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. 多模态人工智能系统全国重点实验室
  5. 遥感图像处理团队
Weakly Semantic Guided Action Recognition

文献类型：期刊论文

作者Yu, Tingzhao1,2; Wang, Lingfeng1; Da, Cheng1,2; Gu, Huxiang1; Xiang, Shiming1; Pan, Chunhong1
刊名IEEE TRANSACTIONS ON MULTIMEDIA
出版日期2019-10-01
卷号21期号:10页码:2504-2517
关键词Semantic guided module action recognition cross domain 3D convolution attention model
ISSN号1520-9210
DOI10.1109/TMM.2019.2907060
通讯作者Yu, Tingzhao(tingzhao.yu@nlpr.ia.ac.cn)
英文摘要Action recognition plays a fundamental role in computer vision and video analysis. Nevertheless, extracting effective spatial-temporal features remains a challenging task. This paper proposes three simple but effective weakly semantic guided modules (SGMs) for both environment-constrained and cross-domain action recognition. The SGMs are composed of total 3-D convolution and element-wise gated operations; thus, they are efficient and easy to implement. The semantic guidance is obtained in a weakly supervised manner, in which each video clip is labeled with only an action class instead of pixel-level semantics. Benefitting from the semantic guidance, the network [called semantic guided network (SGN)] can focus on the salient parts of the video clips. Consequently, the redundant information can be reduced and the model is more robust to noise. Besides, benefitting from the intrinsic property of SGMs, SGN is totally end-to-end trainable. Quantities of experiments on both environment-constrained (e.g., Penn, HMDB-51, and UCF-101) and cross-domain (e.g., ODAR) action recognition datasets demonstrate its effectiveness. Specifically, SGN gets improvements of 3.7%, 2.1%, and 5.2% for Penn, HMDB-51, and UCF-101 than the baseline ResNet3D, respectively, and SGN ranked third place in the ODAR 2017 challenge.
资助项目National Natural Science Foundation of China[61773377] ; National Natural Science Foundation of China[61573352] ; National Natural Science Foundation of China[91646207] ; National Natural Science Foundation of China[91438105]
WOS研究方向Computer Science ; Telecommunications
语种英语
WOS记录号WOS:000489728400007
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
资助机构National Natural Science Foundation of China
源URL[http://ir.ia.ac.cn/handle/173211/23708]  
专题自动化研究所_模式识别国家重点实验室_遥感图像处理团队
通讯作者Yu, Tingzhao
作者单位1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
2.Univ Chinese Acad Sci, Sch Comp & Control Engn, Beijing 101408, Peoples R China
推荐引用方式
GB/T 7714		 Yu, Tingzhao,Wang, Lingfeng,Da, Cheng,et al. Weakly Semantic Guided Action Recognition[J]. IEEE TRANSACTIONS ON MULTIMEDIA,2019,21(10):2504-2517.
APA Yu, Tingzhao,Wang, Lingfeng,Da, Cheng,Gu, Huxiang,Xiang, Shiming,&Pan, Chunhong.(2019).Weakly Semantic Guided Action Recognition.IEEE TRANSACTIONS ON MULTIMEDIA,21(10),2504-2517.
MLA Yu, Tingzhao,et al."Weakly Semantic Guided Action Recognition".IEEE TRANSACTIONS ON MULTIMEDIA 21.10(2019):2504-2517.

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。