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

Aggregating global-scale pixel-wise forgery cues within a graph.

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

Same author

DiMuS: Disentangled Multi-Signal Learning for Weakly Supervised Point-Based 3D Object Detection.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026

Same author

Visual-Textual Information-Driven Tactile Data Generation Method.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026

Same author

Class Sensitive Calibration and Discrepancy-Aware Synthesis for Semi-Supervised Medical Image Segmentation.

IEEE journal of biomedical and health informatics·2026

Same author

Diffusion-based cross-staining feature transformation for whole slide image analysis: From H&E to IHC representation learning.

Medical image analysis·2026

Same author

SD-ReID: View-Aware Stable Diffusion for Aerial-Ground Person Re-Identification.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026

Search research articles

相关实验视频

Updated: Jun 9, 2025

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

MaskTrack:用于视频对象分割的自动标签和稳定跟踪

Zhenyu Chen, Lu Zhang, Ping Hu

IEEE transactions on neural networks and learning systems

|October 22, 2024

概括

本研究介绍了使用分段任何模型 (SAM) 进行有效的视频对象分割 (VOS) 的零拍摄自动标签策略. 新的MaskTrack框架在复杂场景中增强了长期VOS和实例歧视.

科学领域:

计算机视觉计算机视觉
人工智能的人工智能
机器学习机器学习

背景情况:

视频对象细分 (VOS) 已经随着新的数据集和架构而进步.
手动视频口罩注释是劳动密集型和昂贵的,限制了当前基准中的上下文理解.
现有的VOS方法在复杂场景中难以稳定的长期跟踪和实例歧视.

研究的目的:

为密集的视频实例注释开发一个具有成本效益的,零射击的自动标签策略.
引入一个新的框架,MaskTrack,用于强大的长期VOS和改进实例歧视.
评估拟议方法在各种VOS和相关任务上的性能,而无需对图像数据集进行预先培训.

主要方法:

实施了零拍摄自动标签策略,利用分段任何模型 (SAM) 进行密集的视频注释.
开发了MaskTrack框架,旨在实现长期稳定的VOS和在复杂视频中区分类似对象.
在已建立的VOS基准 (YouTube-VOS,LVOS) 和相关任务 (VOT,RVOS) 上进行了广泛的实验.

主要成果:

在没有图像预训练的情况下,在短期VOS (86.2%YouTube-VOS值) 和长期VOS (68.2%LVOS值) 上取得了出色的表现.
在区分复杂视频中的实例与密集的类似对象中表现出显著的优势.

更多相关视频

Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster Nephrops norvegicus

Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster Nephrops norvegicus

Published on: April 8, 2019

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

相关实验视频

Last Updated: Jun 9, 2025

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster Nephrops norvegicus

Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster Nephrops norvegicus

Published on: April 8, 2019

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

展示了强大的概括能力,在视觉对象跟踪 (65.6% VOTS2023) 和引用 VOS (65.2% Ref YouTube VOS) 上表现良好.

结论:

拟议的零拍摄自动标签策略和MaskTrack框架有效地解决了视频对象细分方面的挑战.
该方法简化了注释,并在长期和复杂的视频场景中提高了性能.
该方法在不同的视频分析任务中表现出强烈的概括性.