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
Category co-occurrence modeling for large scale scene recognition

文献类型：期刊论文

作者Song, Xinhang1; Jiang, Shuqiang1; Herranz, Luis1; Kong, Yan2; Zheng, Kai3
刊名PATTERN RECOGNITION
出版日期2016-11-01
卷号59页码:98-111
ISSN号0031-3203
关键词Scene recognition Co-occurrence modeling Semantic space Feature embedding Multiple feature combination Large scale image recognition
DOI10.1016/j.patcog.2016.01.019
英文摘要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.
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
语种英语
出版者ELSEVIER SCI LTD
WOS记录号WOS:000383007800010
源URL[http://119.78.100.204/handle/2XEOYT63/8156]  
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.

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。