Explore human parsing modality for action recognition

IF 8.4 2区 计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE
Jinfu Liu, Runwei Ding, Yuhang Wen, Nan Dai, Fanyang Meng, Fang-Lue Zhang, Shen Zhao, Mengyuan Liu
{"title":"Explore human parsing modality for action recognition","authors":"Jinfu Liu,&nbsp;Runwei Ding,&nbsp;Yuhang Wen,&nbsp;Nan Dai,&nbsp;Fanyang Meng,&nbsp;Fang-Lue Zhang,&nbsp;Shen Zhao,&nbsp;Mengyuan Liu","doi":"10.1049/cit2.12366","DOIUrl":null,"url":null,"abstract":"<p>Multimodal-based action recognition methods have achieved high success using pose and RGB modality. However, skeletons sequences lack appearance depiction and RGB images suffer irrelevant noise due to modality limitations. To address this, the authors introduce human parsing feature map as a novel modality, since it can selectively retain effective semantic features of the body parts while filtering out most irrelevant noise. The authors propose a new dual-branch framework called ensemble human parsing and pose network (EPP-Net), which is the first to leverage both skeletons and human parsing modalities for action recognition. The first human pose branch feeds robust skeletons in the graph convolutional network to model pose features, while the second human parsing branch also leverages depictive parsing feature maps to model parsing features via convolutional backbones. The two high-level features will be effectively combined through a late fusion strategy for better action recognition. Extensive experiments on NTU RGB + D and NTU RGB + D 120 benchmarks consistently verify the effectiveness of our proposed EPP-Net, which outperforms the existing action recognition methods. Our code is available at https://github.com/liujf69/EPP-Net-Action.</p>","PeriodicalId":46211,"journal":{"name":"CAAI Transactions on Intelligence Technology","volume":"9 6","pages":"1623-1633"},"PeriodicalIF":8.4000,"publicationDate":"2024-08-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/cit2.12366","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"CAAI Transactions on Intelligence Technology","FirstCategoryId":"94","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1049/cit2.12366","RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

Abstract

Multimodal-based action recognition methods have achieved high success using pose and RGB modality. However, skeletons sequences lack appearance depiction and RGB images suffer irrelevant noise due to modality limitations. To address this, the authors introduce human parsing feature map as a novel modality, since it can selectively retain effective semantic features of the body parts while filtering out most irrelevant noise. The authors propose a new dual-branch framework called ensemble human parsing and pose network (EPP-Net), which is the first to leverage both skeletons and human parsing modalities for action recognition. The first human pose branch feeds robust skeletons in the graph convolutional network to model pose features, while the second human parsing branch also leverages depictive parsing feature maps to model parsing features via convolutional backbones. The two high-level features will be effectively combined through a late fusion strategy for better action recognition. Extensive experiments on NTU RGB + D and NTU RGB + D 120 benchmarks consistently verify the effectiveness of our proposed EPP-Net, which outperforms the existing action recognition methods. Our code is available at https://github.com/liujf69/EPP-Net-Action.

Abstract Image

求助全文
约1分钟内获得全文 求助全文
来源期刊
CAAI Transactions on Intelligence Technology
CAAI Transactions on Intelligence Technology COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE-
CiteScore
11.00
自引率
3.90%
发文量
134
审稿时长
35 weeks
期刊介绍: CAAI Transactions on Intelligence Technology is a leading venue for original research on the theoretical and experimental aspects of artificial intelligence technology. We are a fully open access journal co-published by the Institution of Engineering and Technology (IET) and the Chinese Association for Artificial Intelligence (CAAI) providing research which is openly accessible to read and share worldwide.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信