CASIA OpenIR  > 模式识别国家重点实验室  > 多媒体计算
Adaptive Feature Fusion via Graph Neural Network for Person Re-identification
Li, Yaoyu1,2; Yao, Hantao1,2; Duan, Lingyu3,4; Yao, Hanxing5; Xu, Changsheng1,2,3
2019-10
会议名称ACM Multimedia
会议录名称ACM Multimedia Conference (MM 19)
会议日期October 21–25, 2019
会议地点Nice, France
摘要

Person Re-identification (ReID) targets to identify a probe person appeared under multiple camera views. Existing methods focus on proposing a robust model to capture the discriminative information. However, they all generate a representation by mining useful clues from a given single image, and ignore the intercommunication with other images. To address this issue, we propose a novel network named Feature-Fusing Graph Neural Network (FFGNN), which fully utilizes the relationships among the nearest neighbors of the given image, and allows message propagation to update the feature of the node during representation learning. Given an anchor image, the FFGNN firstly obtains its Top-K nearest images based on the feature generated by the trained Feature-Extracting Network(FEN). We then construct a graph G based on the obtained K + 1 images, in which each node represents the feature of an image. The edge of the graph G is obtained by combing the visual similarity and Jaccard similarity between nodes. Within the constructed graph G, FFGNN conducts message propagation and adaptive feature fusion between nodes by iteratively performing graph convolutional operation on the input features. Finally, the FFGNN outputs a robust and discriminative representation which contains the information from its similar images. Extensive experiments on three public person ReID datasets including Market-1501, DukeMTMC-ReID, and CUHK03 demonstrate that the proposed model can achieve significant improvement against state-of-the-art methods.

关键词Person Re-identification Feature Fusion GNN
学科门类工学 ; 工学::控制科学与工程
DOI10.1145/3343031.3350982
URL查看原文
收录类别EI
资助项目National Natural Science Foundation of China (NSFC)[61720106006] ; National Natural Science Foundation of China[61432019]
语种英语
七大方向——子方向分类图像视频处理与分析
引用统计
被引频次:12[WOS]   [WOS记录]     [WOS相关记录]
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/44929
专题模式识别国家重点实验室_多媒体计算
通讯作者Xu, Changsheng
作者单位1.National Lab of Pattern Recognition, Institute of Automation, CAS, Beijing 100190, China
2.University of Chinese Academy of Sciences, Beijing
3.Peng Cheng Laboratory, Shenzhen
4.Institute of Digital Media, Peking University, Beijing
5.Llvision Technology
推荐引用方式
GB/T 7714
Li, Yaoyu,Yao, Hantao,Duan, Lingyu,et al. Adaptive Feature Fusion via Graph Neural Network for Person Re-identification[C],2019.
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
Adaptive Feature Fus(2961KB)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
[Li, Yaoyu]的文章
[Yao, Hantao]的文章
[Duan, Lingyu]的文章
百度学术
百度学术中相似的文章
[Li, Yaoyu]的文章
[Yao, Hantao]的文章
[Duan, Lingyu]的文章
必应学术
必应学术中相似的文章
[Li, Yaoyu]的文章
[Yao, Hantao]的文章
[Duan, Lingyu]的文章
相关权益政策
暂无数据
收藏/分享
文件名: Adaptive Feature Fusion via Graph Neural Network for Person Re-identification.pdf
格式: Adobe PDF
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。