Region-aware image-based human action retrieval with transformers

IF 4.3 3区 计算机科学 Q2 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Computer Vision and Image Understanding Pub Date : 2024-10-14 DOI:10.1016/j.cviu.2024.104202
Hongsong Wang , Jianhua Zhao , Jie Gui
{"title":"Region-aware image-based human action retrieval with transformers","authors":"Hongsong Wang ,&nbsp;Jianhua Zhao ,&nbsp;Jie Gui","doi":"10.1016/j.cviu.2024.104202","DOIUrl":null,"url":null,"abstract":"<div><div>Human action understanding is a fundamental and challenging task in computer vision. Although there exists tremendous research on this area, most works focus on action recognition, while action retrieval has received less attention. In this paper, we focus on the neglected but important task of image-based action retrieval which aims to find images that depict the same action as a query image. We establish benchmarks for this task and set up important baseline methods for fair comparison. We present a Transformer-based model that learns rich action representations from three aspects: the anchored person, contextual regions, and the global image. A fusion transformer is designed to model the relationships among different features and effectively fuse them into an action representation. Experiments on both the Stanford-40 and PASCAL VOC 2012 Action datasets show that the proposed method significantly outperforms previous approaches for image-based action retrieval.</div></div>","PeriodicalId":50633,"journal":{"name":"Computer Vision and Image Understanding","volume":"249 ","pages":"Article 104202"},"PeriodicalIF":4.3000,"publicationDate":"2024-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Computer Vision and Image Understanding","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1077314224002832","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

Human action understanding is a fundamental and challenging task in computer vision. Although there exists tremendous research on this area, most works focus on action recognition, while action retrieval has received less attention. In this paper, we focus on the neglected but important task of image-based action retrieval which aims to find images that depict the same action as a query image. We establish benchmarks for this task and set up important baseline methods for fair comparison. We present a Transformer-based model that learns rich action representations from three aspects: the anchored person, contextual regions, and the global image. A fusion transformer is designed to model the relationships among different features and effectively fuse them into an action representation. Experiments on both the Stanford-40 and PASCAL VOC 2012 Action datasets show that the proposed method significantly outperforms previous approaches for image-based action retrieval.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
利用变换器进行基于区域感知图像的人体动作检索
人类动作理解是计算机视觉领域的一项基本而具有挑战性的任务。尽管在这一领域已有大量研究,但大多数作品都集中在动作识别上,而动作检索却较少受到关注。在本文中,我们重点讨论了基于图像的动作检索这一被忽视但却很重要的任务,其目的是找到与查询图像描述相同动作的图像。我们为这项任务建立了基准,并设定了重要的基准方法,以便进行公平比较。我们提出了一种基于变换器的模型,该模型可从三个方面学习丰富的动作表征:锚定人、上下文区域和全局图像。我们设计了一个融合转换器来模拟不同特征之间的关系,并将它们有效地融合到动作表示中。在 Stanford-40 和 PASCAL VOC 2012 动作数据集上进行的实验表明,在基于图像的动作检索方面,所提出的方法明显优于以往的方法。
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 去求助
来源期刊
Computer Vision and Image Understanding
Computer Vision and Image Understanding 工程技术-工程:电子与电气
CiteScore
7.80
自引率
4.40%
发文量
112
审稿时长
79 days
期刊介绍: The central focus of this journal is the computer analysis of pictorial information. Computer Vision and Image Understanding publishes papers covering all aspects of image analysis from the low-level, iconic processes of early vision to the high-level, symbolic processes of recognition and interpretation. A wide range of topics in the image understanding area is covered, including papers offering insights that differ from predominant views. Research Areas Include: • Theory • Early vision • Data structures and representations • Shape • Range • Motion • Matching and recognition • Architecture and languages • Vision systems
期刊最新文献
Editorial Board Multi-Scale Adaptive Skeleton Transformer for action recognition Open-set domain adaptation with visual-language foundation models Leveraging vision-language prompts for real-world image restoration and enhancement RetSeg3D: Retention-based 3D semantic segmentation for autonomous driving
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1