Thumbnail
Access Restriction
Subscribed

Author Yoonseop Kang ♦ Saehoon Kim ♦ Seungjin Choi
Source IEEE Xplore Digital Library
Content type Text
Publisher Institute of Electrical and Electronics Engineers, Inc. (IEEE)
File Format PDF
Copyright Year ©2012
Language English
Subject Domain (in DDC) Computer science, information & general works ♦ Computer programming, programs & data
Subject Keyword Binary codes ♦ Training ♦ Visualization ♦ Computational modeling ♦ Hamming distance ♦ Linear programming ♦ Machine learning ♦ restricted Boltzmann machines ♦ deep learning ♦ harmonium ♦ hashing ♦ multi-view learning
Abstract Hashing seeks an embedding of high-dimensional objects into a similarity-preserving low-dimensional Hamming space such that similar objects are indexed by binary codes with small Hamming distances. A variety of hashing methods have been developed, but most of them resort to a single view (representation) of data. However, objects are often described by multiple representations. For instance, images are described by a few different visual descriptors (such as SIFT, GIST, and HOG), so it is desirable to incorporate multiple representations into hashing, leading to multi-view hashing. In this paper we present a deep network for multi-view hashing, referred to as deep multi-view hashing, where each layer of hidden nodes is composed of view-specific and shared hidden nodes, in order to learn individual and shared hidden spaces from multiple views of data. Numerical experiments on image datasets demonstrate the useful behavior of our deep multi-view hashing (DMVH), compared to recently-proposed multi-modal deep network as well as existing shallow models of hashing.
ISBN 9781467346498
ISSN 15504786
Educational Role Student ♦ Teacher
Age Range above 22 year
Educational Use Research ♦ Reading
Education Level UG and PG
Learning Resource Type Article
Publisher Date 2012-12-10
Publisher Place Belgium
Rights Holder Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Size (in Bytes) 470.96 kB
Page Count 6
Starting Page 930
Ending Page 935


Source: IEEE Xplore Digital Library