Perceptron Synthesis Network: Rethinking the Action Scale Variances in Videos. (arXiv:2007.11460v3 [cs.CV] UPDATED)

Video action recognition has been partially addressed by the CNNs stacking of
fixed-size 3D kernels. However, these methods may under-perform for only
capturing rigid spatial-temporal patterns in single-scale spaces, while
neglecting the scale variances across different action primitives. To overcome
this limitation, we propose to learn the optimal-scale kernels from the data.
More specifically, an \textit{action perceptron synthesizer} is proposed to
generate the kernels from a bag of fixed-size kernels that are interacted by
dense routing paths. To guarantee the …

arxiv cv network perceptron scale videos