CVJul 2, 2019
An Analysis of Deep Neural Networks with Attention for Action Recognition from a Neurophysiological Perspective
arXiv:1907.01273v1
Originality Synthesis-oriented
AI Analysis
This is an incremental analysis that may interest researchers in AI and neuroscience by linking computational models to brain theories.
The paper reviews three deep learning methods for action recognition and compares them from a neurophysiological perspective, suggesting analogies between these methods and hypotheses about human brain functioning.
We review three recent deep learning based methods for action recognition and present a brief comparative analysis of the methods from a neurophyisiological point of view. We posit that there are some analogy between the three presented deep learning based methods and some of the existing hypotheses regarding the functioning of human brain.