Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
Same author

Embodied cognition-driven interpretable trajectory prediction of autonomous systems.

Nature communications·2026
Same author

Recent progress in side-chain amino acid-based polymers: synthesis, self-assembly, and emerging biomedical applications.

Journal of materials chemistry. B·2026
Same author

Comparative Analysis of Microbial Community Structure and Functional Traits of Baijiu Daqu Across Diverse Geographical Regions in China.

Foods (Basel, Switzerland)·2026
Same author

Single-cell analyses identify the ginseng embryonic protoderm as a native compartment for high-efficiency ginsenoside production.

Nature communications·2026
Same author

Comparative analysis of goat milk flavor during different lactation and its interactions with fatty acids and nutrients.

Journal of dairy science·2026
Same author

Electronic metal-support interaction boosts electrochemiluminescence by improving the catalytic activity of palladium.

Chemical communications (Cambridge, England)·2026

相关实验视频

Updated: Jul 8, 2025

Topographical Estimation of Visual Population Receptive Fields by fMRI
06:02

Topographical Estimation of Visual Population Receptive Fields by fMRI

Published on: February 3, 2015

9.3K

深度排名一致的金字塔模型用于增强人群计数.

Jiaqi Gao, Zhizhong Huang, Yiming Lei

    IEEE transactions on neural networks and learning systems
    |December 13, 2023
    PubMed
    概括

    这项研究引入了一个深度排名一致的金字塔模型 (DREAM) 用于人群计数,有效地使用未标记的图像来提高准确性. 梦想利用特征空间中的排名一致性,减少了对广泛的手动注释的需求.

    科学领域:

    • 计算机视觉 计算机视觉
    • 机器学习 机器学习
    • 人工智能的人工智能

    背景情况:

    • 传统的人群计数依赖于完全监督的学习,需要广泛的像素级注释.
    • 标签是昂贵且耗时的,这促使人们使用没有标签的数据.
    • 没有标签的图像提供固有的结构信息,并为监督提供排名一致性.

    研究的目的:

    • 开发一种新的人群计数方法,有效地利用未标记的图像.
    • 在人群计数模型中减少对昂贵的像素级注释的依赖.
    • 通过利用潜在特征空间中的等级一致性来提高人群计数的准确性.

    主要方法:

    • 提出了深度等级一致的金字塔模型 (DREAM).
    • 在横跨粗细金字塔特征的潜伏特征空间中利用等级一致性.
    • 包含众多的金字塔部分顺序,以实现更强的模型表示.
    • 引入了一个新的未标记的人群计数数据集 (FUDAN-UCC),包含4000张图像.

    主要成果:

    • 证明了DREAM在基准数据集上的有效性 (UCF-QNRF,上海科技A/B部分,UCF-CC-50).
    • 与以前的半监督人群计数方法相比,实现了更好的性能.

    更多相关视频

    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
    03:31

    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

    Published on: December 15, 2023

    558
    Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations
    12:27

    Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

    Published on: February 15, 2017

    7.0K

    相关实验视频

    Last Updated: Jul 8, 2025

    Topographical Estimation of Visual Population Receptive Fields by fMRI
    06:02

    Topographical Estimation of Visual Population Receptive Fields by fMRI

    Published on: February 3, 2015

    9.3K
    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
    03:31

    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

    Published on: December 15, 2023

    558
    Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations
    12:27

    Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

    Published on: February 15, 2017

    7.0K
  • 显示使用更多的未标记样品.

    • 结论:

    • DREAM有效地利用了群众计数的潜在特征空间中的排名一致性.
    • 拟议的方法大大减少了对手册注释的需求.
    • DREAM提供了一种有希望的方法,用于使用大量未标记的数据进行人群计数.