Conference Paper/Proceeding/Abstract 204 views 66 downloads
Exploring Human Activity Recognition with Acoustic Data: A Comparative Study of CNN-LSTM, ViViT, and ResNet-Temporal Transformer Model
2025 IEEE Symposium on Computational Intelligence in Image, Signal Processing and Synthetic Media Companion (CISM Companion), Pages: 1 - 5
Swansea University Authors:
AALAA HUMAIDAN, Jeny Roy , Sara Sharifzadeh
, Andrea Tales
, Joe MacInnes
-
PDF | Accepted Manuscript
Author accepted manuscript document released under the terms of a Creative Commons CC-BY licence using the Swansea University Research Publications Policy (rights retention).
Download (310.58KB)
DOI (Published version): 10.1109/cismcompanion65074.2025.11032695
Abstract
Exploring Human Activity Recognition with Acoustic Data: A Comparative Study of CNN-LSTM, ViViT, and ResNet-Temporal Transformer Model
Published in: | 2025 IEEE Symposium on Computational Intelligence in Image, Signal Processing and Synthetic Media Companion (CISM Companion) |
---|---|
ISBN: | 979-8-3315-0852-4 979-8-3315-0851-7 |
Published: |
IEEE
2025
|
URI: | https://cronfa.swan.ac.uk/Record/cronfa69135 |
Keywords: |
Accuracy, Computational modeling, Noise, Pipelines, Transformers, Feature extraction, Data models, Acoustics, Human activity recognition, Convolutional neural networks |
---|---|
College: |
Faculty of Science and Engineering |
Funders: |
This project is partly supported by Swansea University IAA funding scheme and Coventry University |
Start Page: |
1 |
End Page: |
5 |