节点文献

用于行人重识别的多类型特征网络

Multi-type Features Network for Person Re-identification

  • 推荐 CAJ下载
  • PDF下载
  • 不支持迅雷等下载工具,请取消加速工具后下载。

【作者】 王鹏宋晓宁吴小俊於东军

【Author】 WANG Peng;SONG Xiaoning;WU Xiaojun;YU Dongjun;School of Artificial Intelligence and Computer Science,Jiangnan University;School of Computer Science and Engineering,Nanjing University of Science and Technology;

【通讯作者】 宋晓宁;

【机构】 江南大学人工智能与计算机学院南京理工大学计算机科学与工程学院

【摘要】 近年来,注意机制在行人重识别任务中效果较优,但是不同类型的注意机制(如空间注意、自注意等)联合使用的效果仍然有待提高.因此,文中首先提出改进型的卷积块注意模型(CBAM-Pro),再提出多类型特征网络模型.对CBAM-Pro与自注意机制的集成提取不同关注域的特征,同时引入不同划分粒度的局部特征,联合进行行人重识别.在现有的通用基准数据集上的实验验证文中模型的有效性与可靠性.

【Abstract】 The attention mechanism is effective in person re-identification. However, the performance of the combined use of different types of attention mechanisms needs to be improved, such as spatial attention and self-attention. An improved convolutional block attention model(CBAM-PRO) is proposed, and then a multi-type features network(MTFN) is proposed. The features of different interested domains are extracted through the integration of CBAM-Pro and self-attention mechanism, and the local features with different granularities are introduced concurrently to perform person re-identification jointly. The validity and reliability of MTFN are verified by the experiments on the existing general benchmark datasets.

【基金】 国家重点研发计划项目(No.2017YFC1601800);国家自然科学基金项目(No.61876072);中国博士后科学基金特助项目(No.2018T110441);江苏省“六大人才高峰项目”(No.XYDXX-012)资助~~
  • 【文献出处】 模式识别与人工智能 ,Pattern Recognition and Artificial Intelligence , 编辑部邮箱 ,2020年10期
  • 【分类号】TP391.41;TP183
  • 【被引频次】4
  • 【下载频次】228
节点文献中: 

本文链接的文献网络图示:

本文的引文网络