Sciweavers

CVPR
2010
IEEE
13 years 2 months ago
Adaptive pose priors for pictorial structures
Pictorial structure (PS) models are extensively used for part-based recognition of scenes, people, animals and multi-part objects. To achieve tractability, the structure and param...
Benjamin Sapp, Chris Jordan, Ben Taskar
CVPR
2010
IEEE
13 years 2 months ago
Multi-structure model selection via kernel optimisation
Our goal is to fit the multiple instances (or structures) of a generic model existing in data. Here we propose a novel model selection scheme to estimate the number of genuine str...
Tat-Jun Chin, David Suter, Hanzi Wang
CVPR
2010
IEEE
13 years 2 months ago
Spherical embeddings for non-Euclidean dissimilarities
Richard C. Wilson, Edwin R. Hancock, Elzbieta Peka...
CVPR
2010
IEEE
13 years 2 months ago
Visual classification with multi-task joint sparse representation
We address the problem of computing joint sparse representation of visual signal across multiple kernel-based representations. Such a problem arises naturally in supervised visual...
Xiaotong Yuan, Shuicheng Yan
CVPR
2010
IEEE
13 years 2 months ago
Talking pictures: Temporal grouping and dialog-supervised person recognition
Timothee Cour, Benjamin Sapp, Akash Nagle, Ben Tas...
CVPR
2010
IEEE
13 years 2 months ago
Part and appearance sharing: Recursive Compositional Models for multi-view
We propose Recursive Compositional Models (RCMs) for simultaneous multi-view multi-object detection and parsing (e.g. view estimation and determining the positions of the object s...
Long Zhu, Yuanhao Chen, Antonio Torralba, William ...
CVPR
2010
IEEE
13 years 2 months ago
Rectilinear parsing of architecture in urban environment
We propose an approach that parses registered images captured at ground level into architectural units for large-scale city modeling. Each parsed unit has a regularized shape, whi...
Peng Zhao, Tian Fang, Jianxiong Xiao, Honghui Zhan...
CVPR
2010
IEEE
13 years 2 months ago
Axial light field for curved mirrors: Reflect your perspective, widen your view
Mirrors have been used to enable wide field-of-view (FOV) catadioptric imaging. The mapping between the incoming and reflected light rays depends non-linearly on the mirror shape ...
Yuichi Taguchi, Amit K. Agrawal, Srikumar Ramaling...
CVPR
2010
IEEE
13 years 2 months ago
Group motion segmentation using a Spatio-Temporal Driving Force Model
We consider the `group motion segmentation' problem and provide a solution for it. The group motion segmentation problem aims at analyzing motion trajectories of multiple obj...
Ruonan Li, Rama Chellappa
CVPR
2010
IEEE
13 years 2 months ago
Efficient computation of robust low-rank matrix approximations in the presence of missing data using the L1 norm
The calculation of a low-rank approximation of a matrix is a fundamental operation in many computer vision applications. The workhorse of this class of problems has long been the ...
Anders Eriksson, Anton van den Hengel