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

Conservation of Mass in Moving, Nondeforming Control Volume01:14

Conservation of Mass in Moving, Nondeforming Control Volume

1.1K
Stormwater detention basins are essential in managing runoff during heavy rainfall, particularly in urban areas where impervious surfaces increase the risk of flooding. Understanding the conservation of mass in these systems allows engineers to optimize basin performance, balancing inflow, outflow, and water storage.
In the context of a detention basin, the conservation of mass states that the total mass of water entering the basin must equal the mass leaving the basin plus any accumulation of...
1.1K

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

Digital Twin of Coal Mine Rescue Robot-Research on Intelligence and Visualization.

Sensors (Basel, Switzerland)·2026
Same author

Pathways to Wellbeing: Reconceptualizing Resilience to Foreground Marginalized Teachers' Agentic Resistance.

Behavioral sciences (Basel, Switzerland)·2025
Same author

The Controllability of <i>Caenorhabditis elegans</i> Neural Network from Larva to Adult.

Biomimetics (Basel, Switzerland)·2025
Same author

Towards Biologically-Inspired Visual SLAM in Dynamic Environments: IPL-SLAM with Instance Segmentation and Point-Line Feature Fusion.

Biomimetics (Basel, Switzerland)·2025
Same author

Development of a machine learning-based predictive model for intraoperative hypothermia risk during radical surgery for oral cancer.

American journal of translational research·2025
Same author

Dietary supplementation of arachidonic acid promotes humoral immunity.

EMBO molecular medicine·2025

相关实验视频

Updated: May 2, 2026

Measuring Attention and Visual Processing Speed by Model-based Analysis of Temporal-order Judgments
13:00

Measuring Attention and Visual Processing Speed by Model-based Analysis of Temporal-order Judgments

Published on: January 23, 2017

9.8K

视频序列的时空冗余减少:基于运动的透驱动的注意力方法.

Ye Yuan1, Baolei Wu1, Zifan Mo2

  • 1Institute of Machine Intelligence, University of Shanghai for Science and Technology, Shanghai 200093, China.

Biomimetics (Basel, Switzerland)
|April 25, 2025
PubMed
概括

本研究介绍了引运动增强采样 (EGMESampler),这是一种新的采样方法,可以有效地减少冗余的视频数据. EGMESampler通过根据运动信息自适应地选择来提高视频理解中的计算资源利用率.

关键词:
人类视觉灵感的人类视觉灵感关键框架抽样采集运动增强器 运动增强器运动建模运动建模时间空间信息 (entropy)

更多相关视频

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

8.9K
A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers
12:39

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

Published on: January 18, 2020

7.5K

相关实验视频

Last Updated: May 2, 2026

Measuring Attention and Visual Processing Speed by Model-based Analysis of Temporal-order Judgments
13:00

Measuring Attention and Visual Processing Speed by Model-based Analysis of Temporal-order Judgments

Published on: January 23, 2017

9.8K
Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

8.9K
A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers
12:39

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

Published on: January 18, 2020

7.5K

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:

  • 冗余的视频在视频理解任务中浪费计算资源.
  • 目前的框架采样方法对于不同的行动类别缺乏灵活性.
  • 需要适应性框架选择以提高效率.

研究的目的:

  • 提出一种有效和可解释的框架采样方法,EGMESampler,灵感来自人类视觉路径.
  • 为了更好地利用资源,在视频中删除冗余的时空信息.
  • 为了增强运动表达和减少采样中的背景噪音.

主要方法:

  • 运动建模用于从无关背景中提取运动信息.
  • 基于的动态采样策略,利用运动信息.
  • 注意操作以增强运动表达和消除空间背景冗余.

主要成果:

  • EGMESampler有效地删除了冗余的时空信息.
  • 与固定采样策略相比,该方法显示出有效性.
  • 在五个基准数据集上的实验显示了跨模型和数据集的概括性.

结论:

  • EGMESampler提供了一个适应性和高效的解决方案,用于视频采样.
  • 该方法可以集成到现有的视频处理算法中.
  • 它在视频理解任务中显著提高了资源利用率.