中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 紫东太初大模型研究中心
  5. 图像与视频分析团队
Body Joint Guided 3-D Deep Convolutional Descriptors for Action Recognition

文献类型：期刊论文

作者Cao, Congqi1,2; Zhang, Yifan1,2; Zhang, Chunjie2,3; Lu, Hanqing1,2
刊名IEEE TRANSACTIONS ON CYBERNETICS
出版日期2018-03-01
卷号48期号:3页码:1095-1108
关键词Action Recognition Body Joints Convolutional Networks Feature Pooling Two-stream Bilinear Model
DOI10.1109/TCYB.2017.2756840
文献子类Article
英文摘要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.
WOS关键词CLASSIFICATION ; TRAJECTORIES ; HISTOGRAMS ; PARTS
WOS研究方向Automation & Control Systems ; Computer Science
语种英语
WOS记录号WOS:000424826800022
资助机构National Natural Science Foundation of China(61332016 ; Youth Innovation Promotion Association CAS ; 61572500)
源URL[http://ir.ia.ac.cn/handle/173211/20410]  
专题自动化研究所_模式识别国家重点实验室_图像与视频分析团队
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.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

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。