Category co-occurrence modeling for large scale scene recognition

doi:10.1016/j.patcog.2016.01.019

	Category co-occurrence modeling for large scale scene recognition
	Song, Xinhang 1; Jiang, Shuqiang 1; Herranz, Luis 1; Kong, Yan 2; Zheng, Kai 3
	2016-11-01
发表期刊	PATTERN RECOGNITION
ISSN	0031-3203
卷号	59 页码:98-111
摘要	Scene recognition involves complex reasoning from low-level local features to high-level scene categories. The large semantic gap motivates that most methods model scenes resorting to mid-level representations (e.g. objects, topics). However, this implies an additional mid-level vocabulary and has implications in training and inference. In contrast, the semantic multinomial (SMN) represents patches directly in the scene-level semantic space, which leads to ambiguity when aggregated to a global image representation. Fortunately, this ambiguity appears in the form of scene category co-occurrences which can be modeled a posteriori with a classifier. In this paper we observe that these patterns are essentially local rather than global, sparse, and consistent across SMNs obtained from multiple visual features. We propose a co-occurrence modeling framework where we exploit all these patterns jointly in a common semantic space, combining both supervised and unsupervised learning. Based on this framework we can integrate multiple features and design embeddings for large scale recognition directly in the scene-level space. Finally, we use the co-occurrence modeling framework to develop new scene representations, which experiments show that outperform previous SMN-based representations. (C) 2016 Elsevier Ltd. All rights reserved.
关键词	Scene recognition Co-occurrence modeling Semantic space Feature embedding Multiple feature combination Large scale image recognition
DOI	10.1016/j.patcog.2016.01.019
收录类别	SCI
语种	英语
资助项目	National Basic Research 973 Program of China[2012CB316400] ; National Natural Science Foundation of China[61532018] ; National Natural Science Foundation of China[61322212] ; National Natural Science Foundation of China[61550110505] ; National High Technology Research and Development 863 Program of China[2014AA015202] ; Lenovo Outstanding Young Scientists Program (LOYS) ; CAS President's International Fellowship Initiative[2011Y1GB05]
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000383007800010
出版者	ELSEVIER SCI LTD
引用统计	被引频次：17[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/2XEOYT63/8157
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, Beijing, Peoples R China 2.Chinese Acad Sci, Inst Automat, Beijing, Peoples R China 3.Soochow Univ, Sch Comp Sci, Suzhou, Jiangsu, Peoples R China
推荐引用方式 GB/T 7714	Song, Xinhang,Jiang, Shuqiang,Herranz, Luis,et al. Category co-occurrence modeling for large scale scene recognition[J]. PATTERN RECOGNITION,2016,59:98-111.
APA	Song, Xinhang,Jiang, Shuqiang,Herranz, Luis,Kong, Yan,&Zheng, Kai.(2016).Category co-occurrence modeling for large scale scene recognition.PATTERN RECOGNITION,59,98-111.
MLA	Song, Xinhang,et al."Category co-occurrence modeling for large scale scene recognition".PATTERN RECOGNITION 59(2016):98-111.