Knowledge Commons of Institute of Automation,CAS
Weakly Supervised Person Search | |
Yan, Lan1,2; Zheng, Wenbo1,3; Wang, Fei-Yue1; Gou, Chao4 | |
2020-10-06 | |
会议名称 | International Conference on Data Science and Advanced Analytics (DSAA) |
会议日期 | 2020-10-6 |
会议地点 | Sydney, Australia |
摘要 | While existing person search methods have achieved good performance, they require the images used for training contain labels about the identity and bounding box location of each person. However, it is expensive and difficult to manually annotate these labels in the large scale scenario. To overcome this issue, we consider weakly supervised person search. The weakly supervised setting means during training we only know which identities appear in the image set and how many individuals present in each image, without any identity or location information on the image. Facing this challenge, we propose a clustering and patch based weakly supervised learning (CPBWSL) framework, which separately addresses two sub-tasks including pedestrian detection and person re-identification. Particularly, we introduce multiple detectors to provide more detection results as well as fuzzy c-means clustering algorithm to cluster these results and remove low membership ones. Moreover, a patch based learning network is designed to generate different patches and learn discriminative patch features. Extensive experiments on two benchmarks indicate that the proposed weakly supervised setting is feasible and our method can achieve performance comparable to some fully supervised person search methods. |
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/173211/48877 |
专题 | 多模态人工智能系统全国重点实验室_平行智能技术与系统团队 |
作者单位 | 1.State Key Laboratory for Management and Control of Complex Systems, Institute of Automation, Chinese Academy of Sciences 2.University of Chinese Academy of Sciences 3.School of Software Engineering, Xi'an Jiaotong University 4.School of Intelligent Systems Engineering, Sun Yat-sen University |
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 | Yan, Lan,Zheng, Wenbo,Wang, Fei-Yue,et al. Weakly Supervised Person Search[C],2020. |
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 | ||
Weakly Supervised Pe(651KB) | 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