Login (DCU Staff Only)
Login (DCU Staff Only)

DORAS | DCU Research Repository

Explore open access research and scholarly works from DCU

Advanced Search

Activity Classification for Daily Lifelogs

Nie, Dongyun orcid logoORCID: 0000-0003-3109-5762, Gurrin, Cathal orcid logoORCID: 0000-0003-2903-3968 and Scriney, Michael orcid logoORCID: 0000-0001-6813-2630 (2024) Activity Classification for Daily Lifelogs. In: The 1st ACM Workshop on AI-Powered Q&A Systems for Multimedia, 10 - 14, June 2024, Phuket, Thailand. ISBN 9798400706196

Abstract
In recent years, researchers have emphasized interactive question-answering (QA) systems integrated with lifelog retrieval for their prompt query resolution and ability to accommodate various types of data. Lifelog datasets, collected via wearables, serve as valuable resources for multimedia retrieval and human behaviour exploration across diverse fields like healthcare and sports. Accurate lifelong activity prediction is pivotal for understanding daily behaviours, necessitating precise Activities of Daily Living (ADL) prediction. This paper reframes lifelogging’s retrieval task as a question-answering challenge, which can be applied to auto-labelling extensive unseen lifelog activity data using classification algorithms. Leveraging machine learning methodologies enables lifelog retrieval systems to analyze and interpret lifelog data, improving ADL predictions and system performance.
Metadata
Item Type:Conference or Workshop Item (Paper)
Event Type:Workshop
Refereed:Yes
Uncontrolled Keywords:Classification, Lifelog Retrieval, Activities of Daily Living
Subjects:Computer Science > Machine learning
Computer Science > Lifelog
DCU Faculties and Centres:DCU Faculties and Schools > Faculty of Engineering and Computing > School of Computing
Published in: ICMR '24: Proceedings of the 2024 International Conference on Multimedia Retrieval. . ICMR. ISBN 9798400706196
Publisher:ICMR
Funders:Science Foundation Ireland (SFI), European Regional Development Fund
ID Code:30673
Deposited On:23 Jan 2025 12:28 by Dongyun Nie . Last Modified 23 Jan 2025 12:28
Documents

Full text available as:

[thumbnail of AIQAM1607.pdf]
Preview
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
Creative Commons: Attribution 4.0
656kB
Metrics

Altmetric Badge

Dimensions Badge

Downloads

Downloads

Downloads per month over past year

Archive Staff Only: edit this record