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

Depth Perception and Spatial Vision01:15

Depth Perception and Spatial Vision

510
Depth perception is the ability to perceive objects three-dimensionally. It relies on two types of cues: binocular and monocular. Binocular cues depend on the combination of images from both eyes and how the eyes work together. Since the eyes are in slightly different positions, each eye captures a slightly different image. This disparity between images, known as binocular disparity, helps the brain interpret depth. When the brain compares these images, it determines the distance to an object.
510
Visual System01:26

Visual System

476
Light enters the eye through the cornea, a transparent, dome-shaped surface covering the surface of the eyeball that helps to direct and focus incoming light. This light is then channeled toward the pupil, an adjustable opening whose size is controlled by the iris. The iris, a pigmented muscle, regulates the amount of light entering the eye by contracting or dilating the pupil, thereby ensuring optimal light levels for clear vision.
Once through the pupil, the light passes through the lens, a...
476
Vision01:24

Vision

52.9K
Vision is the result of light being detected and transduced into neural signals by the retina of the eye. This information is then further analyzed and interpreted by the brain. First, light enters the front of the eye and is focused by the cornea and lens onto the retina—a thin sheet of neural tissue lining the back of the eye. Because of refraction through the convex lens of the eye, images are projected onto the retina upside-down and reversed.
52.9K

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

People use fast and flat simulation to reason about new games.

Nature·2026
Same author

Evidence from formal logical reasoning reveals that the language of thought is not natural language.

Proceedings of the National Academy of Sciences of the United States of America·2026
Same author

Music-selective cortex is sensitive to structure in both pitch and time.

Cerebral cortex (New York, N.Y. : 1991)·2026
Same author

Perceived authenticity drives gaze behavior when watching AI-generated videos of physical scenes.

Scientific reports·2026
Same author

Conniving With Continuations: Representing Goals in a Domain-Specific Language of Thought.

Topics in cognitive science·2026
Same author

Neural representation of action symbols in primate frontal cortex.

Nature·2026

相关实验视频

Updated: May 25, 2025

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction
06:19

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Published on: August 16, 2024

360

通过深度神经网络接近人类水平的3D视觉推理.

Thomas P O'Connell1, Tyler Bonnen2, Yoni Friedman1

  • 1Brain & Cognitive Sciences, MIT, Cambridge, MA, USA.

Open mind : discoveries in cognitive science
|February 27, 2025
PubMed
概括

与人类相比,深度神经网络 (DNN) 与3D形状推断作斗争. 多视图学习目标有助于DNN,但实现类似人类的3D形状感知仍然是一个挑战,特别是对于新的对象.

关键词:
3D形状感知 3D形状感知深度神经网络是一个神经网络.神经领域的神经领域.心理物理学的心理物理学.

更多相关视频

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
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

相关实验视频

Last Updated: May 25, 2025

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction
06:19

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Published on: August 16, 2024

360
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
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

科学领域:

  • 计算机视觉 计算机视觉
  • 认知科学 认知科学
  • 人工智能的人工智能

背景情况:

  • 人类擅长推断3D视觉世界几何.
  • 深度神经网络 (DNN) 在3D形状推断任务中经常失败,尽管在其他领域的人类水平的性能.
  • 在3D形状表示中,DNN与人类感知之间存在差距.

研究的目的:

  • 调查DNN与人类之间的3D形状表示的差距是否以及如何可以被缩小.
  • 评估各种DNN架构的3D形状推断能力.
  • 在3D形状匹配任务中识别影响DNN性能的因素.

主要方法:

  • 创建了一个用于匹配样本任务的刺激集,以评估3D形状推断.
  • 使用单视图和多视图学习目标构建和训练3D意识的DNN (光场网络,自动编码器,卷积).
  • 评估模型性能与3D形状匹配和一般化到分布之外的类别上的人类性能.

主要成果:

  • 标准DNN在3D形状推断中未能达到人类的性能.
  • 当训练和测试对象类别匹配时,多视图DNN接近人类水平的性能.
  • 3D光场网络显示了与人类表现的最高相似性,这表明3D诱导偏差的好处.
  • 多视图学习是必要的,但不足以实现类似人类的3D形状推断.

结论:

  • 多视图学习目标对于提高DNN的3D形状推断能力至关重要.
  • 结合3D诱导偏差,如在光场网络中,增强了人类模型对齐.
  • 在捕获类似人类的3D形状推断和将其推广到新的对象类别方面,DNN仍然面临局限性.