Accurate and efficient cross-domain visual matching leveraging multiple feature representations
文献类型：会议论文
| 作者 | Sun, Gang (1) ; Wang, Shuhui (3) ; Liu, Xuehui (1) ; Huang, Qingming (2) ; Chen, Yanyun (1) ; Wu, Enhua (1) |
| 出版日期 | 2013 |
| 关键词 | Visual matching Cross-domain Multiple features Hyperplane hashing |
| 页码 | 565-575 |
| 通讯作者 | Sun, G.(sung@ios.ac.cn) |
| 中文摘要 | Cross-domain visual matching aims at finding visually similar images across a wide range of visual domains, and has shown a practical impact on a number of applications. Unfortunately, the state-of-the-art approach, which estimates the relative importance of the single feature dimensions still suffers from low matching accuracy and high time cost. To this end, this paper proposes a novel cross-domain visual matching framework leveraging multiple feature representations. To integrate the discriminative power of multiple features, we develop a data-driven, query specific feature fusion model, which estimates the relative importance of the individual feature dimensions as well as the weight vector among multiple features simultaneously. Moreover, to alleviate the computational burden of an exhaustive subimage search, we design a speedup scheme, which employs hyperplane hashing for rapidly collecting the hard-negatives. Extensive experiments carried out on various matching tasks demonstrate that the proposed approach outperforms the state-of-the-art in both accuracy and efficiency. © 2013 Springer-Verlag Berlin Heidelberg. |
| 英文摘要 | Cross-domain visual matching aims at finding visually similar images across a wide range of visual domains, and has shown a practical impact on a number of applications. Unfortunately, the state-of-the-art approach, which estimates the relative importance of the single feature dimensions still suffers from low matching accuracy and high time cost. To this end, this paper proposes a novel cross-domain visual matching framework leveraging multiple feature representations. To integrate the discriminative power of multiple features, we develop a data-driven, query specific feature fusion model, which estimates the relative importance of the individual feature dimensions as well as the weight vector among multiple features simultaneously. Moreover, to alleviate the computational burden of an exhaustive subimage search, we design a speedup scheme, which employs hyperplane hashing for rapidly collecting the hard-negatives. Extensive experiments carried out on various matching tasks demonstrate that the proposed approach outperforms the state-of-the-art in both accuracy and efficiency. © 2013 Springer-Verlag Berlin Heidelberg. |
| 收录类别 | SCI ; EI |
| 会议录出版地 | Springer Verlag |
| 语种 | 英语 |
| ISSN号 | 1782789 |
| WOS记录号 | WOS:000319478400011 |
| 源URL | [http://ir.iscas.ac.cn/handle/311060/16556]  |
| 专题 | 软件研究所_软件所图书馆_会议论文 |
| 推荐引用方式 GB/T 7714 | Sun, Gang ,Wang, Shuhui ,Liu, Xuehui ,et al. Accurate and efficient cross-domain visual matching leveraging multiple feature representations[C]. 见:. |
入库方式： OAI收割
来源：软件研究所
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。