Hetero-manifold regularisation for cross-modal hashing

Zheng, Feng, Tang, Yi and Shao, Ling (2018) Hetero-manifold regularisation for cross-modal hashing. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40 (5). pp. 1059-1071. ISSN 0162-8828

Preview

PDF (Accepted manuscript) - Accepted Version Download (946kB) | Preview

Abstract

Recently, cross-modal search has attracted considerable attention but remains a very challenging task because of the integration complexity and heterogeneity of the multi-modal data. To address both challenges, in this paper, we propose a novel method termed hetero-manifold regularisation (HMR) to supervise the learning of hash functions for efficient cross-modal search. A hetero-manifold integrates multiple sub-manifolds defined by homogeneous data with the help of cross-modal supervision information. Taking advantages of the hetero-manifold, the similarity between each pair of heterogeneous data could be naturally measured by three order random walks on this hetero-manifold. Furthermore, a novel cumulative distance inequality defined on the hetero-manifold is introduced to avoid the computational difficulty induced by the discreteness of hash codes. By using the inequality, cross-modal hashing is transformed into a problem of hetero-manifold regularised support vector learning. Therefore, the performance of cross-modal search can be significantly improved by seamlessly combining the integrated information of the hetero-manifold and the strong generalisation of the support vector machine. Comprehensive experiments show that the proposed HMR achieve advantageous results over the state-of-the-art methods in several challenging cross-modal tasks.

Item Type:	Article
Uncontrolled Keywords:	cumulative distance inequality,cross-modal hashing,manifold regularisation,information propagation,hinge loss constraint
Faculty \ School:	Faculty of Science > School of Computing Sciences
Related URLs:	http://ieeexplore.ieee.org/document/7801...
Depositing User:	Pure Connector
Date Deposited:	14 Jan 2017 00:07
Last Modified:	22 Oct 2022 02:06
URI:	https://ueaeprints.uea.ac.uk/id/eprint/62091
DOI:	10.1109/TPAMI.2016.2645565

Downloads

Actions (login required)

View Item