Alam, Naushad ORCID: 0000-0002-3144-5622, Graham, Yvette and Gurrin, Cathal
ORCID: 0000-0003-2903-3968
(2024)
Memento 4.0: A Prototype Conversational Search System for
LSC’24.
In: The 7th Annual ACM Lifelog Search Challenge (LSC ’24)., 10 June, 2024, Phuket, Thailand.
ISBN 979-8-4007-0550-2
Abstract
The practice of lifelogging, capturing one’s daily experiences through
wearable devices, has evolved significantly over the last decade, presenting both challenges and opportunities in information retrieval.
This paper presents an early prototype of a conversational lifelog
retrieval system designed to address the open challenges in this
domain. Our system integrates a hierarchical event segmentation
approach to automatically organize lifelog data into meaningful
events, facilitating event-based retrieval over traditional image retrieval. Moreover, we incorporate a question-answering pipeline,
leveraging large language models such as GPT-3.5 Turbo and Mistral7B, to enable free-form natural language interaction with the
lifelog dataset. Moreover, we enhance our system’s user interface
by building on previous versions to streamline event-based retrieval
and question-answering functionalities.
Metadata
Item Type: | Conference or Workshop Item (Paper) |
---|---|
Event Type: | Workshop |
Refereed: | Yes |
Uncontrolled Keywords: | lifelog, information retrieval, semantic image representation, conversational search |
Subjects: | Computer Science > Information retrieval Computer Science > Interactive computer systems Computer Science > Multimedia systems Computer Science > Information storage and retrieval systems Computer Science > Lifelog |
DCU Faculties and Centres: | Research Institutes and Centres > INSIGHT Centre for Data Analytics Research Institutes and Centres > ADAPT |
Published in: | LSC '24: Proceedings of the 7th Annual ACM Workshop on the Lifelog Search Challenge. . LSC. ISBN 979-8-4007-0550-2 |
Publisher: | LSC |
Official URL: | https://dl.acm.org/doi/10.1145/3643489.3661126 |
Funders: | Science Foundation Ireland |
ID Code: | 30691 |
Deposited On: | 24 Jan 2025 09:49 by Naushad Alam . Last Modified 24 Jan 2025 09:49 |
Documents
Full text available as:
Preview |
PDF
- Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
Creative Commons: Attribution 4.0 5MB |
Metrics
Altmetric Badge
Dimensions Badge
Downloads
Downloads
Downloads per month over past year
Archive Staff Only: edit this record