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 | |
会议日期 | October 21–25, 2019 |
会议地点 | Nice, France |
关键词 | Person Re-identification Feature Fusion GNN |
DOI | 10.1145/3343031.3350982 |
英文摘要 | 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. |
会议录 | ACM Multimedia Conference (MM 19) |
语种 | 英语 |
URL标识 | 查看原文 |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/44929] |
专题 | 自动化研究所_模式识别国家重点实验室_多媒体计算与图形学团队 |
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]. 见:. Nice, France. October 21–25, 2019. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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