Effective Image Retrieval via Multilinear Multi-Index Fusion
文献类型：期刊论文
| 作者 | Zhang, Zhizhong1,4 ; Xie, Yuan3; Zhang, Wensheng1,4; Tian, Qi2
|
| 刊名 | IEEE TRANSACTIONS ON MULTIMEDIA
 |
| 出版日期 | 2019-11-01 |
| 卷号 | 21期号:11页码:2878-2890 |
| 关键词 | Visualization Image representation Optimization Buildings Indexing Image retrieval multi-index fusion tensor multi-rank person re-identification |
| ISSN号 | 1520-9210 |
| DOI | 10.1109/TMM.2019.2915036 |
| 通讯作者 | Zhang, Wensheng(zhangwenshengia@hotmail.com) ; Tian, Qi(tian.qi1@huawei.com) |
| 英文摘要 | Multi-index fusion has demonstrated impressive performances in the retrieval task by integrating different visual representations in a unified framework. However, previous works mainly consider propagating similarities via a neighbor structure, ignoring the high-order information among different visual representations. In this paper, we propose a new multi-index fusion scheme for image retrieval. By formulating this procedure as a multilinear-based optimization problem, the complementary information hidden in different indexes can be explored more thoroughly. Specifically, we first build our multiple indexes from various visual representations. Then, a so-called index-specific functional matrix, which aims to propagate similarities, is introduced to update the original index. The functional matrices are then optimized in a unified tensor space to achieve a refinement, such that the relevant images can be pushed closer. The optimization problem can be efficiently solved by the augmented Lagrangian method with a theoretical convergence guarantee. Unlike the traditional multi-index fusion scheme, our approach embeds the multi-index subspace structure into the new indexes with sparse constraint and, thus, it has little additional memory consumption in the online query stage. Experimental evaluation on three benchmark datasets reveals that the proposed approach achieves state-of-the-art performance, that is, N-score 3.94 on UKBench, mAP 94.1 on Holiday, and 62.39 on Market-1501. |
| WOS关键词 | SCALE ; FEATURES |
| 资助项目 | National Key R&D Program of China[2017YFC0803700] ; National Natural Science Foundation of China[U1636220] ; National Natural Science Foundation of China[61432008] ; National Natural Science Foundation of China[61472423] ; National Natural Science Foundation of China[61772524] ; Beijing Municipal Natural Science Foundation[4182067] |
| WOS研究方向 | Computer Science ; Telecommunications |
| 语种 | 英语 |
| WOS记录号 | WOS:000494363000015 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 资助机构 | National Key R&D Program of China ; National Natural Science Foundation of China ; Beijing Municipal Natural Science Foundation |
| 源URL | [http://ir.ia.ac.cn/handle/173211/28828]  |
| 专题 | 精密感知与控制研究中心_人工智能与机器学习 |
| 通讯作者 | Zhang, Wensheng; Tian, Qi |
| 作者单位 | 1.Chinese Acad Sci, Inst Automat, Res Ctr Precis Sensing & Control, Beijing 100190, Peoples R China 2.Huawei Noahs Ark Lab, Comp Vis, Shenzhen 518000, Peoples R China 3.East China Normal Univ, Sch Comp Sci & Software Engn, Shanghai 200241, Peoples R China 4.Univ Chinese Acad Sci, Sch Artificial Intelligence, Shenzhen 518000, Peoples R China |
| 推荐引用方式 GB/T 7714 | Zhang, Zhizhong,Xie, Yuan,Zhang, Wensheng,et al. Effective Image Retrieval via Multilinear Multi-Index Fusion[J]. IEEE TRANSACTIONS ON MULTIMEDIA,2019,21(11):2878-2890. |
| APA | Zhang, Zhizhong,Xie, Yuan,Zhang, Wensheng,&Tian, Qi.(2019).Effective Image Retrieval via Multilinear Multi-Index Fusion.IEEE TRANSACTIONS ON MULTIMEDIA,21(11),2878-2890. |
| MLA | Zhang, Zhizhong,et al."Effective Image Retrieval via Multilinear Multi-Index Fusion".IEEE TRANSACTIONS ON MULTIMEDIA 21.11(2019):2878-2890. |
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。