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

Focusing of Light in the Eye01:16

Focusing of Light in the Eye

2.7K
Light rays enter the eye through the cornea, a transparent dome-shaped tissue that is the eye's outermost layer. The cornea bends or refracts, light rays traveling to the pupil. The shape of the cornea determines how much of the light is bent and whether the image will be focused correctly on the retina at the back of the eye. Once the light has passed through both refraction layers, it converges into a single focal point onto a small area. This is where photoreceptors start transforming...
2.7K

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

Inhibiting ADAR1-Mediated Excessive Epigenetic A-to-I RNA Editing Improves the Immune Microenvironment and Increases Sensitivity to Immunotherapy in Lung Adenocarcinoma.

MedComm·2026
Same author

IL-6 drives chemoimmunotherapy resistance in NSCLC by reprogramming myeloid cells and impairing cytotoxic lymphocyte function.

Cancer letters·2026
Same author

Genistein supplementation modulates the intestinal microbiota-liver-lumbar muscle metabolic axis in DLY commercial pigs without concomitant changes in growth performance.

Frontiers in microbiology·2025
Same author

Tumor-secreted AGR2 induces dendritic cell dysfunction and impairs immunotherapy efficacy in LKB1-deficient cancer.

Journal for immunotherapy of cancer·2025
Same author

FTA2C: Achieving superior trade-off between accuracy and robustness in adversarial training.

Neural networks : the official journal of the International Neural Network Society·2025
Same author

Transcription Factor LjWRKY50 Affects Jasmonate-Regulated Floral Bud Duration in <i>Lonicera japonica</i>.

Plants (Basel, Switzerland)·2025

相关实验视频

Updated: Jun 27, 2025

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

7.6K

蒙蔽和模糊多对象跟踪器与对抗性干扰.

Haibo Pang1, Rongqi Ma1, Jie Su1

  • 1School of Cyber Science and Engineering, Zhengzhou University, Zhengzhou City, 450003, China.

Neural networks : the official journal of the International Neural Network Society
|May 3, 2024
PubMed
概括

一个新的盲目模糊攻击 (BBA) 通过利用运动信息来愚弄深度多对象追踪器. 这种新型的对抗性攻击显著降低了追踪器的性能,证明了在不同算法中具有很高的可转移性.

关键词:
敌对的攻击是敌对的攻击.计算机视觉 计算机视觉 计算机视觉多对象跟踪多对象跟踪对象检测检测对象检测对象检测

更多相关视频

Author Spotlight: Deciphering Electrical Networks Behind Complex Brain Activities and Disorders
05:49

Author Spotlight: Deciphering Electrical Networks Behind Complex Brain Activities and Disorders

Published on: November 1, 2024

774
Assessing Binocular Central Visual Field and Binocular Eye Movements in a Dichoptic Viewing Condition
07:45

Assessing Binocular Central Visual Field and Binocular Eye Movements in a Dichoptic Viewing Condition

Published on: July 21, 2020

4.4K

相关实验视频

Last Updated: Jun 27, 2025

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

7.6K
Author Spotlight: Deciphering Electrical Networks Behind Complex Brain Activities and Disorders
05:49

Author Spotlight: Deciphering Electrical Networks Behind Complex Brain Activities and Disorders

Published on: November 1, 2024

774
Assessing Binocular Central Visual Field and Binocular Eye Movements in a Dichoptic Viewing Condition
07:45

Assessing Binocular Central Visual Field and Binocular Eye Movements in a Dichoptic Viewing Condition

Published on: July 21, 2020

4.4K

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.
  • 敌对的机器学习

背景情况:

  • 深度多对象追踪器整合了检测和关联,使它们易受敌对攻击的影响.
  • 现有的攻击主要增加了ID切换,不足以降低追踪器性能.
  • 不易察觉的干扰可以欺骗深度学习模型,包括对象追踪器.

研究的目的:

  • 提出一种新的对抗性攻击方法,盲目模糊攻击 (BBA),以有效地欺骗多对象追踪器.
  • 探索时空运动信息在制造敌对攻击方面的潜力.
  • 评估攻击的有效性和可转移性在最先进的多对象跟踪算法.

主要方法:

  • 开发了一种新的盲目模糊攻击 (BBA),利用时空运动信息.
  • 采用了一个训练有素的扰动发生器,具有盲模损失函数.
  • 在TraDeS,CenterTrack,FairMOT和ByteTrack上使用MOT-Challenge数据集 (MOT16,MOT17,MOT20) 评估了BBA.

主要成果:

  • BBA成功地使目标对追踪器看不见,同时导致背景元素被视为移动目标.
  • 这次攻击大大降低了TraDeS和ByteTrack的MOTA (多个对象跟踪精度).
  • 证明了BBA方法在各种最先进的跟踪算法中具有很高的可转移性.

结论:

  • 拟议的盲模攻击 (BBA) 是降低多对象跟踪器性能的一种有效方法.
  • 时空运动信息为开发复杂的对抗性攻击提供了强有力的途径.
  • BBA强调了当前深度多对象跟踪系统的重大漏洞.