Knowledge Commons of Institute of Automation,CAS
Effective Image Retrieval via Multilinear Multi-Index Fusion | |
Zhang, Zhizhong1,2; Xie, Yuan3; Zhang, Wensheng1,2; Tian, Qi4 | |
发表期刊 | IEEE TRANSACTIONS ON MULTIMEDIA |
ISSN | 1520-9210 |
2019-11-01 | |
卷号 | 21期号:11页码:2878-2890 |
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. |
关键词 | Visualization Image representation Optimization Buildings Indexing Image retrieval multi-index fusion tensor multi-rank person re-identification |
DOI | 10.1109/TMM.2019.2915036 |
关键词[WOS] | SCALE ; FEATURES |
收录类别 | SCI |
语种 | 英语 |
资助项目 | National Natural Science Foundation of China[61432008] ; National Key R&D Program of China[2017YFC0803700] ; Beijing Municipal Natural Science Foundation[4182067] ; National Natural Science Foundation of China[61772524] ; National Natural Science Foundation of China[61472423] ; National Natural Science Foundation of China[U1636220] ; National Natural Science Foundation of China[U1636220] ; National Natural Science Foundation of China[61472423] ; National Natural Science Foundation of China[61772524] ; Beijing Municipal Natural Science Foundation[4182067] ; National Key R&D Program of China[2017YFC0803700] ; National Natural Science Foundation of China[61432008] |
WOS研究方向 | Computer Science ; Telecommunications |
WOS类目 | Computer Science, Information Systems ; Computer Science, Software Engineering ; Telecommunications |
WOS记录号 | WOS:000494363000015 |
出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
七大方向——子方向分类 | 图像视频处理与分析 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/28829 |
专题 | 多模态人工智能系统全国重点实验室_人工智能与机器学习(杨雪冰)-技术团队 |
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.Univ Chinese Acad Sci, Sch Artificial Intelligence, Shenzhen 518000, Peoples R China 3.East China Normal Univ, Sch Comp Sci & Software Engn, Shanghai 200241, Peoples R China 4.Huawei Noahs Ark Lab, Comp Vis, Shenzhen 518000, Peoples R China |
第一作者单位 | 精密感知与控制研究中心 |
通讯作者单位 | 精密感知与控制研究中心 |
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. |
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 | ||
axivr.pdf(1024KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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。
修改评论