Representation Flow for Action Recognition

CVPR 2019 AJ PiergiovanniMichael S. Ryoo

In this paper, we propose a convolutional layer inspired by optical flow algorithms to learn motion representations. Our representation flow layer is a fully-differentiable layer designed to capture the `flow' of any representation channel within a convolutional neural network for action recognition... (read more)

PDF Abstract

Evaluation results from the paper

#2 best model for Action Classification on HMDB51 (using extra training data)

     Get a GitHub badge
Task Dataset Model Metric name Metric value Global rank Uses extra
training data
Action Classification HMDB51 RepFlow-50 Accuracy 81.1 # 2
Action Classification Kinetics-400 RepFlow-50 Accuracy 77.9 # 4