Learning image manifold using web data

Authors:
Xin-Jing Wang;Wei-Ying Ma;Xing Li
Affiliations:
Microsoft Research Asia, Beijing, P.R. China;Microsoft Research Asia, Beijing, P.R. China;Department of Electronic Engineering, Tsinghua University, Beijing, P.R. China
Venue:
PCM'04 Proceedings of the 5th Pacific Rim Conference on Advances in Multimedia Information Processing - Volume Part II
Year:
2004

Citing 5
Cited 0

ParaSite: mining structural information on the Web

Selected papers from the sixth international conference on World Wide Web
Building a web thesaurus from web link structure

Proceedings of the 26th annual international ACM SIGIR conference on Research and development in informaion retrieval
Contrast-based image attention analysis by using fuzzy growing

MULTIMEDIA '03 Proceedings of the eleventh ACM international conference on Multimedia
Learning block importance models for web pages

Proceedings of the 13th international conference on World Wide Web
Learning an image manifold for retrieval

Proceedings of the 12th annual ACM international conference on Multimedia

Quantified Score

Hi-index	0.00

Visualization

Abstract

Manifold learning has become a hot research topic in recent years and is widely used in the area of dimension reduction, information retrieval and ranking, etc. However, how to reconstruct the intrinsic manifold from the observed data points, i.e. what is the proper data point distance measure, is still an open problem. In this paper, we propose to take advantages of the information provided by web-pages and the image-related website link structure to learn the Web image manifold, which better approaches to the intrinsic manifold than those learned by previous methods which use Euclidean alike distances to construct the initial affinity matrix. Experimental results prove the effectiveness of our learned Web image manifold.