University of Oulu

L. Tian, X. Hong, C. Fan, Y. Ming, M. Pietikäinen and G. Zhao, "Sparse Tikhonov-Regularized Hashing for Multi-Modal Learning," 2018 25th IEEE International Conference on Image Processing (ICIP), Athens, 2018, pp. 3793-3797. doi: 10.1109/ICIP.2018.8451580

Sparse Tikhonov-Regularized Hashing for Multi-Modal Learning

Saved in:
Author: Tian, Lei1,2; Hong, Xiaopeng1; Fan, Chunxiao2;
Organizations: 1The Center for Machine Vision and Signal Analysis, University of Oulu, Finland, 90014
2Beijing University of Posts and Telecommunications, Beijing, P.R.China, 100876
Format: article
Version: accepted version
Access: open
Online Access: PDF Full Text (PDF, 0.3 MB)
Persistent link:
Language: English
Published: Institute of Electrical and Electronics Engineers, 2018
Publish Date: 2019-02-28


This paper mainly focuses on the role of regularization in Multi-Modal Learning (MML). Existing MML studies devote most of the efforts in maximizing the consensus of models from cues of different modalities. However, regularization methods are still far from fully explored. To fill in this gap, we propose a compact and efficient coding solution, termed by sparse Tikhonov-Regularized Hashing (STRH). The STRH enforces both the ℓ₀-norm induced sparsity constraints and the Tikhonov regularization on the binary solution vectors which maximize cross-modal correlation. In addition, we raise the concerns on the challenging testing scenario of ‘Multi-modal Learning and Single-modal Prediction’ (MLSP). Finally, we demonstrate that the STRH is an efficient hashing solutions by showing its superiority under the MLSP scenario.

see all

Series: IEEE International Conference on Image Processing
ISSN: 1522-4880
ISSN-E: 2381-8549
ISSN-L: 1522-4880
ISBN: 978-1-4799-7061-2
ISBN Print: 978-1-4799-7062-9
Pages: 3793 - 3797
DOI: 10.1109/ICIP.2018.8451580
Host publication: 2018 25th IEEE International Conference on Image Processing (ICIP)
Conference: IEEE International Conference on Image Processing
Type of Publication: A4 Article in conference proceedings
Field of Science: 213 Electronic, automation and communications engineering, electronics
Funding: This work was supported by the National Natural Science Foundation of China (Grants No. 61402046, 61572205, 61772419), Beijing Natural Science Foundation (Grants No. 4172024), the Academy of Finland, Infotech Oulu, Tekes Fidipro program (Grant No. 1849/31/2015) and Tekes project (Grant No. 3116/31/2017).
Copyright information: © 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.