...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Multimedia Tools and Applications >Non-full multi-layer feature representations for person re-identification
【24h】

Non-full multi-layer feature representations for person re-identification

机译：用于人员重新识别的非全层特征表示

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

Person re-identification(Re-ID) has attracted increasing attention in the field of computer vision due to its great significance for the potential real-world applications. Profited from the success of convolutional neural networks(CNNs), existing multi-layer approaches leverage different scales of convolutional layers to learn more discriminative features, improving the Re-ID performance to some extent. However, these methods do not further explore whether all the scales of convolutional layers are positive for person re-identification. In this work, we propose a novel non-full multi-layer(NFML) network, which can jointly learn discriminative feature embeddings from positive multiple layers with the manner of combining global and local cues. Moreover, considering few works focus on how to effectively handle the feature maps, a simple yet effective feature progressing module named Pooling Batch Normalization(PBN), consisting of pooling, reduction and batch normalization operations, is introduced to optimize the model structure and further improve the Re-ID performance. Results on three mainstream benchmark datasets Market-1501, DukeMTMC-reID and CUHK03 demonstrate that our method can significantly boost the performances, outperforming the state-of-the-art methods.
机译：由于对潜在的现实世界应用的重要意义，人员重新识别（RE-ID）引起了计算机视野中的越来越关注。利用卷积神经网络（CNNS）的成功，现有的多层方法利用不同的卷积层尺度来了解更多辨别特征，在某种程度上提高重新ID性能。然而，这些方法不进一步探索卷积层的所有尺度是否是人重新识别的阳性。在这项工作中，我们提出了一种新颖的非全层（NFML）网络，其可以共同学习来自正多层的鉴别特征嵌入，以与全球和本地提示组合的方式。此外，考虑到少数作品侧重于如何有效处理特征映射，引入了一个名为池批量标准化（PBN）的简单且有效的特征进展模块，包括池，减少和批量归一化操作，以优化模型结构并进一步改进重新ID性能。结果三个主流基准数据集市场-1501，Dukemtmc-Reid和Cuhk03表明，我们的方法可以显着提高性能，优于最先进的方法。

著录项

  • 来源
    《Multimedia Tools and Applications》 |2021年第11期|17205-17221|共17页
  • 作者

    Wang Jianchen; Zhang Jianguang; Wen Xianbin;

  • 作者单位

    Tianjin Univ Technol Key Lab Comp Vis & Syst Minist Educ Tianjin 300384 Peoples R China|Tianjin Univ Technol Sch Comp Sci & Engn Tianjin 300384 Peoples R China;

    Hengshui Univ Coll Math & Comp Sci Hengshui 053000 Hebei Peoples R China|Shenzhen Univ Coll Comp Sci & Software Engn Shenzhen 518000 Guangdong Peoples R China;

    Tianjin Univ Technol Key Lab Comp Vis & Syst Minist Educ Tianjin 300384 Peoples R China|Tianjin Univ Technol Sch Comp Sci & Engn Tianjin 300384 Peoples R China;

  • 收录信息
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

    Person re-identification; Multi-layer; Multi-task learning; Pooling strategy;

    机译：人重新识别;多层;多任务学习;汇集策略;

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