Sciweavers

3DPVT
2006
IEEE
240views Visualization» more  3DPVT 2006»
13 years 9 months ago
Global Depth from Epipolar Volumes--A General Framework for Reconstructing Non-Lambertian Surfaces
Using Epipolar Image Analysis in the context of the correspondence finding problem in depth reconstruction has several advantages. One is the elegant incorporation of prior knowl...
Timo Stich, Art Tevs, Marcus A. Magnor
IJCNN
2007
IEEE
13 years 10 months ago
Agnostic Learning vs. Prior Knowledge Challenge
We organized a challenge for IJCNN 2007 to assess the added value of prior domain knowledge in machine learning. Most commercial data mining programs accept data pre-formatted in ...
Isabelle Guyon, Amir Saffari, Gideon Dror, Gavin C...
ICPR
2008
IEEE
13 years 10 months ago
Object-of-interest extraction by integrating stochastic inference with learnt active shape sketch
This article presents a novel integrated approach to object of interest extraction, including learning to define target pattern and extracting by combining detection and segmenta...
Hongwei Li, Liang Lin, Tianfu Wu, Xiaobai Liu, Lan...
PAKDD
2009
ACM
186views Data Mining» more  PAKDD 2009»
13 years 10 months ago
Pairwise Constrained Clustering for Sparse and High Dimensional Feature Spaces
Abstract. Clustering high dimensional data with sparse features is challenging because pairwise distances between data items are not informative in high dimensional space. To addre...
Su Yan, Hai Wang, Dongwon Lee, C. Lee Giles
CHI
2009
ACM
13 years 10 months ago
Understanding knowledge management practices for early design activity and its implications for reuse
Prior knowledge is a critical resource for design, especially when designers are striving to generate new ideas for complex problems. Systems that improve access to relevant prior...
Moushumi Sharmin, Brian P. Bailey, Cole Coats, Kev...
CVPR
2010
IEEE
13 years 11 months ago
Safety in Numbers: Learning Categories from Few Examples with Multi Model Knowledge Transfer
Learning object categories from small samples is a challenging problem, where machine learning tools can in general provide very few guarantees. Exploiting prior knowledge may be ...
Tatiana Tommasi, Francesco Orabona, Barbara Caputo
CVPR
2005
IEEE
14 years 5 months ago
Feature Kernel Functions: Improving SVMs Using High-Level Knowledge
Kernel functions are often cited as a mechanism to encode prior knowledge of a learning task. But it can be difficult to capture prior knowledge effectively. For example, we know ...
Qiang Sun, Gerald DeJong
CVPR
2004
IEEE
14 years 5 months ago
Separating Reflections from a Single Image Using Local Features
When we take a picture through a window the image we obtain is often a linear superposition of two images: the image of the scene beyond the window plus the image of the scene ref...
Anat Levin, Assaf Zomet, Yair Weiss