Institute of Computing Technology, Chinese Academy IR
Category co-occurrence modeling for large scale scene recognition | |
Song, Xinhang1; Jiang, Shuqiang1; Herranz, Luis1; Kong, Yan2; Zheng, Kai3 | |
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 | |
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. |
条目包含的文件 | 条目无相关文件。 |
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。
修改评论