MFC: A Multi-scale Fully Convolutional Approach for Visual Instance Retrieval | |
Hao, Jiedong1,2; Wang, Wei1; Dong, Jing1; Tan, Tieniu1 | |
2017-09 | |
会议名称 | 2017 IEEE International Conference on Multimedia & Expo Workshops (ICMEW) |
会议日期 | 10-14 July 2017 |
会议地点 | Hong Kong |
摘要 | Previous work has shown that feature maps of deep convolutional neural networks (CNNs) can be interpreted as feature representation of an image. Image features aggregated from these feature maps have achieved steady progress in terms of performances on visual instance retrieval tasks in recent years. The key to the success of such methods is feature representation. Inthispaper,westudyhowtorepresentanimage using discriminative features. We demonstrate first that image size is an important factor which affects the performance of instance retrieval but has not been thoroughly discussed in previous work. Based on experimental evaluations, we propose a multi-scale fully convolutional (MFC) approach to encode the image efficiently and effectively. The proposed method is simple to implement, which does not employ sophisticated post-processing techniques such as query expansion, yet shows promising results on four public datasets. |
关键词 | Visual Instance Retrieval Image Resizing Strategy Multi-scale Representation Fully Convolutional Neural Network |
收录类别 | EI |
语种 | 英语 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/20992 |
专题 | 智能感知与计算研究中心 |
通讯作者 | Dong, Jing |
作者单位 | 1.中国科学院自动化研究所智能感知与计算研究中心 2.中国科学院大学 |
第一作者单位 | 智能感知与计算研究中心 |
通讯作者单位 | 智能感知与计算研究中心 |
推荐引用方式 GB/T 7714 | Hao, Jiedong,Wang, Wei,Dong, Jing,et al. MFC: A Multi-scale Fully Convolutional Approach for Visual Instance Retrieval[C],2017. |
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 | ||
ICME-w53.pdf(922KB) | 会议论文 | 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