ML Anthology

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

Andrei Barbu, Daniel Paul Barrett, Wei Chen, Siddharth Narayanaswamy, 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
ECCV 2014 pp. 612-627
doi:10.1007/978-3-319-10602-1_40 /eccv/2014/barbu2014eccv-seeing/

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.

PDF ECCV Semantic Scholar

Cite

Text

Barbu et al. "Seeing Is Worse than Believing: Reading People's Minds Better than Computer-Vision Methods Recognize Actions." European Conference on Computer Vision, 2014. doi:10.1007/978-3-319-10602-1_40

Markdown

[Barbu et al. "Seeing Is Worse than Believing: Reading People's Minds Better than Computer-Vision Methods Recognize Actions." European Conference on Computer Vision, 2014.](https://mlanthology.org/eccv/2014/barbu2014eccv-seeing/) doi:10.1007/978-3-319-10602-1_40

BibTeX

@inproceedings{barbu2014eccv-seeing,
  title     = {{Seeing Is Worse than Believing: Reading People's Minds Better than Computer-Vision Methods Recognize Actions}},
  author    = {Barbu, Andrei and Barrett, Daniel Paul and Chen, Wei and Narayanaswamy, Siddharth and Xiong, Caiming and Corso, Jason J. and Fellbaum, Christiane D. and Hanson, Catherine and Hanson, Stephen José and Hélie, Sébastien and Malaia, Evguenia and Pearlmutter, Barak A. and Siskind, Jeffrey Mark and Talavage, Thomas Michael and Wilbur, Ronnie B.},
  booktitle = {European Conference on Computer Vision},
  year      = {2014},
  pages     = {612-627},
  doi       = {10.1007/978-3-319-10602-1_40},
  url       = {https://mlanthology.org/eccv/2014/barbu2014eccv-seeing/}
}