Kinematic skeleton graph augmented network for human parsing
文献类型：期刊论文
| 作者 | Liu, Jinde1,3; Zhang, Zhang1,3 ; Shan, Caifeng2,4; Tan, Tieniu1,3
|
| 刊名 | NEUROCOMPUTING
 |
| 出版日期 | 2020-11-06 |
| 卷号 | 413页码:457-470 |
| 关键词 | Image segmentation Human parsing Deeplab V3+ Kinematic skeleton graph Human parsing dataset |
| ISSN号 | 0925-2312 |
| DOI | 10.1016/j.neucom.2020.07.002 |
| 通讯作者 | Zhang, Zhang(zzhang@nlpr.ia.ac.cn) |
| 英文摘要 | Human parsing, which is a task of labeling pixels in human images into different fine-grained semantic parts, has achieved significant progress during the past decade. However, there are still several challenges in human parsing, due to occlusions, varying poses and similar appearance between the left/right parts. To tackle these problems, a Human Kinematic Skeleton Graph Layer (HKSGL) is proposed to augment regular neural networks with human kinematic skeleton information. The HKSGL has two major components: kinematic skeleton graph and interconnected modular neural layer. The kinematic skeleton graph is a user pre-defined skeleton graph, which models the interconnections between different semantic parts. Then the skeleton graph is passed to the interconnected modular neural layer which is composed of a set of modular blocks corresponding to different semantic parts. The HKSGL is a lightweight, low costs layer which can be easily attached to any existing neural networks. To demonstrate the power of the HKSGL, a new dataset on human parsing in occlusions is also collected, termed the RAP-Occ. Extensive experiments have been performed on four datasets on human parsing, including the LIP, the CIHP, the ATR and the RAP-Occ. And two popular baselines, i.e., the Deeplab V3+ and the CE2P, are agumented by the proposed HKSGL. Competitive performance of the augmented models has been achieved in comparison with state-of-the-art methods. (C) 2020 Elsevier B.V. All rights reserved. |
| WOS关键词 | SEGMENTATION |
| 资助项目 | National Key Research and Development Program of China[2016YFB1001002] ; Shandong Provincial Key Research and Development Program (Major Scientific and Technological Innovation Project)[2019JZZY010119] |
| WOS研究方向 | Computer Science |
| 语种 | 英语 |
| WOS记录号 | WOS:000579803700037 |
| 出版者 | ELSEVIER |
| 资助机构 | National Key Research and Development Program of China ; Shandong Provincial Key Research and Development Program (Major Scientific and Technological Innovation Project) |
| 源URL | [http://ir.ia.ac.cn/handle/173211/42125]  |
| 专题 | 自动化研究所_智能感知与计算研究中心 |
| 通讯作者 | Zhang, Zhang |
| 作者单位 | 1.Chinese Acad Sci, Ctr Res Intelligent Percept & Comp, Inst Automat, Beijing, Peoples R China 2.Shandong Univ Sci & Technol, Coll Elect Engn & Automat, Qingdao, Peoples R China 3.Univ Chinese Acad Sci, Beijing, Peoples R China 4.CAS CAS AIR, Artificial Intelligence Res, Beijing, Peoples R China |
| 推荐引用方式 GB/T 7714 | Liu, Jinde,Zhang, Zhang,Shan, Caifeng,et al. Kinematic skeleton graph augmented network for human parsing[J]. NEUROCOMPUTING,2020,413:457-470. |
| APA | Liu, Jinde,Zhang, Zhang,Shan, Caifeng,&Tan, Tieniu.(2020).Kinematic skeleton graph augmented network for human parsing.NEUROCOMPUTING,413,457-470. |
| MLA | Liu, Jinde,et al."Kinematic skeleton graph augmented network for human parsing".NEUROCOMPUTING 413(2020):457-470. |
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。