skip to main content
Show Results with:

Multi-view manifold learning with locality alignment

Zhao, Yue et al.

Pattern recognition. Volume 78 (2018, June); pp 154-166 -- Elsevier Science

Online access

  • Title:
    Multi-view manifold learning with locality alignment
  • Author: Zhao, Yue;
    You, Xinge;
    Yu, Shujian;
    Xu, Chang;
    Yuan, Wei;
    Jing, Xiao-Yuan;
    Zhang, Taiping;
    Tao, Dacheng
  • Found In: Pattern recognition. Volume 78 (2018, June); pp 154-166
  • Journal Title: Pattern recognition
  • Subjects: Perception des structures--Périodiques; Pattern perception--Periodicals; Patroonherkenning; Manifold learning--Multi-view learning--Locality alignment; Dewey: 006.4
  • Rights: legaldeposit
  • Publication Details: Elsevier Science
  • Abstract: Highlights:

    We learn low-dimensional spaces contain sufficient information of input views.

    We add locality alignment to enhance the discrimination of the latent spaces.

    We propose frameworks under supervised and unsupervised scenarios.


    Manifold learning aims to discover the low dimensional space where the input high dimensional data are embedded by preserving the geometric structure. Unfortunately, almost all the existing manifold learning methods were proposed under single view scenario, and they cannot be straightforwardly applied to multiple feature sets. Although concatenating multiple views into a single feature provides a plausible solution, it remains a question on how to better explore the independence and interdependence of different views while conducting manifold learning. In this paper, we propose a multi-view manifold learning with locality alignment (MVML-LA) framework to learn a common yet discriminative low-dimensional latent space that contain sufficient information of original inputs. Both supervised algorithm (S-MVML-LA) and unsupervised algorithm (U-MVML-LA) are developed. Experiments on benchmark real-world datasets demonstrate the superiority of our proposed S-MVML-LA and U-MVML-LA over existing state-of-the-art methods.

  • Identifier: System Number: LDEAvdc_100089509801.0x000001; Journal ISSN: 0031-3203; 10.1016/j.patcog.2018.01.012
  • Publication Date: 2018
  • Physical Description: Electronic
  • Shelfmark(s): ELD Digital store

Searching Remote Databases, Please Wait