Li, Stephen Lin, Hanqing Lu, Heung-Yeung ...
ICCV
2003
IEEE
14 years 6 months ago
Surface Reconstruction by Integrating 3D and 2D Data of Multiple Views
Surface representation is needed for almost all modeling and visualization applications, but unfortunately, 3D data from a passive vision system are often insufficient for a tradi...
Maxime Lhuillier, Long Quan
ICCV
2003
IEEE
14 years 6 months ago
Learning How to Inpaint from Global Image Statistics
Inpainting is the problem of filling-in holes in images. Considerable progress has been made by techniques that use the immediate boundary of the hole and some prior information o...
Anat Levin, Assaf Zomet, Yair Weiss
ICCV
2003
IEEE
14 years 6 months ago
Learning Pedestrian Models for Silhouette Refinement
We present a model-based method for accurate extraction of pedestrian silhouettes from video sequences. Our approach is based on two assumptions, 1) there is a common appearance t...
L. Lee, Gerald Dalley, Kinh Tieu
ICCV
2003
IEEE
14 years 6 months ago
Unsupervised Improvement of Visual Detectors using Co-Training
One significant challenge in the construction of visual detection systems is the acquisition of sufficient labeled data. This paper describes a new technique for training visual d...
Anat Levin, Paul A. Viola, Yoav Freund