Sciweavers

CVPR
2008
IEEE
15 years 1 months ago
Learning 4D action feature models for arbitrary view action recognition
In this paper we present a novel approach using a 4D (x,y,z,t) action feature model (4D-AFM) for recognizing actions from arbitrary views. The 4D-AFM elegantly encodes shape and m...
Pingkun Yan, Saad M. Khan, Mubarak Shah
CVPR
2008
IEEE
15 years 1 months ago
A factorization approach to structure from motion with shape priors
This paper presents an approach for including 3D prior models into a factorization framework for structure from motion. The proposed method computes a closed-form affine fit which...
Alessio Del Bue
CVPR
2008
IEEE
15 years 1 months ago
Human action recognition using Local Spatio-Temporal Discriminant Embedding
Human action video sequences can be considered as nonlinear dynamic shape manifolds in the space of image frames. In this paper, we address learning and classifying human actions ...
Kui Jia, Dit-Yan Yeung
CVPR
2008
IEEE
15 years 1 months ago
The scale of a texture and its application to segmentation
This paper examines the issue of scale in modeling texture for the purpose of segmentation. We propose a scale descriptor for texture and an energy minimization model to find the ...
Byung-Woo Hong, Kangyu Ni, Stefano Soatto, Tony F....
CVPR
2008
IEEE
15 years 1 months ago
Learning on lie groups for invariant detection and tracking
Oncel Tuzel, Fatih Murat Porikli, Peter Meer
CVPR
2008
IEEE
15 years 1 months ago
Action recognition using ballistic dynamics
We present a Bayesian framework for action recognition through ballistic dynamics. Psycho-kinesiological studies indicate that ballistic movements form the natural units for human...
Shiv Naga Prasad Vitaladevuni, Vili Kellokumpu, La...
CVPR
2008
IEEE
15 years 1 months ago
Mining compositional features for boosting
The selection of weak classifiers is critical to the success of boosting techniques. Poor weak classifiers do not perform better than random guess, thus cannot help decrease the t...
Junsong Yuan, Jiebo Luo, Ying Wu
CVPR
2008
IEEE
15 years 1 months ago
Estimating camera response functions using probabilistic intensity similarity
We propose a method for estimating camera response functions using a probabilistic intensity similarity measure. The similarity measure represents the likelihood of two intensity ...
Jun Takamatsu, Yasuyuki Matsushita, Katsushi Ikeuc...
CVPR
2008
IEEE
15 years 1 months ago
Tensor reduction error analysis - Applications to video compression and classification
Tensor based dimensionality reduction has recently been extensively studied for computer vision applications. To our knowledge, however, there exist no rigorous error analysis on ...
Chris H. Q. Ding, Heng Huang, Dijun Luo