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
Scene Recognition With Prototype-Agnostic Scene Layout

文献类型：期刊论文

作者Chen, Gongwei2; Song, Xinhang2; Zeng, Haitao1,3; Jiang, Shuqiang2
刊名IEEE TRANSACTIONS ON IMAGE PROCESSING
出版日期2020
卷号29页码:5877-5888
关键词Layout Semantics Prototypes Image recognition Convolution Neural networks Deformable models Scene classification convolution neural networks graph neural networks scene layout
ISSN号1057-7149
DOI10.1109/TIP.2020.2986599
英文摘要Exploiting the spatial structure in scene images is a key research direction for scene recognition. Due to the large intra-class structural diversity, building and modeling flexible structural layout to adapt various image characteristics is a challenge. Existing structural modeling methods in scene recognition either focus on predefined grids or rely on learned prototypes, which all have limited representative ability. In this paper, we propose Prototype-agnostic Scene Layout (PaSL) construction method to build the spatial structure for each image without conforming to any prototype. Our PaSL can flexibly capture the diverse spatial characteristic of scene images and have considerable generalization capability. Given a PaSL, we build Layout Graph Network (LGN) where regions in PaSL are defined as nodes and two kinds of independent relations between regions are encoded as edges. The LGN aims to incorporate two topological structures (formed in spatial and semantic similarity dimensions) into image representations through graph convolution. Extensive experiments show that our approach achieves state-of-the-art results on widely recognized MIT67 and SUN397 datasets without multi-model or multi-scale fusion. Moreover, we also conduct the experiments on one of the largest scale datasets, Places365. The results demonstrate the proposed method can be well generalized and obtains competitive performance.
资助项目National Key Research and Development Project of New Generation Artificial Intelligence of China[2018AAA0102500] ; National Natural Science Foundation of China[61532018] ; National Natural Science Foundation of China[61902378] ; Beijing Natural Science Foundation[L182054] ; Beijing Natural Science Foundation[Z190020] ; National Program for Special Support of Eminent Professionals ; National Program for Support of Top-Notch Young Professionals ; Lenovo Outstanding Young Scientists Program ; National Postdoctoral Program for Innovative Talents[BX201700255]
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:000532260800007
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
源URL[http://119.78.100.204/handle/2XEOYT63/15400]  
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.China Univ Min & Technol Beijing, Sch Mech Elect & Informat Engn, Beijing 100083, Peoples R China
2.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China
3.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714		 Chen, Gongwei,Song, Xinhang,Zeng, Haitao,et al. Scene Recognition With Prototype-Agnostic Scene Layout[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2020,29:5877-5888.
APA Chen, Gongwei,Song, Xinhang,Zeng, Haitao,&Jiang, Shuqiang.(2020).Scene Recognition With Prototype-Agnostic Scene Layout.IEEE TRANSACTIONS ON IMAGE PROCESSING,29,5877-5888.
MLA Chen, Gongwei,et al."Scene Recognition With Prototype-Agnostic Scene Layout".IEEE TRANSACTIONS ON IMAGE PROCESSING 29(2020):5877-5888.

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。