Skip to main navigation Skip to search Skip to main content

mmCLIP: Boosting mmWave-based Zero-shot HAR via Signal-Text Alignment

  • Qiming Cao
  • , Hongfei Xue
  • , Tianci Liu
  • , Xingchen Wang
  • , Haoyu Wang
  • , Xincheng Zhang
  • , Lu Su
  • Purdue University
  • University of North Carolina at Charlotte

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

25 Scopus citations

Abstract

Millimeter-wave (mmWave) based human activity recognition (HAR) systems have demonstrated promising performance in various applications, leveraging the power of deep neural networks. However, these systems are suffering from the scarcity of available mmWave data for model training. To address this challenge, we explore the possibility of transferring knowledge from large AI models built on massive text and visual data to enhance the generalizability of mmWave-based HAR models. Towards this end, we introduce mmCLIP, a novel system that aligns mmWave signal space and text space to facilitate zero-shot recognition for unseen activities. To enable this alignment, we employ cross-modality signal synthesis to augment mmWave signal data using large human mesh datasets and design an activity attribute decomposition and recomposition approach to characterize the semantic interconnections among activities. We conducted extensive experiments to demonstrate the effectiveness of our proposed framework.

Original languageEnglish
Title of host publicationSenSys 2024 - Proceedings of the 2024 ACM Conference on Embedded Networked Sensor Systems
PublisherAssociation for Computing Machinery, Inc
Pages184-197
Number of pages14
ISBN (Electronic)9798400706974
DOIs
StatePublished - Nov 4 2024
Event22nd ACM Conference on Embedded Networked Sensor Systems, SenSys 2024 - Hangzhou, China
Duration: Nov 4 2024Nov 7 2024

Publication series

NameSenSys 2024 - Proceedings of the 2024 ACM Conference on Embedded Networked Sensor Systems

Conference

Conference22nd ACM Conference on Embedded Networked Sensor Systems, SenSys 2024
Country/TerritoryChina
CityHangzhou
Period11/4/2411/7/24

Keywords

  • human activity recognition
  • large language model
  • mmwave
  • signal augmentation
  • visual-language model
  • wireless sensing

Fingerprint

Dive into the research topics of 'mmCLIP: Boosting mmWave-based Zero-shot HAR via Signal-Text Alignment'. Together they form a unique fingerprint.

Cite this