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

Color Vision01:24

Color Vision

457
Color perception begins in the retina, the light-sensitive layer at the back of the eye. Two main theories explain how colors are seen: the trichromatic theory and the opponent-process theory. The trichromatic theory, proposed by Thomas Young in 1802 and extended by Hermann von Helmholtz in 1852, suggests that color vision is based on three types of cone receptors in the retina. These cones are sensitive to different but overlapping ranges of wavelengths corresponding to red, blue, and green.
457

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

Activation of sigma non-opioid intracellular receptor 1 (S1R) receptor inhibits plexin domain containing 2 (Plxdc2) driven microglial inflammation to ameliorate depressive-like behaviours in mice.

British journal of pharmacology·2026
Same author

[Effect of GLP-1 on MNCs activity in hypothalamic paraventricular nucleus <i>in vitro</i> in rats].

Sheng li xue bao : [Acta physiologica Sinica]·2026
Same author

In-Plane Conductivity as a Descriptor of Apparent Durability of RuO<sub>2</sub> Anodes in PEM Water Electrolysis.

Nano letters·2026
Same author

Preliminary insights into the release behavior of dissolved organic matter from aged microplastics in seawater: Effects of aging types.

Marine environmental research·2026
Same author

Targeting Neuroinflammation in Depression: The Integrative Role of Sigma-1 Receptor Modulation.

Journal of neurochemistry·2026
Same author

Photocatalyzed oxidative cleavage of alkenes using CO<sub>2</sub> as an oxygen donor.

Science (New York, N.Y.)·2026

相关实验视频

Updated: May 28, 2025

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

455

生物启发的双阶段网络,用于高效的RGB-D突出物体检测.

Peng Ren1, Tian Bai1, Fuming Sun2

  • 1College of Computer Science and Technology, Jilin University, Changchun 130012, China; Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, 130012, China.

Neural networks : the official journal of the International Neural Network Society
|February 11, 2025
PubMed
概括

这项研究介绍了BTNet,一种由灵长类动物视觉路径启发的新型高效RGB-D突出物体检测 (SOD) 模型. 通过显著降低参数和高处理速度,BTNet实现了卓越的性能.

关键词:
生物视觉系统是生物视觉系统.一个高效的网络网络.RGB-D突出物体检测显着物体检测

更多相关视频

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

8.9K
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

9.3K

相关实验视频

Last Updated: May 28, 2025

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

455
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

8.9K
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

9.3K

科学领域:

  • 计算机视觉 计算机视觉
  • 人工智能的人工智能
  • 生物医学工程 生物医学工程

背景情况:

  • 卷积神经网络 (CNN) 和视觉转换器已经提升了RGB-D突出物体检测 (SOD) 的精度.
  • 现有的SOD模型往往难以平衡计算效率与高性能.

研究的目的:

  • 提出一个高效的RGB-D SOD模型,BTNet,灵感来自灵长类动物生物视觉系统的P和M视觉通路.
  • 为了提高RGB-DSOD中的计算效率和检测精度之间的平衡.

主要方法:

  • 开发了BTNet,这是一个双阶段网络,模拟M视觉路径用于粗粒区锁定和P视觉路径用于细粒物体改进.
  • 利用灵长类动物视觉处理的洞察力来实现不同阶段的功能.

主要成果:

  • 与最先进的方法相比,BTNet在六个基准数据集中表现出卓越的表现.
  • 实现了显著的参数减少 (93.6%低于CPNet) 和高处理速度 (175.4 FPS对于384x384图像).
  • BTNet的速度是最先进的CPNet方法的近7.2倍.

结论:

  • BTNet为RGB-D突出物体检测提供了一种高效和高性能解决方案.
  • 生物灵感设计有效平衡计算成本和准确性,优于现有模型.
  • 拟议的方法在有效的视觉注意力建模方面取得了重大进展.