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

VL-HTR: Learning Human-Target Representation From Vision-Language Model.

IEEE transactions on cybernetics·2026
Same author

Acoustic shape-morphing micromachines.

Nature communications·2026
Same author

Towards a better understanding of brief lifestyle interventions in noncommunicable diseases: a concept analysis.

BMC public health·2025
Same author

End-to-end deep learning model for the diagnosis and segmentation of primary retroperitoneal neoplasm: a multicenter cohort study.

EClinicalMedicine·2025
Same author

Worldwide prevalence of discontinuation in fertility treatment: A systematic review and meta-analysis.

International journal of gynaecology and obstetrics: the official organ of the International Federation of Gynaecology and Obstetrics·2025
Same author

Comorbid Anxiety and Depression among Pregnant and Postpartum Women: A Longitudinal Population-Based Study.

Depression and anxiety·2025

相关实验视频

Updated: Jul 11, 2025

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis
05:41

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

Published on: February 6, 2020

9.4K

深度学习时代的时间动作定位:一项调查

Binglu Wang, Yongqiang Zhao, Le Yang

    IEEE transactions on pattern analysis and machine intelligence
    |November 6, 2023
    PubMed
    概括

    这项调查分析了用于智能视频理解的时间动作本地化方法. 它对监督和弱监督的方法进行了分类,提供了新的视角,并突出了信任估计的挑战.

    科学领域:

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

    背景情况:

    • 时间动作定位是智能视频理解的关键.
    • 深度学习骨干网络提取时间空间特征.
    • 监督和弱监督的学习推动了行动本地化方面的进展.

    研究的目的:

    • 提供现有的时间动作本地化工作的全面调查.
    • 建立当前策略的有组织的分类学.
    • 确定优势,弱点和未来的研究方向.

    主要方法:

    • 监督学习方法的分类,包括定机制和一种新的分类方法.
    • 通过增强策略扩展弱监督的学习机制 (预分类,后分类).
    • 分析信心估计作为一个关键的瓶.

    主要成果:

    • 一个结构化的分类,突出了各种动作本地化技术的优缺点.
    • 对监督和弱监督学习策略的新视角.
    • 确定信心估计作为一个未得到解决的挑战.

    结论:

    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

    564
    Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example
    08:45

    Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example

    Published on: October 24, 2012

    14.7K

    相关实验视频

    Last Updated: Jul 11, 2025

    A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis
    05:41

    A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

    Published on: February 6, 2020

    9.4K
    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

    564
    Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example
    08:45

    Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example

    Published on: October 24, 2012

    14.7K
  • 该调查为时间动作本地化研究人员提供了宝贵的资源.
  • 为新人提供指导,为经验丰富的研究人员提供灵感.
  • 强调需要对改善行动本地化模型的信心估计进行进一步研究.