CSpace  > 中国科学院计算技术研究所期刊论文  > 英文
A multi-layer deep fusion convolutional neural network for sketch based image retrieval
Yu, Deng1; Liu, Yujie1; Pang, Yunping1; Li, Zongmin1; Li, Hua2
2018-06-28
发表期刊NEUROCOMPUTING
ISSN0925-2312
卷号296页码:23-32
摘要The purpose of this paper is to introduce a new approach for the free-hand sketch representation in the sketch based image retrieval (SBIR), where the sketches are treated as the queries to search for the natural photos in the natural image dataset. This task is known as an extremely challenging work for 3 main reasons: (i) sketches show a highly abstract visual appearance versus natural photos, fewer context can be extracted as descriptors using the existing methods, (ii) for the same object, different people provide widely different sketches, making sketch-photo matching harder, (iii) mapping the sketches and photos into a common domain is also a challenging task. In this paper, we address the cross-domain question using a strategy of mapping sketches and natural photos in multiple layers. For the first time, we introduce a multi-layer deep CNNs framework to train the multi-layer representation of free hand sketches and natural photos. We use Flickr15k dataset as benchmark for the retrieval and show that our learned representation significantly outperformances both hand-crafted features as well as deep features trained by sketches or photos. (C) 2018 Elsevier B.V. All rights reserved.
关键词Cross-domain retrieval Multi-layer modeling Deep feature fusion
DOI10.1016/j.neucom.2018.03.031
收录类别SCI
语种英语
资助项目Shandong Provincial Natural Science Foundation[ZR2015FM011] ; Shandong Provincial Natural Science Foundation[ZR2013FM036] ; National Natural Science Foundation of China[61379106] ; National Natural Science Foundation of China[61379082] ; National Natural Science Foundation of China[61227802]
WOS研究方向Computer Science
WOS类目Computer Science, Artificial Intelligence
WOS记录号WOS:000430227900003
出版者ELSEVIER SCIENCE BV
引用统计
被引频次:13[WOS]   [WOS记录]     [WOS相关记录]
文献类型期刊论文
条目标识符http://119.78.100.204/handle/2XEOYT63/5768
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Liu, Yujie
作者单位1.China Univ Petr, Coll Comp & Commun Engn, Qingdao 266580, Peoples R China
2.Univ Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714
Yu, Deng,Liu, Yujie,Pang, Yunping,et al. A multi-layer deep fusion convolutional neural network for sketch based image retrieval[J]. NEUROCOMPUTING,2018,296:23-32.
APA Yu, Deng,Liu, Yujie,Pang, Yunping,Li, Zongmin,&Li, Hua.(2018).A multi-layer deep fusion convolutional neural network for sketch based image retrieval.NEUROCOMPUTING,296,23-32.
MLA Yu, Deng,et al."A multi-layer deep fusion convolutional neural network for sketch based image retrieval".NEUROCOMPUTING 296(2018):23-32.
条目包含的文件
条目无相关文件。
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Yu, Deng]的文章
[Liu, Yujie]的文章
[Pang, Yunping]的文章
百度学术
百度学术中相似的文章
[Yu, Deng]的文章
[Liu, Yujie]的文章
[Pang, Yunping]的文章
必应学术
必应学术中相似的文章
[Yu, Deng]的文章
[Liu, Yujie]的文章
[Pang, Yunping]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

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。