CASIA OpenIR  > 模式识别实验室
Deep Spatial Feature Reconstruction for Partial Person Reidentification: Alignment-free Approach
He LX(何凌霄); Liang J(梁坚); Li HQ(李海青); Sun ZN(孙哲南)
2018
会议名称CVPR
会议日期6.18-6.21
会议地点美国盐湖城
摘要

Partial person re-identification (re-id) is a challenging problem, where only several partial observations (images) of people are available for matching. However, few studies have provided flexible solutions to identifying a person in an image containing arbitrary part of the body. In this paper, we propose a fast and accurate matching method to address this problem. The proposed method leverages Fully
Convolutional Network (FCN) to generate fix-sized spatial feature maps such that pixel-level features are consistent. To match a pair of person images of different sizes, a novel method called Deep Spatial feature Reconstruction (DSR) is further developed to avoid explicit alignment. Specifically, DSR exploits the reconstructing error from popular dictionary learning models to calculate the similarity between different spatial feature maps. In that way, we expect that the proposed FCN can decrease the similarity of coupled images from different persons and increase that from the same person. Experimental results on two partial person datasets demonstrate the efficiency and effectiveness of the proposed method in comparison with several state-ofthe-art partial person re-id approaches. Additionally, DSR achieves competitive results on a benchmark person dataset
Market1501 with 83.58% Rank-1 accuracy.

收录类别EI
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/23698
专题模式识别实验室
作者单位中科院自动化研究所
第一作者单位中国科学院自动化研究所
推荐引用方式
GB/T 7714
He LX,Liang J,Li HQ,et al. Deep Spatial Feature Reconstruction for Partial Person Reidentification: Alignment-free Approach[C],2018.
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
DSR for Partial Pers(2312KB)会议论文 开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[He LX(何凌霄)]的文章
[Liang J(梁坚)]的文章
[Li HQ(李海青)]的文章
百度学术
百度学术中相似的文章
[He LX(何凌霄)]的文章
[Liang J(梁坚)]的文章
[Li HQ(李海青)]的文章
必应学术
必应学术中相似的文章
[He LX(何凌霄)]的文章
[Liang J(梁坚)]的文章
[Li HQ(李海青)]的文章
相关权益政策
暂无数据
收藏/分享
文件名: DSR for Partial Person ReID_Camera-Ready Version.pdf
格式: Adobe PDF
此文件暂不支持浏览
所有评论 (0)
暂无评论
 

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。