Sciweavers

84
Voted
CVPR
2008
IEEE
16 years 2 months ago
Annotating collections of photos using hierarchical event and scene models
Liangliang Cao, Jiebo Luo, Henry S. Kautz, Thomas ...
94
Voted
CVPR
2008
IEEE
16 years 2 months ago
Directions of egomotion from antipodal points
We present a novel geometrical constraint on the egomotion of a single, moving camera. Using a camera with a large field-of-view (FOV), the optical flow measured at a single pair ...
John Lim, Nick Barnes
95
Voted
CVPR
2008
IEEE
16 years 2 months ago
Histogram-based search: A comparative study
Histograms represent a popular means for feature representation. This paper is concerned with the problem of exhaustive histogram-based image search. Several standard histogram co...
Mikhail Sizintsev, Konstantinos G. Derpanis, Andre...
105
Voted
CVPR
2008
IEEE
16 years 2 months ago
Spectral methods for semi-supervised manifold learning
Given a finite number of data points sampled from a low-dimensional manifold embedded in a high dimensional space together with the parameter vectors for a subset of the data poin...
Zhenyue Zhang, Hongyuan Zha, Min Zhang
112
Voted
CVPR
2008
IEEE
16 years 2 months ago
Efficient sequential correspondence selection by cosegmentation
In many retrieval, object recognition and wide baseline stereo methods, correspondences of interest points are established possibly sublinearly by matching a compact descriptor su...
Jan Cech, Jiri Matas, Michal Perdoch
116
Voted
CVPR
2008
IEEE
16 years 2 months ago
Local deformation models for monocular 3D shape recovery
Without a deformation model, monocular 3D shape recovery of deformable surfaces is severly under-constrained. Even when the image information is rich enough, prior knowledge of th...
Mathieu Salzmann, Raquel Urtasun, Pascal Fua
109
Voted
CVPR
2008
IEEE
16 years 2 months ago
Multi-label image segmentation via point-wise repetition
Bottom-up segmentation tends to rely on local features. Yet, many natural and man-made objects contain repeating elements. Such structural and more spread-out features are importa...
Gang Zeng, Luc J. Van Gool
94
Voted
CVPR
2008
IEEE
16 years 2 months ago
Learning patch correspondences for improved viewpoint invariant face recognition
Variation due to viewpoint is one of the key challenges that stand in the way of a complete solution to the face recognition problem. It is easy to note that local regions of the ...
Ahmed Bilal Ashraf, Simon Lucey, Tsuhan Chen
122
Voted
CVPR
2008
IEEE
16 years 2 months ago
Privacy preserving crowd monitoring: Counting people without people models or tracking
Antoni B. Chan, Zhang-Sheng John Liang, Nuno Vasco...