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. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 多媒体计算与图形学团队
Scene Recognition Based on Recurrent Memorized Attention Network

文献类型：期刊论文

作者Shao, Xi1,2; Zhang, Xuan1; Tang, Guijin1; Bao, Bingkun1
刊名ELECTRONICS
出版日期2020-12-01
卷号9期号:12页码:19
关键词scene classification attention model object locating
DOI10.3390/electronics9122038
通讯作者Bao, Bingkun(bingkunbao@njupt.edu.cn)
英文摘要We propose a new end-to-end scene recognition framework, called a Recurrent Memorized Attention Network (RMAN) model, which performs object-based scene classification by recurrently locating and memorizing objects in the image. Based on the proposed framework, we introduce a multi-task mechanism that contiguously attends on the different essential objects in a scene image and recurrently performs memory fusion of the features of object focused by an attention model to improve the scene recognition accuracy. The experimental results show that the RMAN model has achieved better classification performance on the constructed dataset and two public scene datasets, surpassing state-of-the-art image scene recognition approaches.
WOS关键词OBJECTS
资助项目National Nature Science Foundation of China[61872199] ; National Nature Science Foundation of China[61872424] ; National Nature Science Foundation of China[61936005] ; National Key Research and Development Project[2020AAA0106200] ; Open Projects Program of National Laboratory of Pattern Recognition and Nanjing University of Posts and Telecommunications Support Funding[NY218001]
WOS研究方向Engineering
语种英语
WOS记录号WOS:000601952300001
出版者MDPI
资助机构National Nature Science Foundation of China ; National Key Research and Development Project ; Open Projects Program of National Laboratory of Pattern Recognition and Nanjing University of Posts and Telecommunications Support Funding
源URL[http://ir.ia.ac.cn/handle/173211/42823]  
专题自动化研究所_模式识别国家重点实验室_多媒体计算与图形学团队
通讯作者Bao, Bingkun
作者单位1.Nanjing Univ Posts & Telecommun, Coll Commun & Informat Engn, Nanjing 210003, Peoples R China
2.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714		 Shao, Xi,Zhang, Xuan,Tang, Guijin,et al. Scene Recognition Based on Recurrent Memorized Attention Network[J]. ELECTRONICS,2020,9(12):19.
APA Shao, Xi,Zhang, Xuan,Tang, Guijin,&Bao, Bingkun.(2020).Scene Recognition Based on Recurrent Memorized Attention Network.ELECTRONICS,9(12),19.
MLA Shao, Xi,et al."Scene Recognition Based on Recurrent Memorized Attention Network".ELECTRONICS 9.12(2020):19.

入库方式： OAI收割

来源：自动化研究所

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。