Knowledge Commons of Institute of Automation,CAS
Recurrent Prediction with Spatio-temporal Attention for Crowd Attribute Recognition | |
Li, Qiaozhe![]() ![]() ![]() ![]() | |
发表期刊 | IEEE Transactions on Circuits and Systems for Video Technology
![]() |
ISSN | 1051-8215 |
2019-06 | |
卷号 | 30期号:Early Access页码:1 - 1 |
摘要 | Crowd attribute recognition is a challenging task for crowd video understanding because a crowd video often contains multiple attributes from various types. Traditional deep learning based methods directly treat this recognition problem as a multiple binary classification problem, and represent video by vectorizing and fusing the separately learned spatial and temporal features in the fully connected layers. Therefore, the correlations between these attributes may not be well captured. In this paper, a bidirectional recurrent prediction model with a semantic aware attention mechanism is proposed to explore the spatio-temporal and semantic relations between attributes for more accurate recognition. The ConvLSTM is introduced for feature representation to capture the spatio-temporal structure of crowd videos and facilitate visual attention. A bidirectional recurrent attention module is proposed for sequential attribute prediction by associating each subcategory attributes to corresponding semantic related regions iteratively. Experiments and evaluations on the challenging WWW crowd video dataset not only show that our approach significantly outperforms state-ofthe-art methods, but also verify that our approach can effectively capture the spatio-temporal and semantic relations of the crowd attributes. |
关键词 | Crowd video understanding , Attribute recognition , Attention mechanism , Multi-label classification |
DOI | 10.1109/TCSVT.2019.2923444 |
收录类别 | SCI |
语种 | 英语 |
资助项目 | National Key Research and Development Program of China[2016YFB1001005] ; National Natural Science Foundation of China[61673375] ; National Natural Science Foundation of China[61602485] ; National Natural Science Foundation of China[61721004] ; Projects of Chinese Academy of Science[QYZDBSSW-JSC006] |
项目资助者 | National Key Research and Development Program of China ; National Natural Science Foundation of China ; Projects of Chinese Academy of Science |
WOS研究方向 | Engineering |
WOS类目 | Engineering, Electrical & Electronic |
WOS记录号 | WOS:000545456800031 |
出版者 | IEEE |
七大方向——子方向分类 | 图像视频处理与分析 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/28375 |
专题 | 复杂系统认知与决策实验室_智能系统与工程 |
作者单位 | 中国科学院自动化研究所 |
第一作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Li, Qiaozhe,Zhao, Xin,He, Ran,et al. Recurrent Prediction with Spatio-temporal Attention for Crowd Attribute Recognition[J]. IEEE Transactions on Circuits and Systems for Video Technology,2019,30(Early Access):1 - 1. |
APA | Li, Qiaozhe,Zhao, Xin,He, Ran,&Huang, Kaiqi.(2019).Recurrent Prediction with Spatio-temporal Attention for Crowd Attribute Recognition.IEEE Transactions on Circuits and Systems for Video Technology,30(Early Access),1 - 1. |
MLA | Li, Qiaozhe,et al."Recurrent Prediction with Spatio-temporal Attention for Crowd Attribute Recognition".IEEE Transactions on Circuits and Systems for Video Technology 30.Early Access(2019):1 - 1. |
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 | ||
08737965.pdf(2648KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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。
修改评论