CASIA OpenIR
Semantic-spatial fusion network for human parsing
Zhang, Xiaomei1,2; Chen, Yingying1,2; Zhu, Bingke1,2; Wang, Jinqiao1,2; Tang, Ming1,2
Source PublicationNEUROCOMPUTING
ISSN0925-2312
2020-08-18
Volume402Pages:375-383
Corresponding AuthorChen, Yingying(yingying.chen@nlpr.ia.ac.cn)
AbstractRecently, many methods have united low-level and high-level features to generate the desired accurate high-resolution prediction for human parsing. Nevertheless, there exists a semantic-spatial gap between low-level and high-level features in some methods, i.e., high-level features represent more semantics and less spatial details, while low-level ones have less semantics and more spatial details. In this paper, we propose a Semantic-Spatial Fusion Network (SSFNet) for human parsing to shrink the gap, which generates the accurate high-resolution prediction by aggregating multi-resolution features. SSFNet includes two models, a semantic modulation model and a resolution-aware model. The semantic modulation model guides spatial details with semantics and then effectively facilitates the feature fusion, narrowing the gap. The resolution-aware model sufficiently boosts the feature fusion and obtains multi-receptive-fields, which generates reliable and fine-grained high-resolution features for each branch, in bottom-up and top-down processes. Extensive experiments on three public datasets, PASCAL-Person-Part, LIP and PPSS, show that SSFNet achieves significant improvements over state-of-the-art methods. (C) 2020 Elsevier B.V. All rights reserved.
KeywordSSFNet Semantic modulation model Resolution-aware model Human parsing
DOI10.1016/j.neucom.2020.03.096
WOS KeywordSEGMENTATION ; MODELS
Indexed BySCI
Language英语
Funding ProjectNational Natural Science Foundation of China[61976210] ; National Natural Science Foundation of China[61772527]
Funding OrganizationNational Natural Science Foundation of China
WOS Research AreaComputer Science
WOS SubjectComputer Science, Artificial Intelligence
WOS IDWOS:000538815500005
PublisherELSEVIER
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/39811
Collection中国科学院自动化研究所
Corresponding AuthorChen, Yingying
Affiliation1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, 95 Zhongguancun East Rd, Beijing 100190, Peoples R China
2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
First Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Corresponding Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Zhang, Xiaomei,Chen, Yingying,Zhu, Bingke,et al. Semantic-spatial fusion network for human parsing[J]. NEUROCOMPUTING,2020,402:375-383.
APA Zhang, Xiaomei,Chen, Yingying,Zhu, Bingke,Wang, Jinqiao,&Tang, Ming.(2020).Semantic-spatial fusion network for human parsing.NEUROCOMPUTING,402,375-383.
MLA Zhang, Xiaomei,et al."Semantic-spatial fusion network for human parsing".NEUROCOMPUTING 402(2020):375-383.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Zhang, Xiaomei]'s Articles
[Chen, Yingying]'s Articles
[Zhu, Bingke]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhang, Xiaomei]'s Articles
[Chen, Yingying]'s Articles
[Zhu, Bingke]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhang, Xiaomei]'s Articles
[Chen, Yingying]'s Articles
[Zhu, Bingke]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.