arrow
返回

Learning Discriminative Binary Codes for Large-scale Cross-modal Retrieval

delete2017-05-01
delete382
PRE
AI
X
Xing Xu
Shen Fumin 封面图
Shen Fumin (Fumin Shen) *
杨
杨阳 (Yang Yang)
申恒涛 封面图
申恒涛 (Heng Tao Shen)
李学龙 封面图
李学龙 (Xuelong Li)
DOI:10.1109/TIP.2017.2676345delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
Hashing based methods have attracted considerable attention for efficient cross-modal retrieval on large-scale multimedia data. The core problem of cross-modal hashing is how to learn compact binary codes that construct the underlying correlations between heterogeneous features from different modalities. A majority of recent approaches aim at learning hash functions to preserve the pairwise similarities defined by given class labels. However, these methods fail to explicitly explore the discriminative property of class labels during hash function learning. In addition, they usually discard the discrete constraints imposed on the to-be-learned binary codes, and compromise to solve a relaxed problem with quantization to obtain the approximate binary solution. Therefore, the binary codes generated by these methods are suboptimal and less discriminative to different classes. To overcome these drawbacks, we propose a novel cross-modal hashing method, termed discrete cross-modal hashing (DCH), which directly learns discriminative binary codes while retaining the discrete constraints. Specifically, DCH learns modality-specific hash functions for generating unified binary codes, and these binary codes are viewed as representative features for discriminative classification with class labels. An effective discrete optimization algorithm is developed for DCH to jointly learn the modality-specific hash function and the unified binary codes. Extensive experiments on three benchmark data sets highlight the superiority of DCH under various cross-modal scenarios and show its state-of-the-art performance.
Keyword:
Cross-modal retrieval
hashing
discrete optimization
discriminant analysis
AI总结

AI总结

对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

IEEE Transactions on Image Processing 封面图
IEEE Transactions on Image Processing
IF:
13.7
论文数:
1.0W
被引数:
8.4W

机构

S
state key laboratory of transient optics & photonics
学者数:
842
论文数: 634
被引数: 0
引用论文

引用论文

The effect of a novel extracorporeal cytokine hemoadsorption device on IL-6 elimination in septic patients: A randomized controlled trial
err2017-10-30
err0
errOAAI
errDirk Schädler; Christine Pausch; Daniel Heise; Andreas Meier-Hellmann; Jörg Brederlau; Norbert Weiler; Gernot Marx; Christian Putensen; Claudia Spies; Achim Jörres; Michael Quintel; Christoph Engel; John A. Kellum; Martin K. Kuhlmann
err分享
err收藏
Hashing on Nonlinear Manifolds
err2015-06-01
err136
errOAAI
errShen, Fumin; Shen, Chunhua; Shi, Qinfeng; van den Hengel, Anton; Tang, Zhenmin; Shen, Heng Tao
err分享
err收藏
Full-Space Local Topology Extraction for Cross-Modal Retrieval
err2015-07-01
err26
PREAI
errZhang, Lei; Zhang, Yongdong; Hong, Richang; Tian, Qi
err分享
err收藏
A Fast Optimization Method for General Binary Code Learning
err2016-12-01
err135
PREAI
errShen, Fumin; Zhou, Xiang; Yang, Yang; Song, Jingkuan; Shen, Heng Tao; Tao, Dacheng
err分享
err收藏
Rotterdam Transition Test
err2021-08-05
err0
errOAAI
errMartha A.C. van Gaalen; Merel van Pieterson; Gertrude van den Brink; Lissy de Ridder; Dimitris Rizopoulos; C. Janneke van der Woude; Johanna C. Escher
err分享
err收藏
学者 查看更多内容