• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops >Vehicle Re-identification with the Space-Time Prior
【24h】

Vehicle Re-identification with the Space-Time Prior

机译：车辆重新识别现时

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Vehicle re-identification (Re-ID) is fundamentally challenging due to the difficulties in data labeling, visual domain mismatch between datasets and diverse appearance of the same vehicle. We propose the adaptive feature learning technique based on the space-time prior to address these issues. The idea is demonstrated effectively in both the human Re-ID and the vehicle Re-ID tasks. We train a vehicle feature extractor in a multi-task learning manner on three existing vehicle datasets and fine-tune the feature extractor with the adaptive feature learning technique on the target domain. We then develop a vehicle Re-ID system based on the learned vehicle feature extractor. Finally, our meticulous system design leads to the second place in the 2018 NVIDIA AI City Challenge Track 3.
机译：由于数据标签的困难，数据集之间的视域不匹配和同一车辆的多样化外观，车辆重新识别（RE-ID）基本上挑战。我们提出了基于解决这些问题之前的空间时间的自适应特征学习技术。这些想法在人类重新ID和车辆重新ID任务中有效地说明。我们在三个现有的车辆数据集中以多任务学习方式培训车辆功能提取器，并在目标域上微调具有自适应特征学习技术的特征提取器。然后，我们基于学习的车辆特征提取器开发车辆RE-ID系统。最后，我们一丝不苟的系统设计导致2018年NVIDIA AI City挑战3的第二名。

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