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

TitleSeeing is Worse than Believing: Reading People’s Minds Better than Computer-Vision Methods Recognize Actions
Publication TypeCBMM Memos
Year of Publication2014
AuthorsBarbu, A, Barrett, D, Chen, W, Siddharth, N, Xiong, C, Corso, JJ, Fellbaum, CD, Hanson, C, Hanson, SJosé, Helie, S, Malaia, E, Pearlmutter, BA, Siskind, JMark, Talavage, TMichael, Wilbur, RB
Number012
Date Published09/2014
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.

DSpace@MIT

http://hdl.handle.net/1721.1/100176

Download:  PDF icon CBMM Memo 012.pdf CBMM Memo No:  012

Research Area: 

CBMM Relationship: 

  • CBMM Funded