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. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
Amorphous Region Context Modeling for Scene Recognition

文献类型：期刊论文

作者Zeng, Haitao1,2; Song, Xinhang1,2; Chen, Gongwei1,2; Jiang, Shuqiang1,2
刊名IEEE TRANSACTIONS ON MULTIMEDIA
出版日期2022
卷号24页码:141-151
关键词Semantics Feature extraction Image segmentation Convolution Context modeling Saliency detection Layout Graph neural network scene recognition semantic segmentation
ISSN号1520-9210
DOI10.1109/TMM.2020.3046877
英文摘要Scene images are usually composed of foreground and background regional contents. Some existing methods propose to extract regional contents with dense grids or objectness region proposals. However, dense grids may split the object into several discrete parts, learning semantic ambiguity for the patches. The objectness methods may focus on particular objects but only pay attention to the foreground contents and do not exploit the background that is key to scene recognition. In contrast, we propose a novel scene recognition framework with amorphous region detection and context modeling. In the proposed framework, discriminative regions are first detected with amorphous contours that can tightly surround the targets through semantic segmentation techniques. In addition, both foreground and background regions are jointly embedded to obtain the scene representations with the graph model. Based on the graph modeling module, we explore the contextual relations between the regions in geometric and morphology aspects, and generate the discriminative representations for scene recognition. Experimental results on MIT67 and SUN397 demonstrate the effectiveness and generality of the proposed method.
资助项目National Key Research and Development Project of New Generation Artificial Intelligence of China[2018AAA0102500] ; National Natural Science Foundation of China[61532018] ; National Natural Science Foundation of China[61902378] ; National Natural Science Foundation of China[62032022] ; National Natural Science Foundation of China[U1936203] ; Beijing Natural Science Foundation[L182054] ; Beijing Natural Science Foundation[Z190020] ; Lenovo Outstanding Young Scientists Program ; National Postdoctoral Program for Innovative Talents[BX201700255]
WOS研究方向Computer Science ; Telecommunications
语种英语
WOS记录号WOS:000745524300011
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
源URL[http://119.78.100.204/handle/2XEOYT63/18227]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Jiang, Shuqiang
作者单位1.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China
2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
推荐引用方式
GB/T 7714		 Zeng, Haitao,Song, Xinhang,Chen, Gongwei,et al. Amorphous Region Context Modeling for Scene Recognition[J]. IEEE TRANSACTIONS ON MULTIMEDIA,2022,24:141-151.
APA Zeng, Haitao,Song, Xinhang,Chen, Gongwei,&Jiang, Shuqiang.(2022).Amorphous Region Context Modeling for Scene Recognition.IEEE TRANSACTIONS ON MULTIMEDIA,24,141-151.
MLA Zeng, Haitao,et al."Amorphous Region Context Modeling for Scene Recognition".IEEE TRANSACTIONS ON MULTIMEDIA 24(2022):141-151.

入库方式： OAI收割

来源：计算技术研究所

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。