Evaluation of Triple-Stream Convolutional Networks for Action Recognition
Evaluation of Triple-Stream Convolutional Networks for Action Recognition
复制标题
DOI：
10.1109/dicta.2017.8227428
复制
发表时间：
2017-11
期刊：
影响因子：
--
通讯作者：
Dichao Liu;Yu Wang;Jien Kato
中科院分区：
文献类型：
--
作者：
Dichao Liu;Yu Wang;Jien Kato
近年来，双流卷积网络取得了显著的性能。特别是，通过捕捉外观和运动信息，时空双流网络带来了显著的改进。另一方面，动态图像作为视频的一种强有力的表现形式，也被证实可以为空间外观提供补充信息。受这些工作的启发，我们通过融合输入为动态图像的第三个网络流，提出了三流卷积网络。在本文中，我们实现了所提出的三流卷积网络，并从两个方面对它们进行了评估：(A)如何通过添加动态流来提高端到端的整体分类性能；(B)使用训练好的三流卷积网络来进行分类是有效的。我们的评估表明，与单一网络(空间和时间)和融合时空双流网络相比，该算法都有改进。
Recently, Two-Stream Convolutional Network has achieved remarkable performance. Especially, by capturing appearance and motion information, spatial-temporal two- stream networks bring noticeable improvement. On the other hand, dynamic image, which is a powerful representation for videos, has also been confirmed to provide complimentary information to spatial appearance. Inspired by these works, we proposed Triple-Stream Convolutional Networks by fusing a third network stream whose input is dynamic image. In this paper, we implement the proposed Triple-Stream Convolutional Networks and evaluated them in two aspects: (a) how the overall end-to-end classification performance can be benefited by adding the dynamic stream; (b) which way is efficient to use the trained Triple-Stream Convolutional Networks in classification. Our evaluation shows improvements over both single networks (spatial and temporal) and Fused Spatial-temporal Two-Stream Network.