Institute of Computing Technology, Chinese Academy IR
| Sparse Online Learning of Image Similarity | |
| Gao, Xingyu1,3; Hoi, Steven C. H.2; Zhang, Yongdong3; Zhou, Jianshe4; Wan, Ji3; Chen, Zhenyu5; Li, Jintao3; Zhu, Jianke6 | |
| 2017-09-01 | |
| 发表期刊 | ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY
 |
| ISSN | 2157-6904 |
| 卷号 | 8期号:5页码:22 |
| 摘要 | Learning image similarity plays a critical role in real-world multimedia information retrieval applications, especially in Content-Based Image Retrieval (CBIR) tasks, in which an accurate retrieval of visually similar objects largely relies on an effective image similarity function. Crafting a good similarity function is very challenging because visual contents of images are often represented as feature vectors in high-dimensional spaces, for example, via bag-of-words (BoW) representations, and traditional rigid similarity functions, for example, cosine similarity, are often suboptimal for CBIR tasks. In this article, we address this fundamental problem, that is, learning to optimize image similarity with sparse and high-dimensional representations from large-scale training data, and propose a novel scheme of Sparse Online Learning of Image Similarity (SOLIS). In contrast to many existing image-similarity learning algorithms that are designed to work with low-dimensional data, SOLIS is able to learn image similarity from large-scale image data in sparse and high-dimensional spaces. Our encouraging results showed that the proposed new technique achieves highly competitive accuracy as compared to the state-of-the-art approaches but enjoys significant advantages in computational efficiency, model sparsity, and retrieval scalability, making it more practical for real-world multimedia retrieval applications. |
| 关键词 | Online learning metric learning similarity learning distance metric bag-of-words representation image retrieval |
| DOI | 10.1145/3065950 |
| 收录类别 | SCI |
| 语种 | 英语 |
| 资助项目 | National Key Research and Development Program of China[2016YFB0800403] ; National Nature Science Foundation of China[61525206] ; National Nature Science Foundation of China[61572472] ; National Nature Science Foundation of China[61428207] ; Singapore Ministry of Education (MOE) Academic Research Fund (AcRF) Tier 1 Grant ; Beijing Natural Science Foundation[4152050] ; Beijing Advanced Innovation Center for Imaging Technology[BAICIT-2016009] |
| WOS研究方向 | Computer Science |
| WOS类目 | Computer Science, Artificial Intelligence ; Computer Science, Information Systems |
| WOS记录号 | WOS:000414318500003 |
| 出版者 | ASSOC COMPUTING MACHINERY |
| 引用统计 | |
| 文献类型 | 期刊论文 |
| 条目标识符 | http://119.78.100.204/handle/2XEOYT63/6468 |
| 专题 | 中国科学院计算技术研究所期刊论文_英文 |
| 通讯作者 | Hoi, Steven C. H.; Zhang, Yongdong |
| 作者单位 | 1.Chinese Acad Sci, Inst Software, Lab Parallel Software & Computat Sci, Beijing 100190, Peoples R China 2.Singapore Management Univ, Sch Informat Syst, Singapore 188065, Singapore 3.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China 4.Capital Normal Univ, Beijing Adv Innovat Ctr Imaging Technol, Beijing 100048, Peoples R China 5.Chinese Acad Sci, China Elect Power Res Inst, Key Lab Intelligent Informat Proc, Inst Comp Technol, Beijing 100192, Peoples R China 6.Zhejiang Univ, Coll Comp Sci & Technol, Hangzhou 310058, Zhejiang, Peoples R China |
| 推荐引用方式 GB/T 7714 | Gao, Xingyu,Hoi, Steven C. H.,Zhang, Yongdong,et al. Sparse Online Learning of Image Similarity[J]. ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY,2017,8(5):22. |
| APA | Gao, Xingyu.,Hoi, Steven C. H..,Zhang, Yongdong.,Zhou, Jianshe.,Wan, Ji.,...&Zhu, Jianke.(2017).Sparse Online Learning of Image Similarity.ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY,8(5),22. |
| MLA | Gao, Xingyu,et al."Sparse Online Learning of Image Similarity".ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY 8.5(2017):22. |
| 条目包含的文件 | 条目无相关文件。 | |||||
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