109
Voted
CVPR
2007
IEEE
16 years 2 months ago
2007
IEEE
A novel algorithm called Average Neighborhood Margin Maximization (ANMM) is proposed for supervised linear feature extraction. For each data point, ANMM aims at pulling the neighb...
93
Voted
CVPR
2007
IEEE
16 years 2 months ago
2007
IEEE
In object tracking, occlusions significantly undermine the performance of tracking algorithms. Unlike the existing methods that solely depend on the observed target appearance to ...
CVPR
2007
IEEE
16 years 2 months ago
2007
IEEE
A large family of algorithms for dimensionality reduction end with solving a Trace Ratio problem in the form of arg maxW Tr(WT SpW)/Tr(WT SlW)1 , which is generally transformed in...
124
Voted
CVPR
2007
IEEE
16 years 2 months ago
2007
IEEE
This paper presents a method of learning and recognizing generic object categories using part-based spatial models. The models are multiscale, with a scene component that specifie...
108
Voted
CVPR
2007
IEEE
16 years 2 months ago
2007
IEEE
For video summarization and retrieval, one of the important modules is to group temporal-spatial coherent shots into high-level semantic video clips namely scene segmentation. In ...
CVPR
2007
IEEE
16 years 2 months ago
2007
IEEE
114
click to vote
CVPR
2007
IEEE
16 years 2 months ago
2007
IEEE
Discontinuity preserving filtering of images is an important low-level vision task. With the development of new imaging techniques like diffusion tensor imaging (DTI), where the d...
107
Voted
CVPR
2007
IEEE
16 years 2 months ago
2007
IEEE
A jigsaw is a recently proposed generative model that describes an image as a composition of non-overlapping patches of varying shape, extracted from a latent image. By learning t...
100
Voted
CVPR
2007
IEEE
16 years 2 months ago
2007
IEEE
Utilization of an acoustic camera for range measurements is a key advantage for 3-D shape recovery of underwater targets by opti-acoustic stereo imaging, where the associated epip...
115
Voted
CVPR
2007
IEEE
16 years 2 months ago
2007
IEEE
Conventional stereo matching algorithms assume color constancy on the corresponding opaque pixels in the stereo images. However, when the foreground objects with fractional bounda...