.png){kind=icon}
返回
Multi-stream deep networks for human action classification with sequential tensor decomposition
.png){kind=icon}
PRE
AI
DOI：10.1016/j.sigpro.2017.05.022.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Effective spatial-temporal representation of motion information is crucial to human action classification. In spite of the attempt of most existing methods capturing spatial-temporal structure and learning motion representations with deep neural networks, such representations are failing to model action at their full temporal extent. To address this problem, this paper proposes a global motion representation by using sequential low-rank tensor decomposition. Specifically, we model an action sequence as a third-order tensor with spatiotemporal structure. Then, by using low-rank tensor decomposition, partial motion of objects in global context were preserved which will be feeding into deep architecture to automatically learning global-term motion features. To simultaneously exploit static spatial features, short-term motion and global-term motion in the video, we describe a multi-stream framework with recurrent convolutional architectures which is end-to-end trainable. Gated Recurrent Unit (GRU) is used as our recurrent unit which have fewer parameters than Long Short-Term Memory (LSTM). Extensive experiments were conducted on two challenging dataset: HMDB51 and UCF101. Experimental results show that our method achieves state-of-the-art performance on the HMDB51 dataset, and is comparable to the state-of-the-art methods on the UCF101 dataset. (C) 2017 Elsevier B.V. All rights reserved.
Keyword:
Action classification
Global motion
Tensor decomposition
Gated Recurrent Unit
Recurrent Neural network
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
3.6
论文数:
10.0K
被引数:
1.7W
机构
引用论文
分享收藏Titanium Aneurysm Clips: Part I-Mechanical, Radiological, and Biocompatibility Testing.png)
Neurosurgery
NeurosurgeryIF0
PREAI
分享收藏
分享收藏
查看更多内容