MURAL - Maynooth University Research Archive Library



    Seeing is Worse than Believing: Reading People’s Minds Better than Computer-Vision Methods Recognize Actions


    Barbu, Andrei and Barrett, Daniel P. and Chen, Wei and Siddharth, N. and Xiong, Caiming and Corso, Jason J. and Fellbaum, Christiane D. and Hanson, Catherine and Hanson, Stephen Jose and Helie, Sebastien and Malaia, Evguenia and Pearlmutter, Barak A. and Siskind, Jeffrey Mark and Talavage, Thomas Michael and Wilbur, Ronnie B. (2014) Seeing is Worse than Believing: Reading People’s Minds Better than Computer-Vision Methods Recognize Actions. In: Computer Vision – ECCV 2014. Lecture Notes in Computer Science (8693). Springer International Publishing, pp. 612-627. ISBN 9783319106014

    [img]
    Preview
    Download (356kB) | Preview


    Share your research

    Twitter Facebook LinkedIn GooglePlus Email more...



    Add this article to your Mendeley library


    Abstract

    We had human subjects perform a one-out-of-six class action recognition task from video stimuli while undergoing functional magnetic resonance imaging (fMRI). Support-vector machines (SVMs) were trained on the recovered brain scans to classify actions observed during imaging, yielding average classification accuracy of 69.73% when tested on scans from the same subject and of 34.80% when tested on scans from different subjects. An apples-to-apples comparison was performed with all publicly available software that implements state-of-the-art action recognition on the same video corpus with the same cross-validation regimen and same partitioning into training and test sets, yielding classification accuracies between 31.25% and 52.34%. This indicates that one can read people’s minds better than state-of-the-art computer-vision methods can perform action recognition.

    Item Type: Book Section
    Additional Information: This is the preprint version of the published article, which is available at DOI: 10.1007/978-3-319-10602-1_40
    Keywords: action recognition; fMRI;
    Academic Unit: Faculty of Science and Engineering > Computer Science
    Item ID: 6547
    Identification Number: https://doi.org/10.1007/978-3-319-10602-1_40
    Depositing User: Barak Pearlmutter
    Date Deposited: 09 Nov 2015 16:42
    Publisher: Springer International Publishing
    Refereed: Yes
    URI:

    Repository Staff Only(login required)

    View Item Item control page

    Downloads

    Downloads per month over past year