Time-Asymmetric 3d Convolutional Neural Networks For Action Recognition

Three-dimensional (3D) convolutional neural network (CNN) is widely used for action recognition. However, it performs same on time and space, which dose not match asymmetry of time. To overcome this problem, we propose the time-asymmetric 3D CNN based on the hypothesis that the early frames persist. Our time-asymmetric 3D CNN performs better on Kinetics-400 than normal 3D CNN with less parameters. And it can get comparable results on UCF101 among leading methods, which indicates that our time-asymmetric 3D CNN is a good choice for action recognition.