Institutional Repository of Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Weakly Semantic Guided Action Recognition | |
Tingzhao Yu1,2![]() ![]() ![]() ![]() ![]() ![]() | |
Source Publication | IEEE Transactions on Multimedia
![]() |
2019 | |
Volume | 1Issue:1Pages:1-14 |
Abstract | 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 totally 3D convolution and element-wise gated operations, thus they are efficient and easy to be implemented. 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 (named SGN, abbreviation for Semantic Guided Network) can focus on the salient parts of the video clips. Consequently, the redundant information can be reduced and the model is more robust to noises. 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 the 3rd place in ODAR 2017 challenge. |
Keyword | Semantic Guided Module Action Recognition Cross Domain 3d Convolution Attention Model |
Language | 英语 |
Document Type | 期刊论文 |
Identifier | http://ir.ia.ac.cn/handle/173211/23708 |
Collection | 模式识别国家重点实验室_先进数据分析与学习 |
Corresponding Author | Tingzhao Yu |
Affiliation | 1.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences 2.School of Computer and Control Engineering, University of Chinese Academy of Sciences |
First Author Affilication | Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China |
Corresponding Author Affilication | Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China |
Recommended Citation GB/T 7714 | Tingzhao Yu,Lingfeng Wang,Cheng Da,et al. Weakly Semantic Guided Action Recognition[J]. IEEE Transactions on Multimedia,2019,1(1):1-14. |
APA | Tingzhao Yu,Lingfeng Wang,Cheng Da,Huxiang Gu,Shiming Xiang,&Chunhong Pan.(2019).Weakly Semantic Guided Action Recognition.IEEE Transactions on Multimedia,1(1),1-14. |
MLA | Tingzhao Yu,et al."Weakly Semantic Guided Action Recognition".IEEE Transactions on Multimedia 1.1(2019):1-14. |
Files in This Item: | ||||||
File Name/Size | DocType | Version | Access | License | ||
[Tsingzao]Weakly Sem(18774KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | View Application Full Text |
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment