Variational Gaussian Process Auto-Encoder for Ordinal Prediction of Facial Action Units

Stefanos Eleftheriadis, Ognjen Rudovic, Marc Peter Deisenroth, Maja Pantic

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

    15 Citations (Scopus)
    31 Downloads (Pure)


    We address the task of simultaneous feature fusion and modeling of discrete ordinal outputs. We propose a novel Gaussian process (GP) auto-encoder modeling approach. In particular, we introduce GP encoders to project multiple observed features onto a latent space, while GP decoders are responsible for reconstructing the original features. Inference is performed in a novel variational framework, where the recovered latent representations are further constrained by the ordinal output labels. In this way, we seamlessly integrate the ordinal structure in the learned manifold, while attaining robust fusion of the input features. We demonstrate the representation abilities of our model on benchmark datasets from machine learning and affect analysis. We further evaluate the model on the tasks of feature fusion and joint ordinal prediction of facial action units. Our experiments demonstrate the benefits of the proposed approach compared to the state of the art.
    Original languageEnglish
    Title of host publicationComputer Vision – ACCV 2016
    Subtitle of host publication13th Asian Conference on Computer Vision, Taipei, Taiwan, November 20-24, 2016, Revised Selected Papers
    EditorsShang-Hong Lai, Vincent Lepetit, Ko Nishino, Yoichi Sato
    Place of PublicationNew York
    Number of pages16
    ISBN (Electronic)978-3-319-54184-6
    ISBN (Print)978-3-319-54183-9
    Publication statusPublished - Nov 2016
    Event13th Asian Conference on Computer Vision, ACCV 2016 - National Chiao Tung University, Taipei, Taiwan
    Duration: 21 Nov 201623 Nov 2016
    Conference number: 13

    Publication series

    NameLecture Notes in Computer Science
    PublisherSpringer Verlag
    ISSN (Print)0302-9743
    ISSN (Electronic)1611-3349


    Conference13th Asian Conference on Computer Vision, ACCV 2016
    Abbreviated titleACCV


    • HMI-HF: Human Factors
    • EWI-27595


    Dive into the research topics of 'Variational Gaussian Process Auto-Encoder for Ordinal Prediction of Facial Action Units'. Together they form a unique fingerprint.

    Cite this