Amorphous Region Context Modeling for Scene Recognition

doi:10.1109/TMM.2020.3046877

	Amorphous Region Context Modeling for Scene Recognition
	Zeng, Haitao 1,2; Song, Xinhang 1,2; Chen, Gongwei 1,2; Jiang, Shuqiang 1,2
	2022
发表期刊	IEEE TRANSACTIONS ON MULTIMEDIA
ISSN	1520-9210
卷号	24 页码:141-151
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.
关键词	Semantics Feature extraction Image segmentation Convolution Context modeling Saliency detection Layout Graph neural network scene recognition semantic segmentation
DOI	10.1109/TMM.2020.3046877
收录类别	SCI
语种	英语
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
WOS类目	Computer Science, Information Systems ; Computer Science, Software Engineering ; Telecommunications
WOS记录号	WOS:000745524300011
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：6[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/18228
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.