LRDNN: Local-refining based deep neural network for person re-identification with attribute discerning | |
Gou, Mengran1; Zhang, Yulun1; Sun G(孙干)2,3; Lan, Xiangyuan4; Zhong BN(钟必能)5,6; Zhou, Qinqin6 | |
2019 | |
会议日期 | August 10-16, 2019 |
会议地点 | Macao, China |
页码 | 1041-1047 |
英文摘要 | Recently, pose or attribute information has been widely used to solve person re-identification (re-ID) problem. However, the inaccurate output from pose or attribute modules will impair the final person re-ID performance. Since re-ID, pose estimation and attribute recognition are all based on the person appearance information, we propose a Local-refining based Deep Neural Network (LRDNN) to aggregate pose estimation and attribute recognition to improve the re-ID performance. To this end, we add a pose branch to extract the local spatial information and optimize the whole network on both person identity and attribute objectives. To diminish the negative affect from unstable pose estimation, a novel structure called channel parse block (CPB) is introduced to learn weights on different feature channels in pose branch. Then two branches are combined with compact bilinear pooling. Experimental results on Market1501 and DukeMTMC-reid datasets illustrate the effectiveness of the proposed method. |
源文献作者 | Baidu ; et al. ; Huawei ; International Joint Conferences on Artifical Intelligence (IJCAI) ; Sony ; Xiao-i |
产权排序 | 4 |
会议录 | Proceedings of the 28th International Joint Conference on Artificial Intelligence, IJCAI 2019 |
会议录出版者 | International Joint Conferences on Artificial Intelligence |
语种 | 英语 |
ISSN号 | 1045-0823 |
ISBN号 | 978-0-9992411-4-1 |
内容类型 | 会议论文 |
源URL | [http://ir.sia.cn/handle/173321/25875] |
专题 | 沈阳自动化研究所_机器人学研究室 |
作者单位 | 1.Department of ECE, Northeastern University, United States 2.University of Chinese Academy of Sciences, China 3.State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, China 4.Department of Computer Science, Hong Kong Baptist University, Hong Kong 5.Provincial Key Laboratory for Computer Information Processing Technology, Soochow University, China 6.Department of Computer Science and Technology, Huaqiao University, China |
推荐引用方式 GB/T 7714 | Gou, Mengran,Zhang, Yulun,Sun G,et al. LRDNN: Local-refining based deep neural network for person re-identification with attribute discerning[C]. 见:. Macao, China. August 10-16, 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