Sciweavers

149
Voted
ICCV
2011
IEEE
14 years 3 months ago
Contextual Weighting for Vocabulary Tree based Image Retrieval
In this paper we address the problem of image retrieval from millions of database images. We improve the vocabulary tree based approach by introducing contextual weighting of loca...
Xiaoyu Wang, Ming Yang, Timothee Cour, Shenghuo Zh...
106
Voted
ICCV
2011
IEEE
14 years 3 months ago
Learning Component-Level Sparse Representation Using Histogram Information for Image Classification
Chen-Kuo Chiang, Chih-Hsueh Duan, Shang-Hong Lai, ...
180
Voted
ICCV
2011
IEEE
14 years 3 months ago
The Generalized Trace-Norm and its Application to Structure-from-Motion Problems
In geometric computer vision, the structure from motion (SfM) problem can be formulated as a optimization problem with a rank constraint. It is well known that the trace norm of a...
Roland Angst, Christopher Zach, Marc Pollefeys
134
Voted
ICCV
2011
IEEE
14 years 3 months ago
A robust pipeline for rapid feature-based pre-alignment of dense range scans
Aiming at reaching an interactive and simplified usage of high-resolution 3D acquisition systems, this paper presents a fast and automated technique for pre-alignment of dense ra...
Francesco Bonarrigo, Alberto Signoroni, Riccardo L...
131
Voted
ICCV
2011
IEEE
14 years 3 months ago
Optimal Estimation of Vanishing Points in a Manhattan World
In this paper, we present an analytical method for computing the globally optimal estimates of orthogonal vanishing points in a “Manhattan world” with a calibrated camera. We ...
Faraz Mirzaei, Stergios Roumeliotis
140
Voted
ICCV
2011
IEEE
14 years 3 months ago
Double Window Optimisation for Constant Time Visual SLAM
We present a novel and general optimisation framework for visual SLAM, which scales for both local, highly accurate reconstruction and large-scale motion with long loop closures. ...
Hauke Strasdat, Andrew J. Davison, J. M. M. Montie...
136
Voted
ICCV
2011
IEEE
14 years 3 months ago
iGroup : Weakly supervised image and video grouping
We present a generic, efficient and iterative algorithm for interactively clustering classes of images and videos. The approach moves away from the use of large hand labelled tra...
Andrew Gilbert, Richard Bowden
162
Voted
ICCV
2011
IEEE
14 years 3 months ago
Gradient-based learning of higher-order image features
Recent work on unsupervised feature learning has shown that learning on polynomial expansions of input patches, such as on pair-wise products of pixel intensities, can improve the...
Roland Memisevic
132
Voted
ICCV
2011
IEEE
14 years 3 months ago
Spatiotemporal Oriented Energies for Spacetime Stereo
This paper presents a novel approach to recovering temporally coherent estimates of 3D structure of a dynamic scene from a sequence of binocular stereo images. The approach is bas...
Mikhail Sizintsev, Richard Wildes
140
Voted
ICCV
2011
IEEE
14 years 3 months ago
Dynamic Fluid Surface Acquisition Using a Camera Array
Acquiring dynamic 3D fluid surfaces is a challenging problem in computer vision. Single or stereo camera based solutions are sensitive to refraction distortions, fast fluid moti...
Yuanyuan Ding, Feng Li, Yu Ji, Jingyi Yu