Multi-View 3D Object Retrieval With Deep Embedding Network
Guo, Haiyun1,2; Wang, Jinqiao1,2; Gao, Yue3; Li, Jianqiang4; Lu, Hanqing1,2
2016-12-01
发表期刊IEEE TRANSACTIONS ON IMAGE PROCESSING
卷号25期号:12页码:5526-5537
文章类型Article
摘要In multi-view 3D object retrieval, each object is characterized by a group of 2D images captured from different views. Rather than using hand-crafted features, in this paper, we take advantage of the strong discriminative power of convolutional neural network to learn an effective 3D object representation tailored for this retrieval task. Specifically, we propose a deep embedding network jointly supervised by classification loss and triplet loss to map the high-dimensional image space into a low-dimensional feature space, where the Euclidean distance of features directly corresponds to the semantic similarity of images. By effectively reducing the intra-class variations while increasing the inter-class ones of the input images, the network guarantees that similar images are closer than dissimilar ones in the learned feature space. Besides, we investigate the effectiveness of deep features extracted from different layers of the embedding network extensively and find that an efficient 3D object representation should be a tradeoff between global semantic information and discriminative local characteristics. Then, with the set of deep features extracted from different views, we can generate a comprehensive description for each 3D object and formulate the multi-view 3D object retrieval as a set-to-set matching problem. Extensive experiments on SHREC'15 data set demonstrate the superiority of our proposed method over the previous state-of-the-art approaches with over 12% performance improvement.
关键词Convolutional Neural Network Multi-view 3d Object Retrieval Triplet Loss
WOS标题词Science & Technology ; Technology
DOI10.1109/TIP.2016.2609814
关键词[WOS]MODEL RETRIEVAL ; VISUAL SIMILARITY ; DISTANCE ; DESCRIPTOR
收录类别SCI
语种英语
项目资助者863 Program(2014AA015104) ; National Natural Science Foundation of China(61273034 ; 61332016)
WOS研究方向Computer Science ; Engineering
WOS类目Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号WOS:000388205100002
引用统计
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/13354
专题模式识别国家重点实验室_图像与视频分析
作者单位1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
2.Univ Chinese Acad Sci, Beijing 100190, Peoples R China
3.Tsinghua Univ, Sch Software, Tsinghua Natl Lab Informat Sci & Technol TNList, Key Lab Informat Syst Secur,Minist Educ, Beijing 100084, Peoples R China
4.Beijing Univ Technol, Sch Software Engn, Beijing Engn Res Ctr IoT Software & Syst, Beijing 100083, Peoples R China
推荐引用方式
GB/T 7714
Guo, Haiyun,Wang, Jinqiao,Gao, Yue,et al. Multi-View 3D Object Retrieval With Deep Embedding Network[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2016,25(12):5526-5537.
APA Guo, Haiyun,Wang, Jinqiao,Gao, Yue,Li, Jianqiang,&Lu, Hanqing.(2016).Multi-View 3D Object Retrieval With Deep Embedding Network.IEEE TRANSACTIONS ON IMAGE PROCESSING,25(12),5526-5537.
MLA Guo, Haiyun,et al."Multi-View 3D Object Retrieval With Deep Embedding Network".IEEE TRANSACTIONS ON IMAGE PROCESSING 25.12(2016):5526-5537.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
HaiyunGuo-multi-view(2793KB)期刊论文作者接受稿开放获取CC BY-NC-SA浏览 下载
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
[Guo, Haiyun]的文章
[Wang, Jinqiao]的文章
[Gao, Yue]的文章
百度学术
百度学术中相似的文章
[Guo, Haiyun]的文章
[Wang, Jinqiao]的文章
[Gao, Yue]的文章
必应学术
必应学术中相似的文章
[Guo, Haiyun]的文章
[Wang, Jinqiao]的文章
[Gao, Yue]的文章
相关权益政策
暂无数据
收藏/分享
文件名: HaiyunGuo-multi-view 3D object retrieval with deep embedding network.pdf
格式: Adobe PDF
此文件暂不支持浏览
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。