.png){kind=icon}
返回
Human action recognition based on multi-layer Fisher vector encoding method
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patrec.2015.06.029.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In this paper, we propose a new multi layer Fisher vector encoding method based on trajectory descriptors for human action recognition. The proposed method aims at improving the classical shallow Fisher vector (FV) encoding method. Our main contribution resides in considering a progressive representation of the geometric relationships among trajectories. In fact, our presentation is based on three nested layers and provides deep and discriminant structures by local spatial pooling and refining the representation from one layer to the next. To preserve more information in feature encoding process, fine and large spatio-ternporal structures have been applied. Fine structures aim at exploiting the local spatio-temporal information by building graphs of trajectories, while large structures aim at exploiting the global spatio-temporal information by spatio-temporal video subdivision. Our approach is evaluated on three popular and large human action datasets: Hollywood2, Olympic sports and HMDB51. Experiments show that more layers produce higher action classification accuracy, which proves the capability of our multi-layer Fisher vector encoding method. (C) 2015 Elsevier B.V. All rights reserved.
Keyword:
Human action recognition
Geometric relationships
Multi-layer Fisher encoding
Local pooling
Global pooling
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:
3.3
论文数:
8.0K
被引数:
1.6W
机构
引用论文
Simulation of amine concentration dependence on line edge roughness after development in electron beam lithography电子束光刻中显影后胺浓度对线边缘粗糙度的影响模拟
PREAI
分享收藏
Extending Laplacian sparse coding by the incorporation of the image spatial context.png)
NEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
分享收藏 没有更多内容
没有更多内容