Weakly Semantic Guided Action Recognition
Yu, Tingzhao1,2; Wang, Lingfeng1; Da, Cheng1,2; Gu, Huxiang1; Xiang, Shiming1; Pan, Chunhong1
发表期刊IEEE TRANSACTIONS ON MULTIMEDIA
ISSN1520-9210
2019-10-01
卷号21期号:10页码:2504-2517
通讯作者Yu, Tingzhao(tingzhao.yu@nlpr.ia.ac.cn)
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.
关键词Semantic guided module action recognition cross domain 3D convolution attention model
DOI10.1109/TMM.2019.2907060
收录类别SCI
语种英语
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] ; 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]
项目资助者National Natural Science Foundation of China
WOS研究方向Computer Science ; Telecommunications
WOS类目Computer Science, Information Systems ; Computer Science, Software Engineering ; Telecommunications
WOS记录号WOS:000489728400007
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
七大方向——子方向分类目标检测、跟踪与识别
引用统计
被引频次:22[WOS]   [WOS记录]     [WOS相关记录]
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/23708
专题模式识别国家重点实验室_先进时空数据分析与学习
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
第一作者单位模式识别国家重点实验室
通讯作者单位模式识别国家重点实验室
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.
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
[Tsingzao]Weakly Sem(18774KB)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
[Yu, Tingzhao]的文章
[Wang, Lingfeng]的文章
[Da, Cheng]的文章
百度学术
百度学术中相似的文章
[Yu, Tingzhao]的文章
[Wang, Lingfeng]的文章
[Da, Cheng]的文章
必应学术
必应学术中相似的文章
[Yu, Tingzhao]的文章
[Wang, Lingfeng]的文章
[Da, Cheng]的文章
相关权益政策
暂无数据
收藏/分享
文件名: [Tsingzao]Weakly Semantic Guided Action Recognition.pdf
格式: Adobe PDF
此文件暂不支持浏览
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。