| How to represent scenes for classification? | |
Shi, Jianhua1,2 ; Li, Xuelong1; Dong, Yongsheng1
| |
| 2015 | |
| 会议名称 | IEEE China Summit and International Conference on Signal and Information Processing, ChinaSIP 2015 |
| 会议录名称 | 2015 IEEE China Summit and International Conference on Signal and Information Processing, ChinaSIP 2015 - Proceedings |
| 页码 | 191-195 |
| 会议日期 | 2015-07 |
| 会议地点 | Chengdu, China |
| 出版者 | Institute of Electrical and Electronics Engineers Inc. |
| 产权排序 | 1 |
| 摘要 | Object-based scene image representations can effectively capture the semantic meanings of a scene. However, they usually neglect a scene's structure information. In this paper, we propose a novel and effective detector-based scene representation method for scene classification. In particular, we extract object features by object detectors. By sensible principal component analysis, we obtain a compact representation vector of objects in a scene image. To capture the scene layout, we then train lots of deformable part models to form a scene response vector. By concatenating these two vectors we use a linear support vector machine for scene classification. When combining with DeCAF [1] in a special way, our method is even more powerful on complex scene categorization. Experimental results on the MIT indoor database show that our approach achieves state-of-The-Art performance on scene classification compared with several popular methods. © 2015 IEEE. |
| 作者部门 | 光学影像学习与分析中心 |
| DOI | 10.1109/ChinaSIP.2015.7230389 |
| 收录类别 | EI |
| ISBN号 | 9781479919482 |
| 语种 | 英语 |
| 引用统计 | |
| 文献类型 | 会议论文 |
| 条目标识符 | http://ir.opt.ac.cn/handle/181661/27821 |
| 专题 | 光谱成像技术研究室 |
| 通讯作者 | Dong, Yongsheng |
| 作者单位 | 1.Center for OPTical IMagery Analysis and Learning (OPTIMAL), State Key Laboratory of Transient Optics and Photonics, Xi'An Institute of Optics and Precision Mechanics, Xi'an, Shaanxi, China 2.University of Chinese Academy of Sciences, 19A Yuquanlu, Beijing, China |
| 推荐引用方式 GB/T 7714 | Shi, Jianhua,Li, Xuelong,Dong, Yongsheng. How to represent scenes for classification?[C]:Institute of Electrical and Electronics Engineers Inc.,2015:191-195. |
| 条目包含的文件 | ||||||
| 文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
| How to represent sce（890KB） | 会议论文 | 限制开放 | CC BY-NC-SA | 请求全文 | ||
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