In this paper we discuss several forms of spatiotemporal convolutions for video analysis and study their effects on action recognition. Our motivation stems from the observation that 2D CNNs applied to individual frames of the video have remained solid performers in action recognition. In this work we empirically demonstrate the accuracy advantages of 3D CNNs over 2D CNNs within the framework of residual learning. Furthermore, we show that factorizing the 3D convolutional filters into separate spatial and temporal components yields significantly advantages in accuracy. Our empirical study leads to the design of a new spatiotemporal convolutional block "R(2+1)D" which gives rise to CNNs that achieve results comparable or superior to the state-of-the-art on Sports-1M, Kinetics, UCF101 and HMDB51.

本文研究了几种用于视频分析的时空卷积形式，并研究了它们对动作识别的影响。我们在残差学习的框架下，实证演示了 3D CNNs 相对于 2D CNNs 的准确性优势。此外，我们还表明把 3D 卷积滤波器分解成单独的时空分量会显著提高准确性。最终，我们设计了一个新的时空卷积块 “R(2+1)D”，这种方法产生的 CNN 的结果与最新技术相当甚至更好，可以在 Sports-1M、Kinetics、UCF101 和 HMDB51 数据集上取得更好的表现。

动作识别中空间-时间卷积的近距离观察