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

Integrative omics reveals IbADT6 involvement in chlorogenic acid accumulation and stress tolerance in sweet potato.

Plant physiology and biochemistry : PPB·2026
Same author

Dual contextual learning for semi-supervised medical image classification.

Frontiers in medicine·2026
Same author

Effects of Halliwick-based aquatic exercise on social and motor skills of children with autism spectrum disorder: a pilot study.

Frontiers in psychology·2026
Same author

Ubiquitin-dependent mitochondrial protein degradation ensures seedling emergence by regulating ER-mitochondrial interaction and mitophagy.

Nature plants·2026
Same author

Secondary signs combined with renal pelvis urine density on preoperative CT as a predictor of infection following ureteroscopic lithotripsy with chronic kidney disease.

Polish journal of radiology·2026
Same author

Disc collapse aggravates vertebral recollapse following percutaneous kyphoplasty: a clinical review and biomechanical study.

Quantitative imaging in medicine and surgery·2026
Same journal

Granular Ball-Based Noise-Resistant Fuzzy Multineighborhood Feature Selection via Label Enhancement and Feature Graph.

IEEE transactions on neural networks and learning systems·2026
Same journal

Fighting Evolving Spam With ARTMAP Models: A Noise-Resilient Online Detection Framework.

IEEE transactions on neural networks and learning systems·2026
Same journal

HyperSAT: Unsupervised Hypergraph Neural Networks for Weighted MaxSAT Problems.

IEEE transactions on neural networks and learning systems·2026
Same journal

Negation of Basic Belief Assignment in Multisource Information Fusion on Dempster-Shafer Theory With Applications in Pattern Classification.

IEEE transactions on neural networks and learning systems·2026
Same journal

Intervention Feasible Region and Driver Risk Capacity Aware Human-Machine Collaborative Safe Trajectory Planning.

IEEE transactions on neural networks and learning systems·2026
Same journal

A Unified Differential Denoising Learning Framework With a Pre-Trained Model and Fuzzy Graph Networks for Drug-Drug Interaction Prediction.

IEEE transactions on neural networks and learning systems·2026
查看所有相关文章

相关实验视频

Updated: Sep 8, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

491

针对未对齐的RGB-T语义细分的变形弹性多细分学习.

Heng Zhou, Zhenxi Zhang, Chengyang Li

    IEEE transactions on neural networks and learning systems
    |July 8, 2025
    PubMed
    概括
    此摘要是机器生成的。

    本研究引入了一个新的基准和方法,用于非对齐的RGB-Thermal语义细分,通过对齐跨模式的特征来提高对象面具的准确性. 抗变形多粒度学习 (DML) 方法有效地处理不对齐的图像对.

    更多相关视频

    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

    633
    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
    04:48

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

    Published on: November 30, 2022

    2.9K

    相关实验视频

    Last Updated: Sep 8, 2025

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    491
    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

    633
    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
    04:48

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

    Published on: November 30, 2022

    2.9K

    科学领域:

    • 计算机视觉 计算机视觉
    • 机器学习 机器学习
    • 图像处理 图像处理

    背景情况:

    • 语义细分 (SS) 通常需要对齐的RGB-热 (RGB-T) 图像对.
    • 现实世界的RGB-T数据往往不对齐,对现有的SS方法构成重大挑战.
    • 不对齐的RGB-T图像的像素级对齐是计算密集和困难的.

    研究的目的:

    • 为了解决语义细分中未对齐的RGB-T图像对的挑战.
    • 引入一个新的基准数据集,用于非对齐的RGB-TSS.
    • 为强大的RGB-T SS.提出一种抗变形多颗粒度学习 (DML) 方法.

    主要方法:

    • 开发了一个新的非对齐的RGB-T SS基准数据集.
    • 提出了对变形弹性多粒度学习 (DML) 方法.
    • 引入了一个变形感知互补特征增强器 (DCFE) 与变形感知特征对齐 (DFA) 和互补特征聚合 (CFA) 模块.
    • 设计了一个多颗粒度面具精制引擎 (MMFE),结合了无类突出性预测 (CSP) 和类意识边缘生成 (CEG).

    主要成果:

    • DML方法有效地将多式联运特征与粗到细的策略对齐,减轻扭曲方式的干扰.
    • DFA估计了变形场,以改善空间对齐,而CFA则汇总了跨尺度的互补上下文信息.
    • MMFE增强了语义对齐和类间的分离性,产生了具有清晰边界的对象口罩.
    • 实验表明,与现有方法相比,在对齐和不对齐的数据集上,DML的性能优越.

    结论:

    • 拟议的DML方法为使用非对齐的RGB-T图像对进行语义细分提供了强大的解决方案.
    • 新的基准标准有助于研究处理现实世界,错位的多式联络成像数据.
    • DML取得了最先进的结果,突出了解决RGB-T SS中的模式调整的重要性.