首页> 外文期刊>IEEE Transactions on Image Processing >CDPM: Convolutional Deformable Part Models for Semantically Aligned Person Re-Identification
【24h】

CDPM: Convolutional Deformable Part Models for Semantically Aligned Person Re-Identification

机译:CDPM:用于语义对齐人的卷积可变形部件模型重新识别

获取原文
获取原文并翻译 | 示例

摘要

Part-level representations are essential for robust person re-identification. However, common errors that arise during pedestrian detection frequently result in severe misalignment problems for body parts, which degrade the quality of part representations. Accordingly, to deal with this problem, we propose a novel model named Convolutional Deformable Part Models (CDPM). CDPM works by decoupling the complex part alignment procedure into two easier steps: first, a vertical alignment step detects each body part in the vertical direction, with the help of a multi-task learning model; second, a horizontal refinement step based on attention suppresses the background information around each detected body part. Since these two steps are performed orthogonally and sequentially, the difficulty of part alignment is significantly reduced. In the testing stage, CDPM is able to accurately align flexible body parts without any need for outside information. Extensive experimental results demonstrate the effectiveness of the proposed CDPM for part alignment. Most impressively, CDPM achieves state-of-the-art performance on three large-scale datasets: Market-1501, DukeMTMC-ReID, and CUHK03.
机译:部分级别表示对于强大的人重新识别至关重要。然而,在行人检测期间出现的常见错误经常导致身体部位的严重未对准问题,这降低了部分表示的质量。因此,要解决这个问题,我们提出了一种名为卷积可变形部分模型(CDPM)的小说模型。 CDPM通过将复杂部分对齐过程解耦为两个更轻松的步骤:首先,在多任务学习模型的帮助下,垂直对准步骤在垂直方向上检测每个主体部分;其次,基于注意力的水平细化步骤抑制了每个检测到的身体部位周围的背景信息。由于这两个步骤正交和顺序地进行,因此部分对准的难度显着降低。在测试阶段,CDPM能够在无需外部信息的情况下准确地对准灵活的身体部位。广泛的实验结果证明了所提出的CDPM用于部分对准的有效性。最令人印象深刻地,CDPM在三个大型数据集上实现最先进的性能:Market-1501,Dukemtmc-Reid和Cuhk03。

著录项

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