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

Andrei Barbu, Daniel P. Barrett, Wei Chen, Narayanaswamy Siddharth, Caiming Xiong, Jason J. Corso, Christiane D. Fellbaum, Catherine Hanson, Stephen José Hanson, Sébastien Hélie, Evguenia Malaia, Barak A. Pearlmutter, Jeffrey Mark Siskind, Thomas Michael Talavage, Ronnie B. Wilbur

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

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.
Original languageEnglish
Title of host publicationComputer Vision -- ECCV 2014
Subtitle of host publicationPart V
EditorsDavid Fleet, Tomas Pajdla, Bernt Schiele, Tinne Tuytelaars
Place of PublicationCham
PublisherSpringer
Pages612-627
Number of pages16
ISBN (Electronic)978-3-319-10602-1
ISBN (Print)978-3-319-10601-4
DOIs
Publication statusPublished - 12 Sept 2014
EventEuropean Conference on Computer Vision 2014 - Zurich, Switzerland
Duration: 5 Sept 201412 Sept 2014

Publication series

Name Lecture Notes in Computer Science
PublisherSpringer, Cham
Volume8693
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

ConferenceEuropean Conference on Computer Vision 2014
Abbreviated titleECCV 2014
Country/TerritorySwitzerland
CityZurich
Period5/09/1412/09/14

Keywords / Materials (for Non-textual outputs)

  • action recognition
  • fMRI

Fingerprint

Dive into the research topics of 'Seeing is Worse than Believing: Reading People's Minds Better than Computer-Vision Methods Recognize Actions'. Together they form a unique fingerprint.

Cite this