Search research articles

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 Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

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

Analysis of the Current Status and Associated Factors of Premature Frailty in Adults Aged 18-59 Years Based on the NHANES Database.

Geriatrics & gerontology international·2026

Same author

Exploring barriers to the sustainable implementation of an evidence-based program for preventing deep vein thrombosis in patients with aneurysmal subarachnoid hemorrhage: a qualitative study using the Consolidated Framework for Implementation Research (CFIR).

BMC health services research·2026

Same author

Face Forgery Detection With CLIP-Enhanced Multi-Encoder Distillation.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2025

Same author

FA-Net: A Feature Alignment Network for Video-Based Visible-Infrared Person Re-Identification.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2025

Same author

VPT-NSP<sup>2</sup>++: Importance-Aware Visual Prompt Tuning in Null Space for Continual Learning.

IEEE transactions on pattern analysis and machine intelligence·2025

Same author

Missing links in nanomaterials research impacting productivity and perceptions.

Beilstein journal of nanotechnology·2025

Same journal

A boundary-regularization-enhanced video anomaly detection network based on context-adaptive spatio-temporal conditional diffusion.

Neural networks : the official journal of the International Neural Network Society·2026

Same journal

MT<sup>2</sup>-CSD and LLM-CRAN: A new dataset and an LLM-based multi-semantic knowledge fusion model for conversational stance detection.

Neural networks : the official journal of the International Neural Network Society·2026

Same journal

TriAlignNet: A triple-path cross-modality alignment framework for multimodal time series forecasting.

Neural networks : the official journal of the International Neural Network Society·2026

Same journal

Anchor-based disentanglement framework for incremental multi-view clustering.

Neural networks : the official journal of the International Neural Network Society·2026

Same journal

Complex-valued amplitude-phase interference modeling for adversarially robust classification.

Neural networks : the official journal of the International Neural Network Society·2026

Same journal

TraNce: Type-aware hypergraph neural network with biological mediators for drug repositioning.

Neural networks : the official journal of the International Neural Network Society·2026

查看所有相关文章

Search research articles

相关实验视频

Updated: Sep 10, 2025

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities

Published on: October 27, 2023

对称的双向知识对齐用于基于零拍摄草图的图像检索.

Decheng Liu¹, Xu Luo¹, Chunlei Peng¹

¹State Key Laboratory of Integrated Services Networks, School of Cyber Engineering, Xidian University, Xi'an, 710071, Shaanxi, PR China.

Neural networks : the official journal of the International Neural Network Society

|August 19, 2025

概括

此摘要是机器生成的。

本研究引入了对称双向知识对齐 (SBKA),通过对模型之间的知识进行对齐来改进基于零拍摄草图的图像检索 (ZS-SBIR). 这种方法增强了跨模式匹配,以便在未见的类别中更好地泛化.

关键词:

跨模式性跨模式性图像检索图像检索图像检索知识对等化知识对等化零射击学习的学习.

更多相关视频

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization

Published on: February 23, 2024

相关实验视频

Last Updated: Sep 10, 2025

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities

Published on: October 27, 2023

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization

Published on: February 23, 2024

科学领域:

计算机科学计算机科学
人工智能的人工智能
机器学习机器学习

背景情况:

基于零拍摄草图的图像检索 (ZS-SBIR) 面临着挑战,原因是显著的交叉模式差异.
现有的方法往往缺乏教师和学生模型之间的有效的双向知识对齐,限制了概括.

研究的目的:

为 ZS-SBIR 提出一个新的对称双向知识对齐 (SBKA) 框架.
通过有效地调整教师和学生模型之间的知识来提高ZS-SBIR模型的通用性.

主要方法:

开发了一个对称的双向知识对齐学习框架 (SBKA).
实施一对多集群跨模式匹配方法,以利用类内关系和减轻模式差距.

主要成果:

拟议的SBKA算法在代表性的ZS-SBIR数据集 (Sketchy Ext,TU-Berlin Ext,QuickDraw Ext) 上取得了卓越的性能.
在减少 ZS-SBIR 任务中模式差距的不利影响方面表现出有效性.

结论:

SBKA框架有效地学习相互歧视的信息,以改善知识对齐.
新的匹配策略提高了ZS-SBIR的性能,超过了最先进的方法.