...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Neurocomputing >Learning refined attribute-aligned network with attribute selection for person re-identification
【24h】

Learning refined attribute-aligned network with attribute selection for person re-identification

机译：学习精确的属性对齐的网络，具有属性选择的人重新识别

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Effective person re-identification (Re-ID) is often required in real applications. While most exiting approaches either assume the detected pedestrian bounding box well-aligned or utilize limited human structural information (pose, attention, segmentation) to calibrate the misalignment. However, the value of utilizing attributes for pedestrian alignment is still under explored. Furthermore, the hierarchy of attributes in previous works has been largely ignored, appearance feature and attribute feature are often fused in a rigid way. This directly limits the discriminatory and robustness of feature representation. In this paper, we propose a Refined Attribute-aligned Network (RAN), which consists of a coarse-alignment and a fine-alignment module. First, the pre-trained part and attribute predictor are used to generate body parts and candidate attributes. Then the body parts are used for coarse alignment and the attributes are selected by an agent. The agent is optimized with policy gradient algorithm, which can maximize the accumulative reward to increase the probability of proper attribute selection. Finally, for the fine-alignment, the attribute maps and body part features are aggregated by a bilinear-pooling layer to support accurate Re-ID. Extensive experimental results based on multiple datasets including CUHK03, DukeMTMC and Market-1501 demonstrate the superiority of our method over state-of-the-art methods. (C) 2020 Elsevier B.V. All rights reserved.
机译：实际应用中通常需要有效的人重新识别（RE-ID）。虽然大多数退出方法假设检测到的行人边界框良好对齐或利用有限的人类结构信息（姿势，注意，分割）来校准未对准。然而，仍在探索利用行人对齐的属性的价值。此外，以前的作品中的属性层次已经大大忽略，外观功能和属性功能通常以刚性的方式融合。这直接限制了特征表示的歧视性和鲁棒性。在本文中，我们提出了一种精确的属性对齐的网络（RAN），其包括粗对准和微调模块。首先，预先训练的部分和属性预测器用于生成身体部位和候选属性。然后，车身部件用于粗略对准，并且由代理选择属性。该代理通过策略梯度算法进行了优化，可以最大化累积奖励以增加适当的属性选择的概率。最后，对于细准，属性映射和主体零件特征由双线性池层聚合，以支持精确的RE-ID。基于多个数据集的大量实验结果包括CUHK03，Dukemtmc和Market-1501展示了我们对最先进的方法的方法的优越性。 （c）2020 Elsevier B.v.保留所有权利。

著录项

  • 来源
    《Neurocomputing》 |2020年第18期|124-133|共10页
  • 作者

    Shi Yuxuan; Ling Hefei; Wu Lei; Shen Jialie; Li Ping;

  • 作者单位

    Huazhong Univ Sci & Technol Dept Comp Sci & Technol Luoyu Rd 1037 Wuhan Peoples R China;

    Huazhong Univ Sci & Technol Dept Comp Sci & Technol Luoyu Rd 1037 Wuhan Peoples R China;

    Huazhong Univ Sci & Technol Dept Comp Sci & Technol Luoyu Rd 1037 Wuhan Peoples R China;

    Queens Univ Sch EEECS Comp Sci Bldg Belfast Antrim North Ireland;

    Huazhong Univ Sci & Technol Dept Comp Sci & Technol Luoyu Rd 1037 Wuhan Peoples R China;

  • 收录信息 美国《科学引文索引》(SCI);美国《工程索引》(EI);
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

    Person re-identification; Attribute-aligned; Attribute selection; Policy gradient;

    机译：人重新识别;属性对齐;属性选择;政策梯度;

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号