Dynamic probabilistic CCA for analysis of affective behaviour

Mihalis A. Nicolaou*, Vladimir Pavlovic, Maja Pantic

*Corresponding author for this work

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

    19 Citations (Scopus)
    199 Downloads (Pure)

    Abstract

    Fusing multiple continuous expert annotations is a crucial problem in machine learning and computer vision, particularly when dealing with uncertain and subjective tasks related to affective behaviour. Inspired by the concept of inferring shared and individual latent spaces in probabilistic CCA (PCCA), we firstly propose a novel, generative model which discovers temporal dependencies on the shared/individual spaces (DPCCA). In order to accommodate for temporal lags which are prominent amongst continuous annotations, we further introduce a latent warping process. We show that the resulting model (DPCTW) (i) can be used as a unifying framework for solving the problems of temporal alignment and fusion of multiple annotations in time, and (ii) that by incorporating dynamics, modelling annotation/sequence specific biases, noise estimation and time warping, DPCTW outperforms state-of-the-art methods for both the aggregation of multiple, yet imperfect expert annotations as well as the alignment of affective behavior.

    Original languageEnglish
    Title of host publicationComputer Vision, ECCV 2012
    Subtitle of host publication12th European Conference on Computer Vision, Florence, Italy, October 7-13, 2012. Proceedings, Part VII
    EditorsAndrew Andrew Fitzgibbon
    Place of PublicationBerlin, Heidelberg
    PublisherSpringer
    Pages98-111
    Number of pages14
    EditionPART 7
    ISBN (Electronic)978-3-642-33786-4
    ISBN (Print)978-3-642-33785-7
    DOIs
    Publication statusPublished - 7 Oct 2012
    Event12th European Conference on Computer Vision, ECCV 2012 - Florence, Italy
    Duration: 7 Oct 201213 Oct 2012

    Publication series

    NameLecture Notes in Computer Science
    PublisherSpringer
    Volume7578
    ISSN (Print)0302-9743
    ISSN (Electronic)1611-3349

    Conference

    Conference12th European Conference on Computer Vision, ECCV 2012
    Country/TerritoryItaly
    CityFlorence
    Period7/10/1213/10/12

    Keywords

    • EC Grant Agreement nr.: ERC-2007-STG-203143 (MAHNOB)
    • EC Grant Agreement nr.: FP7/288235
    • EC Grant Agreement nr.: FP7/2007-2013
    • HMI-MI: MULTIMODAL INTERACTIONS
    • 2024 OA procedure

    Fingerprint

    Dive into the research topics of 'Dynamic probabilistic CCA for analysis of affective behaviour'. Together they form a unique fingerprint.

    Cite this