Sciweavers

CVPR
2001
IEEE
14 years 11 months ago
Event-Based Analysis of Video
Dynamic events can be regarded as long-term temporal objects, which are characterized by spatio-temporal features at multiple temporal scales. Based on this, we design a simple st...
Lihi Zelnik-Manor, Michal Irani
CVPR
2001
IEEE
14 years 11 months ago
Small Sample Learning during Multimedia Retrieval using BiasMap
All positive examples are alike; each negative example is negative in its own way. During interactive multimedia information retrieval, the number of training samples fed-back by ...
Xiang Sean Zhou, Thomas S. Huang
CVPR
2001
IEEE
14 years 11 months ago
Understanding Popout through Repulsion
Perceptual popout is defined by both feature similarity and local feature contrast. We identify these two measures with attraction and repulsion, and unify the dual processes of a...
Stella X. Yu, Jianbo Shi
CVPR
2001
IEEE
14 years 11 months ago
Multibody Grouping via Orthogonal Subspace Decomposition
Ying Wu, Zhengyou Zhang, Thomas S. Huang, John Y. ...
CVPR
2001
IEEE
14 years 11 months ago
Matching of Double-Sided Document Images to Remove Interference
The National Archives of Singapore keeps a large volume of historical handwritten documents. One common problem with the archives is that over the years, ink sipped through the pa...
Qian Wang, Chew Lim Tan
CVPR
2001
IEEE
14 years 11 months ago
Optimal Texture Map Reconstruction from Multiple Views
The recovery of 3D models from multiple reference images involves not only the extraction of 3D shape, but also of texture. Assuming that all surfaces are Lambertian, the resultin...
Lifeng Wang, Sing Bing Kang, Richard Szeliski, Heu...
CVPR
2001
IEEE
14 years 11 months ago
Optimal Adaptive Learning for Image Retrieval
Learning-enhanced relevance feedback is one of the most promising and active research directions in recent year's content-based image retrieval. However, the existing approac...
Tao Wang, Yong Rui, Shi-Min Hu
CVPR
2001
IEEE
14 years 11 months ago
Rapid Object Detection using a Boosted Cascade of Simple Features
This paper describes a machine learning approach for visual object detection which is capable of processing images extremely rapidly and achieving high detection rates. This wor...
Paul A. Viola, Michael J. Jones
CVPR
2001
IEEE
14 years 11 months ago
Using Robust Methods for Automatic Extraction of Buildings
We present a system for modeling buildings from a single correlation-based Digital Elevation Model (DEM). The model is constructed in two stages. The first stage segments the DEM ...
Christophe Vestri, Frederic Devernay