Abstract

We had human sub jects perform a one-out-of-six class action recognition task from video stimuli while undergoing functional mag- netic 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 sub ject and of 34.80% when tested on scans from different sub jects. An apples-to-apples comparison was performed with all publicly available software that implements state-of-the-art ac- tion recognition on the same video corpus with the same cross-validation regimen and same partitioning into training and test sets, yielding clas- sification 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.