Automatic Scene Recognition Based on Constructed Knowledge Space Learning

doi:10.1109/ACCESS.2019.2919342

	Automatic Scene Recognition Based on Constructed Knowledge Space Learning
	Shao, Xi 1,2; Zhang, Jin 3; Bao, Bing-Kun 1; Xia, Yang 4
刊名	IEEE ACCESS
	2019
卷号	7 页码:102902-102910
关键词	Scene classification sub-graph mining bi-enhanced learning
ISSN号	2169-3536
DOI	10.1109/ACCESS.2019.2919342
通讯作者	Xia, Yang(yxia@cumt.edu)
英文摘要	An automatic visual scene recognition has attracted increasing attention for developing multimedia systems as it provides rich information beyond object recognition and action recognition. Each scene image often contains or is characterized by a certain of same essential objects and relations, for example, scene images of "wedding'' usually have bridegroom and bride next to him. Theoretically, this kind of scene knowledge can be properly modeled by some essential objects in the scene image and with their relations for each scene class. Inspired by the observation, we proposed a novel approach to improve the accuracy of scene recognition by mining essential scene sub-graph and learning a bi-enhanced knowledge space. The essential scene sub-graph describes the essential objects and their relations for each scene class. The learned knowledge space is bi-enhanced by global representation on the entire image and local representation on the corresponding essential scene sub-graph. The experiment results in the widely used scene classification dataset Scene30 and Scene15 demonstrate the effectiveness of the proposed approach with improvements in scene recognition accuracy compared with the state-of-the-art techniques.
资助项目	National Nature Science Foundation of China[61872199] ; National Nature Science Foundation of China[61872424] ; National Nature Science Foundation of China[61772287] ; Key University Science Research Project of Jiangsu Province[18KJA510004] ; Nanjing University of Posts and Telecommunications Support Funding[NY218001]
WOS关键词	REPRESENTATION ; TUTORIAL
WOS研究方向	Computer Science ; Engineering ; Telecommunications
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000481688500202
资助机构	National Nature Science Foundation of China ; Key University Science Research Project of Jiangsu Province ; Nanjing University of Posts and Telecommunications Support Funding
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/27600]
专题	中国科学院自动化研究所
通讯作者	Xia, Yang
作者单位	1.Nanjing Univ Posts & Telecommun, Coll Commun & Informat Engn, Nanjing 210003, Jiangsu, Peoples R China 2.Chinese Acad Sci, Natl Lab Pattern Recognit, Inst Automat, Beijing 100190, Peoples R China 3.Hefei Univ Technol, Sch Comp Sci & Informat Engn, Hefei 230009, Anhui, Peoples R China 4.China Univ Min & Technol, Coll Comp Sci & Technol, Xuzhou 221116, Jiangsu, Peoples R China
推荐引用方式 GB/T 7714	Shao, Xi,Zhang, Jin,Bao, Bing-Kun,et al. Automatic Scene Recognition Based on Constructed Knowledge Space Learning[J]. IEEE ACCESS,2019,7:102902-102910.
APA	Shao, Xi,Zhang, Jin,Bao, Bing-Kun,&Xia, Yang.(2019).Automatic Scene Recognition Based on Constructed Knowledge Space Learning.IEEE ACCESS,7,102902-102910.
MLA	Shao, Xi,et al."Automatic Scene Recognition Based on Constructed Knowledge Space Learning".IEEE ACCESS 7(2019):102902-102910.