R(2+1)D

2000년 도입 · 논문 14편에서 사용

A R(2+1)D convolutional neural network is a network for action recognition that employs R(2+1)D convolutions in a ResNet inspired architecture. The use of these convolutions over regular 3D Convolutions reduces computational complexity, prevents overfitting, and introduces more non-linearities that allow for a better functional relationship to be modeled.

출처: A Closer Look at Spatiotemporal Convolutions for Action Recognition

소개 논문: A Closer Look at Spatiotemporal Convolutions for Action Recognition