Sciweavers

CVPR
2004
IEEE
15 years 3 days ago
Minimum Effective Dimension for Mixtures of Subspaces: A Robust GPCA Algorithm and Its Applications
In this paper, we propose a robust model selection criterion for mixtures of subspaces called minimum effective dimension (MED). Previous information-theoretic model selection cri...
Kun Huang, René Vidal, Yi Ma
CVPR
2004
IEEE
15 years 3 days ago
MetaMorphs: Deformable Shape and Texture Models
We present a new class of deformable models, MetaMorphs, whose formulation integrates both shape and interior texture. The model deformations are derived from both boundary and re...
Xiaolei Huang, Dimitris N. Metaxas, Ting Chen
CVPR
2004
IEEE
15 years 3 days ago
Multi-Scale Visual Tracking by Sequential Belief Propagation
A novel statistical method is proposed in this paper to overcome abrupt motion for robust visual tracking. Existing tracking methods that are based on the small motion assumption ...
Gang Hua, Ying Wu
CVPR
2004
IEEE
15 years 3 days ago
Shedding Light on Stereoscopic Segmentation
We propose a variational algorithm to jointly estimate the shape, albedo, and light configuration of a Lambertian scene from a collection of images taken from different vantage po...
Hailin Jin, Daniel Cremers, Anthony J. Yezzi, Stef...
CVPR
2004
IEEE
15 years 3 days ago
Video Repairing: Inference of Foreground and Background under Severe Occlusion
In this paper, we propose a new method, video repairing, to robustly infer missing static background and moving foreground due to severe damage or occlusion from a video. To recov...
Jiaya Jia, Tai-Pang Wu, Yu-Wing Tai, Chi-Keung Tan...
CVPR
2004
IEEE
15 years 3 days ago
Optimizing Motion Estimation with Linear Programming and Detail-Preserving Variational Method
In this paper, we propose a novel linear programming based method to estimate arbitrary motion from two images. The proposed method always finds the global optimal solution of the...
Hao Jiang, Ze-Nian Li, Mark S. Drew
CVPR
2004
IEEE
15 years 3 days ago
Effect of Colorspace Transformation, the Illuminance Component, and Color Modeling on Skin Detection
Skin detection is an important preliminary process in human motion analysis. It is commonly performed in three steps: transforming the pixel color to a non-RGB colorspace, droppin...
Sriram Jayaram, Stephen Schmugge, Min C. Shin, Leo...
CVPR
2004
IEEE
15 years 3 days ago
Segment-Based Stereo Matching Using Graph Cuts
In this paper, we present a new segment-based stereo matching algorithm using graph cuts. In our approach, the reference image is divided into non-overlapping homogeneous segments...
Li Hong, George Chen
CVPR
2004
IEEE
15 years 3 days ago
Object-Based Image Retrieval Using the Statistical Structure of Images
We propose a new Bayesian approach to object-based image retrieval with relevance feedback. Although estimating the object posterior probability density from few examples seems in...
Derek Hoiem, Rahul Sukthankar, Henry Schneiderman,...
CVPR
2004
IEEE
15 years 3 days ago
Value Directed Learning of Gestures and Facial Displays
This paper presents a method for learning decision theoretic models of facial expressions and gestures from video data. We consider that the meaning of a facial display or gesture...
Jesse Hoey, James J. Little