首页> 外文期刊>Knowledge-Based Systems >A multi-context representation approach with multi-task learning for object counting
【24h】

A multi-context representation approach with multi-task learning for object counting

机译:对对象计数的多任务学习的多上下文表示方法

获取原文
获取原文并翻译 | 示例
       

摘要

Object counting is a fundamental while challenging computer vision task, as it requires the object appearance information as well as semantic understanding of the object. In this paper, we propose an end-to-end multi-context embedding deep network for object counting(MCENet), which observes the object counting task from the three different perspectives to count the number of vehicles in the traffic video frame, or to estimate the number of the pedestrian in the largely congested scene. The first sub-network of MCENet extracts the potential features for the appearance context and the semantic context from different-level layers. The two different-level features from the first sub-network are transferred into the two parallel and complementary sub-networks, which are used to model the appearance context and semantic context for final counting. And thus the multiple contexts are represented and embedded to assist the counting task. Extensive experimental evaluations are reported in this paper, using up to three different object counting benchmarks, which show the proposed approach achieves a competitive performance in all these heterogeneous scenarios. (C) 2020 Elsevier B.V. All rights reserved.
机译:对象计数是一个基本的计算机视觉任务,因为它需要对象外观信息以及对象的语义理解。在本文中,我们提出了一个端到端的多上下文嵌入对象计数的深网络(MCenet),其观察到三种不同的观点的对象计数任务,以计算交通视频帧中的车辆数量,或者估计在很大的拥挤场景中的行人的数量。 Mcenet的第一子网络提取出外观上下文的潜在特征和来自不同级别的层的语义上下文。来自第一子网络的两个不同级别的特征被传送到两个并行和互补的子网中,用于模拟最终计数的外观上下文和语义上下文。因此,表示和嵌入多个上下文以帮助计数任务。本文报告了广泛的实验评估,使用最多三个不同的对象计数基准,显示了所提出的方法在所有这些异构情景中实现了竞争性能。 (c)2020 Elsevier B.v.保留所有权利。

著录项

  • 来源
    《Knowledge-Based Systems》 |2020年第7期|105927.1-105927.10|共10页
  • 作者单位

    Yanshan Univ Sch Informat Sci & Engn Qinhuangdao 066004 Hebei Peoples R China|Key Lab Comp Virtual Technol & Syst Integrat Hebe Qinhuangdao 066004 Hebei Peoples R China;

    Yanshan Univ Sch Informat Sci & Engn Qinhuangdao 066004 Hebei Peoples R China;

    Yanshan Univ Sch Informat Sci & Engn Qinhuangdao 066004 Hebei Peoples R China;

    Yanshan Univ Sch Informat Sci & Engn Qinhuangdao 066004 Hebei Peoples R China;

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

    Object counting; Multi-task learning; Multi-context representation; Appearance context; Multi-scale semantic;

    机译:对象计数;多任务学习;多语境表示;外观上下文;多尺度语义;
  • 入库时间 2022-08-18 21:28:49

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