Sciweavers

CVPR
2008
IEEE
15 years 1 months ago
Who killed the directed model?
Prior distributions are useful for robust low-level vision, and undirected models (e.g. Markov Random Fields) have become a central tool for this purpose. Though sometimes these p...
Justin Domke, Alap Karapurkar, Yiannis Aloimonos
CVPR
2008
IEEE
15 years 1 months ago
Coherent Laplacian 3-D protrusion segmentation
In this paper, an analysis of locally linear embedding (LLE) in the context of clustering is developed. As LLE conserves the local affine coordinates of points, shape protrusions ...
Fabio Cuzzolin, Diana Mateus, David Knossow, Edmon...
CVPR
2008
IEEE
15 years 1 months ago
3D surface models by geometric constraints propagation
This paper proposes a technique for estimating piecewise planar models of objects from their images and geometric constraints. First, assuming a bounded noise in the localization ...
Michela Farenzena, Andrea Fusiello
CVPR
2008
IEEE
15 years 1 months ago
Max Margin AND/OR Graph learning for parsing the human body
We present a novel structure learning method, Max Margin AND/OR Graph (MM-AOG), for parsing the human body into parts and recovering their poses. Our method represents the human b...
Long Zhu, Yuanhao Chen, Yifei Lu, Chenxi Lin, Alan...
CVPR
2008
IEEE
15 years 1 months ago
From appearance to context-based recognition: Dense labeling in small images
Traditionally, object recognition is performed based solely on the appearance of the object. However, relevant information also exists in the scene surrounding the object. As supp...
Devi Parikh, C. Lawrence Zitnick, Tsuhan Chen
CVPR
2008
IEEE
15 years 1 months ago
Shape priors in variational image segmentation: Convexity, Lipschitz continuity and globally optimal solutions
In this work, we introduce a novel implicit representation of shape which is based on assigning to each pixel a probability that this pixel is inside the shape. This probabilistic...
Daniel Cremers, Frank R. Schmidt, Frank Barthel
CVPR
2008
IEEE
15 years 1 months ago
Cost-sensitive face recognition
Traditional face recognition systems attempt to achieve a high recognition accuracy, which implicitly assumes that the losses of all misclassifications are the same. However, in m...
Yin Zhang, Zhi-Hua Zhou
CVPR
2008
IEEE
15 years 1 months ago
Fast texture segmentation model based on the shape operator and active contour
We present an approach for unsupervised segmentation of natural and textural images based on active contour, differential geometry and information theoretical concept. More precis...
Nawal Houhou, Jean-Philippe Thiran, Xavier Bresson
CVPR
2008
IEEE
15 years 1 months ago
Summarizing visual data using bidirectional similarity
We propose a principled approach to summarization of visual data (images or video) based on optimization of a well-defined similarity measure. The problem we consider is re-target...
Denis Simakov, Yaron Caspi, Eli Shechtman, Michal ...
CVPR
2008
IEEE
15 years 1 months ago
Globally optimal bilinear programming for computer vision applications
We present a practical algorithm that provably achieves the global optimum for a class of bilinear programs commonly arising in computer vision applications. Our approach relies o...
Manmohan Krishna Chandraker, David J. Kriegman