Multi-Scale Multi-Feature Context Modeling for Scene Recognition in the Semantic Manifold

doi:10.1109/TIP.2017.2686017

CORC > 计算技术研究所 > 中国科学院计算技术研究所 > 中国科学院计算技术研究所期刊论文 > 英文

	Multi-Scale Multi-Feature Context Modeling for Scene Recognition in the Semantic Manifold
	Song, Xinhang 1,2; Jiang, Shuqiang 1,2; Herranz, Luis 1
刊名	IEEE TRANSACTIONS ON IMAGE PROCESSING
	2017-06-01
卷号	26 期号:6 页码:2721-2735
关键词	Scene recognition semantic manifold semantic multinomial multi-scale context model Markov random field convolutional neural networks
ISSN号	1057-7149
DOI	10.1109/TIP.2017.2686017
英文摘要	Before the big data era, scene recognition was often approached with two-step inference using localized intermediate representations (objects, topics, and so on). One of such approaches is the semantic manifold (SM), in which patches and images are modeled as points in a semantic probability simplex. Patch models are learned resorting to weak supervision via image labels, which leads to the problem of scene categories co-occurring in this semantic space. Fortunately, each category has its own co-occurrence patterns that are consistent across the images in that category. Thus, discovering and modeling these patterns are critical to improve the recognition performance in this representation. Since the emergence of large data sets, such as ImageNet and Places, these approaches have been relegated in favor of the much more powerful convolutional neural networks (CNNs), which can automatically learn multilayered representations from the data. In this paper, we address many limitations of the original SM approach and related works. We propose discriminative patch representations using neural networks and further propose a hybrid architecture in which the semantic manifold is built on top of multiscale CNNs. Both representations can be computed significantly faster than the Gaussian mixture models of the original SM. To combine multiple scales, spatial relations, and multiple features, we formulate rich context models using Markov random fields. To solve the optimization problem, we analyze global and local approaches, where a top-down hierarchical algorithm has the best performance. Experimental results show that exploiting different types of contextual relations jointly consistently improves the recognition accuracy.
资助项目	National Natural Science Foundation of China[61532018] ; National Natural Science Foundation of China[61322212] ; Beijing Municipal Commission of Science and Technology[D161100001816001] ; Lenovo Outstanding Young Scientists Program ; National Program for Special Support of Eminent Professionals ; National Program for Support of Top-notch Young Professionals
WOS研究方向	Computer Science ; Engineering
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000401296100012
内容类型	期刊论文
源URL	[http://119.78.100.204/handle/2XEOYT63/7231]
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, Key Lab Intelligent Informat Proc, Inst Comp Technol, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
推荐引用方式 GB/T 7714	Song, Xinhang,Jiang, Shuqiang,Herranz, Luis. Multi-Scale Multi-Feature Context Modeling for Scene Recognition in the Semantic Manifold[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2017,26(6):2721-2735.
APA	Song, Xinhang,Jiang, Shuqiang,&Herranz, Luis.(2017).Multi-Scale Multi-Feature Context Modeling for Scene Recognition in the Semantic Manifold.IEEE TRANSACTIONS ON IMAGE PROCESSING,26(6),2721-2735.
MLA	Song, Xinhang,et al."Multi-Scale Multi-Feature Context Modeling for Scene Recognition in the Semantic Manifold".IEEE TRANSACTIONS ON IMAGE PROCESSING 26.6(2017):2721-2735.