Sciweavers

CVPR
2008
IEEE
14 years 6 months ago
Simultaneous clustering and tracking unknown number of objects
In this paper, we present a novel on-line probabilistic generative model that simultaneously deals with both the clustering and the tracking of an unknown number of moving objects...
Katsuhiko Ishiguro, Takeshi Yamada, Naonori Ueda
CVPR
2008
IEEE
14 years 6 months ago
Classification using intersection kernel support vector machines is efficient
Straightforward classification using kernelized SVMs requires evaluating the kernel for a test vector and each of the support vectors. For a class of kernels we show that one can ...
Subhransu Maji, Alexander C. Berg, Jitendra Malik
CVPR
2008
IEEE
14 years 6 months ago
Information-theoretic active scene exploration
Studies support the need for high resolution imagery to identify persons in surveillance videos[13]. However, the use of telephoto lenses sacrifices a wider field of view and ther...
Eric Sommerlade, Ian Reid
CVPR
2008
IEEE
14 years 6 months ago
An efficient algorithm for compressed MR imaging using total variation and wavelets
Compressed sensing, an emerging multidisciplinary field involving mathematics, probability, optimization, and signal processing, focuses on reconstructing an unknown signal from a...
Shiqian Ma, Wotao Yin, Yin Zhang, Amit Chakraborty
CVPR
2008
IEEE
14 years 6 months ago
Robust tensor factorization using R1 norm
Over the years, many tensor based algorithms, e.g. two dimensional principle component analysis (2DPCA), two dimensional singular value decomposition (2DSVD), high order SVD, have...
Heng Huang, Chris H. Q. Ding
CVPR
2008
IEEE
14 years 6 months ago
A fast local descriptor for dense matching
We introduce a novel local image descriptor designed for dense wide-baseline matching purposes. We feed our descriptors to a graph-cuts based dense depth map estimation algorithm ...
Engin Tola, Vincent Lepetit, Pascal Fua
CVPR
2008
IEEE
14 years 6 months ago
Hybrid body representation for integrated pose recognition, localization and segmentation
We propose a hybrid body representation that represents each typical pose by both template-like view information and part-based structural information. Specifically, each body par...
Cheng Chen, Guoliang Fan
CVPR
2008
IEEE
14 years 6 months ago
Boosted deformable model for human body alignment
This paper studies image alignment, the problem of learning a shape and appearance model from labeled data and efficiently fitting the model to a non-rigid object with large varia...
Xiaoming Liu 0002, Ting Yu, Thomas Sebastian, Pete...
CVPR
2008
IEEE
14 years 6 months ago
Simultaneous data volume reconstruction and pose estimation from slice samples
Modeling the dynamics of heart and lung tissue is challenging because the tissue deforms between data acquisitions. To reconstruct complete volumes, sample data captured at differ...
Manfred Georg, Richard Souvenir, Andrew Hope, Robe...
CVPR
2008
IEEE
14 years 6 months ago
Two-Dimensional Active Learning for image classification
In this paper, we propose a two-dimensional active learning scheme and show its application in image classification. Traditional active learning methods select samples only along ...
Guo-Jun Qi, Xian-Sheng Hua, Yong Rui, Jinhui Tang,...