A Transformer Based Approach for Activity Detection

Gulshan Sharma, Abhinav Dhall, Ramanathan Subramanian

Research output: A Conference proceeding or a Chapter in BookConference contributionpeer-review

3 Citations (Scopus)

Abstract

Non-invasive physiological sensors allow for the collection of user-specific data in realistic environments. In this paper, using physiological data, we investigate the effectiveness of Convolutional Neural Network (CNN) based feature embeddings and Transformer architecture for the human activity recognition task. 1D-CNN representation is used for the heart rate, and 2D-CNN is used for short-term Fourier transformation of the accelerometer data. Post fusion, the feature is input into a transformer. The experiments are performed on the harAGE dataset. The findings indicate the discriminative ability of the feature-fusion on transformer-based architecture, and the method outperforms the harAGE baseline by an absolute 3.7%.

Original languageEnglish
Title of host publicationMM 2022 - Proceedings of the 30th ACM International Conference on Multimedia
PublisherAssociation for Computing Machinery, Inc
Pages7155-7159
Number of pages5
ISBN (Electronic)9781450392037
DOIs
Publication statusPublished - 10 Oct 2022
Event30th ACM International Conference on Multimedia, MM 2022 - Lisboa, Portugal
Duration: 10 Oct 202214 Oct 2022

Publication series

NameMM 2022 - Proceedings of the 30th ACM International Conference on Multimedia

Conference

Conference30th ACM International Conference on Multimedia, MM 2022
Abbreviated titleACM MM
Country/TerritoryPortugal
CityLisboa
Period10/10/2214/10/22

Fingerprint

Dive into the research topics of 'A Transformer Based Approach for Activity Detection'. Together they form a unique fingerprint.

Cite this