Learning a cross-modal hashing network for multimedia search

In this paper, we propose a cross-modal hashing network (CMHN) method to learn compact binary codes for cross-modality multimedia search. Unlike most existing cross-modal hashing methods which learn a single pair of projections to map each example into a binary vector, we design a deep neural networ...

Full description

Saved in:
Bibliographic Details
Main Authors: Liong, Venice Erin, Lu, Jiwen, Tan, Yap-Peng
Format: Conference Proceeding
Language:English
Subjects:
Benchmark testing
binary code learning
Binary codes
cross-modal retrieval
hashing
Multimedia communication
Optimization
Quantization (signal)
Semantics
Training
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, we propose a cross-modal hashing network (CMHN) method to learn compact binary codes for cross-modality multimedia search. Unlike most existing cross-modal hashing methods which learn a single pair of projections to map each example into a binary vector, we design a deep neural network to learn multiple pairs of hierarchical non-linear transformations, under which the nonlinear characteristics of samples can be well exploited and the modality gap is well reduced. Our model is trained under an iterative optimization procedure which learns a (1) unified binary code discretely and discriminatively through a classification-based hinge-loss criterion, and (2) cross-modal hashing network, one deep network for each modality, through minimizing the quantization loss between real-valued neural code and binary code, and maximizing the variance of the learned neural codes. Experimental results on two benchmark datasets show the efficacy of the proposed approach.
ISSN:2381-8549
DOI:10.1109/ICIP.2017.8296973