Two-Stream Temporal Feature Aggregation Based on Clustering for Few-Shot Action Recognition

IF 3.2 2区 工程技术 Q2 ENGINEERING, ELECTRICAL & ELECTRONIC IEEE Signal Processing Letters Pub Date : 2024-09-09 DOI:10.1109/LSP.2024.3456670
Long Deng;Ao Li;Bingxin Zhou;Yongxin Ge
{"title":"Two-Stream Temporal Feature Aggregation Based on Clustering for Few-Shot Action Recognition","authors":"Long Deng;Ao Li;Bingxin Zhou;Yongxin Ge","doi":"10.1109/LSP.2024.3456670","DOIUrl":null,"url":null,"abstract":"The metric learning paradigm has achieved notable success in few-shot action recognition; however, it faces unaddressed challenges. Specifically, \n<bold>(1)</b>\n limited training data could impede the exploration of temporal action relations, and \n<bold>(2)</b>\n precision would decline from the presence of outliers during the frame-level feature alignment. To address the challenges, we propose a two-stream temporal feature aggregation method based on clustering, incorporating a temporal augmentation module (TAM) and a feature aggregation module (FAM). The TAM adeptly integrates three consecutive grayscale frames into the original RGB frame through weighted summation, thereby addressing the color-related misguidance and enhancing the temporal information extraction. Meanwhile, the FAM employs clustering to aggregate the frame-level features into high semantic sub-actions and replaces the original features with cluster centers to mitigate the adverse impact of outliers on the model performance. Experimental results on benchmark datasets demonstrate the effectiveness of our method in few-shot action recognition. We validate our proposed approach by conducting comprehensive ablation experiments.","PeriodicalId":13154,"journal":{"name":"IEEE Signal Processing Letters","volume":null,"pages":null},"PeriodicalIF":3.2000,"publicationDate":"2024-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Signal Processing Letters","FirstCategoryId":"5","ListUrlMain":"https://ieeexplore.ieee.org/document/10669816/","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}
引用次数: 0

Abstract

The metric learning paradigm has achieved notable success in few-shot action recognition; however, it faces unaddressed challenges. Specifically, (1) limited training data could impede the exploration of temporal action relations, and (2) precision would decline from the presence of outliers during the frame-level feature alignment. To address the challenges, we propose a two-stream temporal feature aggregation method based on clustering, incorporating a temporal augmentation module (TAM) and a feature aggregation module (FAM). The TAM adeptly integrates three consecutive grayscale frames into the original RGB frame through weighted summation, thereby addressing the color-related misguidance and enhancing the temporal information extraction. Meanwhile, the FAM employs clustering to aggregate the frame-level features into high semantic sub-actions and replaces the original features with cluster centers to mitigate the adverse impact of outliers on the model performance. Experimental results on benchmark datasets demonstrate the effectiveness of our method in few-shot action recognition. We validate our proposed approach by conducting comprehensive ablation experiments.
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
基于聚类的双流时态特征聚合用于少量动作识别
度量学习范式在少镜头动作识别方面取得了显著的成功,但也面临着尚未解决的挑战。具体来说,(1) 有限的训练数据可能会阻碍对时间动作关系的探索,(2) 在帧级特征对齐过程中,由于异常值的存在,精度会下降。为了应对这些挑战,我们提出了一种基于聚类的双流时态特征聚合方法,其中包含一个时态增强模块(TAM)和一个特征聚合模块(FAM)。TAM 通过加权求和将三个连续的灰度帧巧妙地整合到原始 RGB 帧中,从而解决了与颜色相关的误导问题,增强了时间信息的提取。同时,FAM 采用聚类方法将帧级特征聚合为高语义子动作,并用聚类中心替换原始特征,以减轻异常值对模型性能的不利影响。在基准数据集上的实验结果证明了我们的方法在少镜头动作识别中的有效性。我们通过进行全面的消融实验验证了我们提出的方法。
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
IEEE Signal Processing Letters
IEEE Signal Processing Letters 工程技术-工程:电子与电气
CiteScore
7.40
自引率
12.80%
发文量
339
审稿时长
2.8 months
期刊介绍: The IEEE Signal Processing Letters is a monthly, archival publication designed to provide rapid dissemination of original, cutting-edge ideas and timely, significant contributions in signal, image, speech, language and audio processing. Papers published in the Letters can be presented within one year of their appearance in signal processing conferences such as ICASSP, GlobalSIP and ICIP, and also in several workshop organized by the Signal Processing Society.
期刊最新文献
KFA: Keyword Feature Augmentation for Open Set Keyword Spotting RFI-Aware and Low-Cost Maximum Likelihood Imaging for High-Sensitivity Radio Telescopes Audio Mamba: Bidirectional State Space Model for Audio Representation Learning System-Informed Neural Network for Frequency Detection Order Estimation of Linear-Phase FIR Filters for DAC Equalization in Multiple Nyquist Bands
×
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