Sciweavers

155 search results - page 18 / 31
» Exploiting Unlabeled Data in Content-Based Image Retrieval
Sort
View
CVPR
2008
IEEE
14 years 9 months ago
A joint appearance-spatial distance for kernel-based image categorization
The goal of image categorization is to classify a collection of unlabeled images into a set of predefined classes to support semantic-level image retrieval. The distance measures ...
Guo-Jun Qi, Xian-Sheng Hua, Yong Rui, Jinhui Tang,...
AAAI
2007
13 years 9 months ago
Semi-Supervised Learning with Very Few Labeled Training Examples
In semi-supervised learning, a number of labeled examples are usually required for training an initial weakly useful predictor which is in turn used for exploiting the unlabeled e...
Zhi-Hua Zhou, De-Chuan Zhan, Qiang Yang
MM
2009
ACM
221views Multimedia» more  MM 2009»
14 years 2 months ago
Using large-scale web data to facilitate textual query based retrieval of consumer photos
The rapid popularization of digital cameras and mobile phone cameras has lead to an explosive growth of consumer photo collections. In this paper, we present a (quasi) real-time t...
Yiming Liu, Dong Xu, Ivor W. Tsang, Jiebo Luo
SSDBM
1998
IEEE
107views Database» more  SSDBM 1998»
13 years 11 months ago
Discrete Object Detection and Motion Registration Based on a Data Management Approach
When scientific data sets can be interpreted visually they are typically managed as pictures and consequently stored as large collections of bitmaps. Valuable information containe...
Hans Hinterberger, Bettina Bauer-Messmer
MM
2004
ACM
173views Multimedia» more  MM 2004»
14 years 27 days ago
Cortina: a system for large-scale, content-based web image retrieval
Recent advances in processing and networking capabilities of computers have led to an accumulation of immense amounts of multimedia data such as images. One of the largest reposit...
Till Quack, Ullrich Mönich, Lars Thiele, B. S...