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

Gender Recognition Based on Gradual and Ensemble Learning from Multi-View Gait Energy Images and Poses.

Sensors (Basel, Switzerland)·2023
Same author

Facial Micro-Expression Recognition Using Double-Stream 3D Convolutional Neural Network with Domain Adaptation.

Sensors (Basel, Switzerland)·2023
Same author

Deep Learning-Based Monocular 3D Object Detection with Refinement of Depth Information.

Sensors (Basel, Switzerland)·2022
Same author

Saliency Detection with Moving Camera via Background Model Completion.

Sensors (Basel, Switzerland)·2021
Same author

Shadow Detection in Still Road Images Using Chrominance Properties of Shadows and Spectral Power Distribution of the Illumination.

Sensors (Basel, Switzerland)·2020
Same journal

RETRACTED: Zhang et al. A Novel Framework for Reconstruction and Imaging of Target Scattering Centers via Wide-Angle Incidence in Radar Networks. <i>Sensors</i> 2025, <i>25</i>, 6802.

Sensors (Basel, Switzerland)·2026
Same journal

Enhancing Unsupervised Multi-Source Domain Adaptation for Person Re-Identification via Mixture of Experts and Graph-Based Relation.

Sensors (Basel, Switzerland)·2026
Same journal

Development of an Instrumented Glove for Palmar Pressure Assessment in Kayakers.

Sensors (Basel, Switzerland)·2026
Same journal

Development and Experimental Validation of an Autonomous IoT-Based Monitoring System for Real-Time Water Quality Assessment in the Amazon River.

Sensors (Basel, Switzerland)·2026
Same journal

Semi-Supervised Adversarial Learning Framework for Controller Area Network Bus Intrusion Detection.

Sensors (Basel, Switzerland)·2026
Same journal

Smart Optimization Method for Safety Signs in Innovative Manufacturing Environments Integrating Industrial Field IoT Sensors and Knowledge Graphs.

Sensors (Basel, Switzerland)·2026
查看所有相关文章

相关实验视频

Updated: Jun 23, 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

可变时间长度 行动识别培训 CNNs CNNs

Tan-Kun Li1, Kwok-Leung Chan1, Tardi Tjahjadi2

  • 1Department of Electrical Engineering, City University of Hong Kong, Hong Kong, China.

Sensors (Basel, Switzerland)
|June 19, 2024
PubMed
概括
此摘要是机器生成的。

深度学习模型与可变的视频长度作斗争. 用于3D-CNNs的可变长度训练 (VLT) 能够灵活处理具有不同时间维度的视频,从而提高动作识别性能.

关键词:
行动认可 行动认可深度学习是一种深度学习.代表性学习学习学习视频分类视频分类 视频分类

更多相关视频

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

2.7K
Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception
05:48

Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception

Published on: August 9, 2024

1.5K

相关实验视频

Last Updated: Jun 23, 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: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

2.7K
Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception
05:48

Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception

Published on: August 9, 2024

1.5K

科学领域:

  • 计算机视觉 计算机视觉
  • 深度学习 (Deep Learning) 是一种深度学习.
  • 人工智能的人工智能

背景情况:

  • 当前的深度学习模型,特别是计算机视觉模型,在输入形状方面具有有限的灵活性,通常需要固定尺寸以获得最佳性能.
  • 视频分析任务面临挑战,因为视频长度 (数) 固有的变化,需要采样技术,这可能会降低功能质量并阻碍适应性.
  • 标准的训练方法可能会损害更长的视频中的特征,并阻止模型灵活地适应可变长度以进行按需推断.

研究的目的:

  • 为3D卷积神经网络 (3D-CNNs) 提出一种新的训练范式,即可变长度训练 (VLT).
  • 为了使3D-CNN能够有效地处理具有可变时间长度的视频而不会降低性能.
  • 提高视频相关任务的深度学习模型的灵活性和适应性.

主要方法:

  • 引入了3D-CNNs的可变长度训练 (VLT),包括三个额外的训练操作:两次采样,时间包装和独立于子视频的3D卷积.
  • 将这些高效的操作集成到现有的3D-CNN架构中.
  • 实现一致性损失以规范表示空间,进一步增强模型的稳定性.

主要成果:

  • 拟议的VLT方法允许训练有素的模型在推断过程中处理不同时间长度的视频,而无需任何架构修改.
  • 在流行的动作识别数据集上的实验表明,与传统的训练范式相比,性能优越.
  • 该方法比其他用于可变长度视频处理的最先进的培训方法取得了更好的结果.

结论:

  • 可变长度培训 (VLT) 为深度学习模型提供了一个简单但有效的解决方案,用于处理可变长度的视频输入.
  • 该VLT范式增强了模型的灵活性,适应性和视频分析任务的性能,特别是动作识别.
  • 这种方法克服了视频处理当前深度学习模型中固定长度输入要求的局限性.