CASIA OpenIR  > 视频内容安全团队
Asymmetric 3D Convolutional Neural Networks for action recognition
Yang, Hao1,3; Yuan, Chunfeng1; Li, Bing1; Du, Yang1,3; Xing, Junliang1; Hu, Weiming1,2,3; Maybank, Stephen J.4
发表期刊PATTERN RECOGNITION
ISSN0031-3203
2019
卷号85页码:1-12
通讯作者Yuan, Chunfeng(cfyuan@nlpr.ia.ac.cn)
摘要Convolutional Neural Network based action recognition methods have achieved significant improvements in recent years. The 3D convolution extends the 2D convolution to the spatial-temporal domain for better analysis of human activities in videos. The 3D convolution, however, involves many more parameters than the 2D convolution. Thus, it is much more expensive on computation, costly on storage, and difficult to learn. This work proposes efficient asymmetric one-directional 3D convolutions to approximate the traditional 3D convolution. To improve the feature learning capacity of asymmetric 3D convolutions, a set of local 3D convolutional networks, called MicroNets, are proposed by incorporating multi-scale 3D convolution branches. Then, an asymmetric 3D-CNN deep model is constructed by MicroNets for the action recognition task. Moreover, to avoid training two networks on the RGB and Flow frames separately as most works do, a simple but effective multi-source enhanced input is proposed, which fuses useful information of the RGB and Flow frame at the pre-processing stage. The asymmetric 3D-CNN model is evaluated on two of the most challenging action recognition benchmarks, UCF-101 and HMDB-51. The asymmetric 3D-CNN model outperforms all the traditional 3D-CNN models in both effectiveness and efficiency, and its performance is comparable with that of recent state-of-the-art action recognition methods on both benchmarks. (C) 2018 Elsevier Ltd. All rights reserved.
关键词Asymmetric 3D convolution MicroNets 3D-CNN Action recognition
DOI10.1016/j.patcog.2018.07.028
关键词[WOS]SHORT-TERM-MEMORY ; FEATURES ; VIDEOS ; TIME ; FLOW
收录类别SCI
语种英语
WOS研究方向Computer Science ; Engineering
WOS类目Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号WOS:000447819300001
出版者ELSEVIER SCI LTD
引用统计
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/22816
专题视频内容安全团队
通讯作者Yuan, Chunfeng
作者单位1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
2.Chinese Acad Sci, CAS Ctr Excellence Brain Sci & Intelligence Techn, Beijing 100190, Peoples R China
3.Univ Chinese Acad Sci, Beijing 100190, Peoples R China
4.Birkbeck Coll, Dept Comp Sci & Informat Syst, London WC1E 7HX, England
推荐引用方式
GB/T 7714
Yang, Hao,Yuan, Chunfeng,Li, Bing,et al. Asymmetric 3D Convolutional Neural Networks for action recognition[J]. PATTERN RECOGNITION,2019,85:1-12.
APA Yang, Hao.,Yuan, Chunfeng.,Li, Bing.,Du, Yang.,Xing, Junliang.,...&Maybank, Stephen J..(2019).Asymmetric 3D Convolutional Neural Networks for action recognition.PATTERN RECOGNITION,85,1-12.
MLA Yang, Hao,et al."Asymmetric 3D Convolutional Neural Networks for action recognition".PATTERN RECOGNITION 85(2019):1-12.
条目包含的文件
条目无相关文件。
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Yang, Hao]的文章
[Yuan, Chunfeng]的文章
[Li, Bing]的文章
百度学术
百度学术中相似的文章
[Yang, Hao]的文章
[Yuan, Chunfeng]的文章
[Li, Bing]的文章
必应学术
必应学术中相似的文章
[Yang, Hao]的文章
[Yuan, Chunfeng]的文章
[Li, Bing]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。