Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?

• Published in: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition pp. 6546 - 6555
• Main Authors: Hara, Kensho, Kataoka, Hirokatsu, Satoh, Yutaka
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2018
• Subjects: Computer vision; Kernel; Kinetic theory; Task analysis; Three-dimensional displays; Training; Two dimensional displays

The purpose of this study is to determine whether current video datasets have sufficient data for training very deep convolutional neural networks (CNNs) with spatio-temporal three-dimensional (3D) kernels. Recently, the performance levels of 3D CNNs in the field of action recognition have improved...