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

DORAS | DCU Research Repository

Explore open access research and scholarly works from DCU

Advanced Search

Flexible interactive retrieval SysTem 3.0 for visual lifelog exploration at LSC 2022

Hoang-Xuan, Nhat, Trang-Trung, Hoang-Phuc, Nguyen, E-Ro, Le, Thanh-Cong, Tran, Mai-Khiem, Le, Tu-Khiem orcid logoORCID: 0000-0003-3013-9380, Ninh, Van-Tu, Gurrin, Cathal orcid logoORCID: 0000-0003-2903-3968 and Tran, Minh-Triet orcid logoORCID: 0000-0003-3046-3041 (2022) Flexible interactive retrieval SysTem 3.0 for visual lifelog exploration at LSC 2022. In: 5th Annual on Lifelog Search Challenge (LSC'22), 27–30 June 2022, Newark, NJ, USA. ISBN 978-1-4503-9239-6

Abstract
Building a retrieval system with lifelogging data is more complicated than with ordinary data due to the redundancies, blurriness, massive amount of data, various sources of information accompanying lifelogging data, and especially the ad-hoc nature of queries. The Lifelog Search Challenge (LSC) is a benchmarking challenge that encourages researchers and developers to push the boundaries in lifelog retrieval. For LSC'22, we develop FIRST 3.0, a novel and flexible system that leverages expressive cross-domain embeddings to enhance the searching process. Our system aims to adaptively capture the semantics of an image at different levels of detail. We also propose to augment our system with an external search engine to help our system with initial visual examples for unfamiliar concepts. Finally, we organize image data in hierarchical clusters based on their visual similarity and location to assist users in data exploration. Experiments show that our system is both fast and effective in handling various retrieval scenarios.
Metadata
Item Type:Conference or Workshop Item (Paper)
Event Type:Workshop
Refereed:Yes
Uncontrolled Keywords:query expansion; interactive retrieval systems; semantic embedding; lifelog
Subjects:Computer Science > Information retrieval
DCU Faculties and Centres:DCU Faculties and Schools > Faculty of Engineering and Computing > School of Computing
Research Initiatives and Centres > ADAPT
Published in: Proceedings of the 5th Annual on Lifelog Search Challenge. . Association for Computing Machinery (ACM). ISBN 978-1-4503-9239-6
Publisher:Association for Computing Machinery (ACM)
Official URL:https://doi.org/10.1145/3512729.3533013
Copyright Information:©2022 Association for Computing Machinery (ACM)
Funders:Gia Lam Urban Development and Investment Company Limited, Vingroup and supported byVingroup Innovation Foundation (VINIF) under project code VINIF.2019.DA19
ID Code:27631
Deposited On:07 Sep 2022 13:16 by Cathal Gurrin . Last Modified 03 Mar 2023 12:45
Documents

Full text available as:

[thumbnail of 3512729.3533013.pdf]
Preview
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
4MB
Downloads

Downloads

Downloads per month over past year

Archive Staff Only: edit this record