Body Joint Guided 3-D Deep Convolutional Descriptors for Action Recognition
Cao, Congqi1,2; Zhang, Yifan1,2; Zhang, Chunjie2,3; Lu, Hanqing1,2
2018-03-01
发表期刊IEEE TRANSACTIONS ON CYBERNETICS
卷号48期号:3页码:1095-1108
文章类型Article
摘要3-D convolutional neural networks (3-D CNNs) have been established as a powerful tool to simultaneously learn features from both spatial and temporal dimensions, which is suitable to be applied to video-based action recognition. In this paper, we propose not to directly use the activations of fully connected layers of a 3-D CNN as the video feature, but to use selective convolutional layer activations to form a discriminative descriptor for video. It pools the feature on the convolutional layers under the guidance of body joint positions. Two schemes of mapping body joints into convolutional feature maps for pooling are discussed. The body joint positions can be obtained from any off-the-shelf skeleton estimation algorithm. The helpfulness of the body joint guided feature pooling with inaccurate skeleton estimation is systematically evaluated. To make it end-to-end and do not rely on any sophisticated body joint detection algorithm, we further propose a two-stream bilinear model which can learn the guidance from the body joints and capture the spatio-temporal features simultaneously. In this model, the body joint guided feature pooling is conveniently formulated as a bilinear product operation. Experimental results on three real-world datasets demonstrate the effectiveness of body joint guided pooling which achieves promising performance.
关键词Action Recognition Body Joints Convolutional Networks Feature Pooling Two-stream Bilinear Model
WOS标题词Science & Technology ; Technology
DOI10.1109/TCYB.2017.2756840
关键词[WOS]CLASSIFICATION ; TRAJECTORIES ; HISTOGRAMS ; PARTS
收录类别SCI
语种英语
项目资助者National Natural Science Foundation of China(61332016 ; Youth Innovation Promotion Association CAS ; 61572500)
WOS研究方向Automation & Control Systems ; Computer Science
WOS类目Automation & Control Systems ; Computer Science, Artificial Intelligence ; Computer Science, Cybernetics
WOS记录号WOS:000424826800022
引用统计
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/20410
专题模式识别国家重点实验室_图像与视频分析
作者单位1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
2.Univ Chinese Acad Sci, Beijing 100190, Peoples R China
3.Chinese Acad Sci, Inst Automat, Res Ctr Brain Inspired Intelligence, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714
Cao, Congqi,Zhang, Yifan,Zhang, Chunjie,et al. Body Joint Guided 3-D Deep Convolutional Descriptors for Action Recognition[J]. IEEE TRANSACTIONS ON CYBERNETICS,2018,48(3):1095-1108.
APA Cao, Congqi,Zhang, Yifan,Zhang, Chunjie,&Lu, Hanqing.(2018).Body Joint Guided 3-D Deep Convolutional Descriptors for Action Recognition.IEEE TRANSACTIONS ON CYBERNETICS,48(3),1095-1108.
MLA Cao, Congqi,et al."Body Joint Guided 3-D Deep Convolutional Descriptors for Action Recognition".IEEE TRANSACTIONS ON CYBERNETICS 48.3(2018):1095-1108.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
曹聪琦_T-Cybernetics_Bo(1731KB)期刊论文作者接受稿开放获取CC BY-NC-SA浏览 下载
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
[Cao, Congqi]的文章
[Zhang, Yifan]的文章
[Zhang, Chunjie]的文章
百度学术
百度学术中相似的文章
[Cao, Congqi]的文章
[Zhang, Yifan]的文章
[Zhang, Chunjie]的文章
必应学术
必应学术中相似的文章
[Cao, Congqi]的文章
[Zhang, Yifan]的文章
[Zhang, Chunjie]的文章
相关权益政策
暂无数据
收藏/分享
文件名: 曹聪琦_T-Cybernetics_Body Joint guided 3D Deep Convolutional Descriptors for Action Recognition.pdf
格式: Adobe PDF
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。