Dual temporal memory network with high-order spatio-temporal graph learning for video object segmentation

IF 4.2 3区 计算机科学 Q2 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE
Jiaqing Fan , Shenglong Hu , Long Wang , Kaihua Zhang , Bo Liu
{"title":"Dual temporal memory network with high-order spatio-temporal graph learning for video object segmentation","authors":"Jiaqing Fan ,&nbsp;Shenglong Hu ,&nbsp;Long Wang ,&nbsp;Kaihua Zhang ,&nbsp;Bo Liu","doi":"10.1016/j.imavis.2024.105208","DOIUrl":null,"url":null,"abstract":"<div><p>Typically, Video Object Segmentation (VOS) always has the semi-supervised setting in the testing phase. The VOS aims to track and segment one or several target objects in the following frames in the sequence, only given the ground-truth segmentation mask in the initial frame. A fundamental issue in VOS is how to best utilize the temporal information to improve the accuracy. To address the aforementioned issue, we provide an end-to-end framework that simultaneously extracts long-term and short-term historical sequential information to current frame as temporal memories. The integrated temporal architecture consists of a short-term and a long-term memory modules. Specifically, the short-term memory module leverages a high-order graph-based learning framework to simulate the fine-grained spatial–temporal interactions between local regions across neighboring frames in a video, thereby maintaining the spatio-temporal visual consistency on local regions. Meanwhile, to relieve the occlusion and drift issues, the long-term memory module employs a Simplified Gated Recurrent Unit (S-GRU) to model the long evolutions in a video. Furthermore, we design a novel direction-aware attention module to complementarily augment the object representation for more robust segmentation. Our experiments on three mainstream VOS benchmarks, containing DAVIS 2017, DAVIS 2016, and Youtube-VOS, demonstrate that our proposed solution provides a fair tradeoff performance between both speed and accuracy.</p></div>","PeriodicalId":50374,"journal":{"name":"Image and Vision Computing","volume":"150 ","pages":"Article 105208"},"PeriodicalIF":4.2000,"publicationDate":"2024-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Image and Vision Computing","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0262885624003135","RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

Abstract

Typically, Video Object Segmentation (VOS) always has the semi-supervised setting in the testing phase. The VOS aims to track and segment one or several target objects in the following frames in the sequence, only given the ground-truth segmentation mask in the initial frame. A fundamental issue in VOS is how to best utilize the temporal information to improve the accuracy. To address the aforementioned issue, we provide an end-to-end framework that simultaneously extracts long-term and short-term historical sequential information to current frame as temporal memories. The integrated temporal architecture consists of a short-term and a long-term memory modules. Specifically, the short-term memory module leverages a high-order graph-based learning framework to simulate the fine-grained spatial–temporal interactions between local regions across neighboring frames in a video, thereby maintaining the spatio-temporal visual consistency on local regions. Meanwhile, to relieve the occlusion and drift issues, the long-term memory module employs a Simplified Gated Recurrent Unit (S-GRU) to model the long evolutions in a video. Furthermore, we design a novel direction-aware attention module to complementarily augment the object representation for more robust segmentation. Our experiments on three mainstream VOS benchmarks, containing DAVIS 2017, DAVIS 2016, and Youtube-VOS, demonstrate that our proposed solution provides a fair tradeoff performance between both speed and accuracy.

采用高阶时空图学习的双时空记忆网络,用于视频对象分割
通常情况下,视频对象分割(VOS)在测试阶段总是采用半监督设置。VOS 的目的是在序列的后续帧中跟踪和分割一个或多个目标对象,但只给定初始帧中的地面实况分割掩码。VOS 的一个基本问题是如何更好地利用时间信息来提高准确性。为解决上述问题,我们提供了一个端到端框架,可同时提取当前帧的长期和短期历史序列信息作为时态记忆。集成时空架构由短期和长期记忆模块组成。具体来说,短期记忆模块利用基于高阶图的学习框架来模拟视频中相邻帧之间局部区域的细粒度时空交互,从而保持局部区域的时空视觉一致性。同时,为了缓解遮挡和漂移问题,长期记忆模块采用了简化门控递归单元(S-GRU)来模拟视频中的长期演变。此外,我们还设计了一个新颖的方向感知注意力模块,以补充增强对象表示,从而实现更稳健的分割。我们在三个主流 VOS 基准(包括 DAVIS 2017、DAVIS 2016 和 Youtube-VOS)上进行的实验表明,我们提出的解决方案在速度和准确性之间实现了公平的性能权衡。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Image and Vision Computing
Image and Vision Computing 工程技术-工程:电子与电气
CiteScore
8.50
自引率
8.50%
发文量
143
审稿时长
7.8 months
期刊介绍: Image and Vision Computing has as a primary aim the provision of an effective medium of interchange for the results of high quality theoretical and applied research fundamental to all aspects of image interpretation and computer vision. The journal publishes work that proposes new image interpretation and computer vision methodology or addresses the application of such methods to real world scenes. It seeks to strengthen a deeper understanding in the discipline by encouraging the quantitative comparison and performance evaluation of the proposed methodology. The coverage includes: image interpretation, scene modelling, object recognition and tracking, shape analysis, monitoring and surveillance, active vision and robotic systems, SLAM, biologically-inspired computer vision, motion analysis, stereo vision, document image understanding, character and handwritten text recognition, face and gesture recognition, biometrics, vision-based human-computer interaction, human activity and behavior understanding, data fusion from multiple sensor inputs, image databases.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信