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. 紫东太初大模型研究中心
  5. 图像与视频分析团队
Semantic-spatial fusion network for human parsing

文献类型：期刊论文

作者Zhang, Xiaomei1,2; Chen, Yingying1,2; Zhu, Bingke1,2; Wang, Jinqiao1,2; Tang, Ming1,2
刊名NEUROCOMPUTING
出版日期2020-08-18
卷号402页码:375-383
关键词SSFNet Semantic modulation model Resolution-aware model Human parsing
ISSN号0925-2312
DOI10.1016/j.neucom.2020.03.096
通讯作者Chen, Yingying(yingying.chen@nlpr.ia.ac.cn)
英文摘要Recently, 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.
WOS关键词SEGMENTATION ; MODELS
资助项目National Natural Science Foundation of China[61976210] ; National Natural Science Foundation of China[61772527]
WOS研究方向Computer Science
语种英语
WOS记录号WOS:000538815500005
出版者ELSEVIER
资助机构National Natural Science Foundation of China
源URL[http://ir.ia.ac.cn/handle/173211/39810]  
专题自动化研究所_模式识别国家重点实验室_图像与视频分析团队
通讯作者Chen, Yingying
作者单位1.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
推荐引用方式
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.

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。