Comparing Interactive Retrieval Approaches at the Lifelog Search Challenge 2021

Ly Duyen Tran; Manh Duy Nguyen; Duc Tien Dang-Nguyen; Silvan Heller; Florian Spiess; Jakub Lokoc; Ladislav Peska; Thao Nhu Nguyen; Omar Shahbaz Khan; Aaron Duane; Bjorn Por Jonsson; Luca Rossetto; An Zi Yen; Ahmed Alateeq; Naushad Alam; Minh Triet Tran; Graham Healy; Klaus Schoeffmann; Cathal Gurrin

doi:10.1109/ACCESS.2023.3248284

Comparing Interactive Retrieval Approaches at the Lifelog Search Challenge 2021

Ly Duyen Tran^*, Manh Duy Nguyen, Duc Tien Dang-Nguyen, Silvan Heller, Florian Spiess, Jakub Lokoc, Ladislav Peska, Thao Nhu Nguyen, Omar Shahbaz Khan, Aaron Duane, Bjorn Por Jonsson, Luca Rossetto, An Zi Yen, Ahmed Alateeq, Naushad Alam, Minh Triet Tran, Graham Healy, Klaus Schoeffmann, Cathal Gurrin

^*Corresponding author for this work

Department of Computer Science

Research output: Contribution to journal › Article › peer-review

16 Scopus citations

Abstract

The Lifelog Search Challenge (LSC) is an interactive benchmarking evaluation workshop for lifelog retrieval systems. The challenge was first organised in 2018 aiming to find the system that can quickly retrieve relevant lifelog images for a given semantic query. This paper provides an analysis of the performance of all 17 systems participating in the 4th LSC workshop held at the 2021 Annual ACM International Conference on Multimedia Retrieval (ICMR). LSC'21 was the largest effort at comparing different approaches to interactive lifelog retrieval systems seen thus far. Findings from the challenge suggest that many different interactive factors contribute to the success (or otherwise) of participating teams. In this paper, we provide an overview of the LSC'21 challenge, introduce each team's approach and explore these factors in depth and offer clues on how to develop a high-performing interactive lifelog search engine.

Original language	English
Pages (from-to)	30982-30995
Number of pages	14
Journal	IEEE Access
Volume	11
DOIs	https://doi.org/10.1109/ACCESS.2023.3248284
State	Published - 2023

Keywords

analytics
information retrieval
Lifelog
multimodal

Access to Document

10.1109/ACCESS.2023.3248284

Cite this

Tran, L. D., Nguyen, M. D., Dang-Nguyen, D. T., Heller, S., Spiess, F., Lokoc, J., Peska, L., Nguyen, T. N., Khan, O. S., Duane, A., Jonsson, B. P., Rossetto, L., Yen, A. Z., Alateeq, A., Alam, N., Tran, M. T., Healy, G., Schoeffmann, K., & Gurrin, C. (2023). Comparing Interactive Retrieval Approaches at the Lifelog Search Challenge 2021. IEEE Access, 11, 30982-30995. https://doi.org/10.1109/ACCESS.2023.3248284

@article{cfef94cc940e45718ab4718bf9bd76cd,

title = "Comparing Interactive Retrieval Approaches at the Lifelog Search Challenge 2021",

abstract = "The Lifelog Search Challenge (LSC) is an interactive benchmarking evaluation workshop for lifelog retrieval systems. The challenge was first organised in 2018 aiming to find the system that can quickly retrieve relevant lifelog images for a given semantic query. This paper provides an analysis of the performance of all 17 systems participating in the 4th LSC workshop held at the 2021 Annual ACM International Conference on Multimedia Retrieval (ICMR). LSC'21 was the largest effort at comparing different approaches to interactive lifelog retrieval systems seen thus far. Findings from the challenge suggest that many different interactive factors contribute to the success (or otherwise) of participating teams. In this paper, we provide an overview of the LSC'21 challenge, introduce each team's approach and explore these factors in depth and offer clues on how to develop a high-performing interactive lifelog search engine.",

keywords = "analytics, information retrieval, Lifelog, multimodal",

author = "Tran, {Ly Duyen} and Nguyen, {Manh Duy} and Dang-Nguyen, {Duc Tien} and Silvan Heller and Florian Spiess and Jakub Lokoc and Ladislav Peska and Nguyen, {Thao Nhu} and Khan, {Omar Shahbaz} and Aaron Duane and Jonsson, {Bjorn Por} and Luca Rossetto and Yen, {An Zi} and Ahmed Alateeq and Naushad Alam and Tran, {Minh Triet} and Graham Healy and Klaus Schoeffmann and Cathal Gurrin",

note = "Publisher Copyright: {\textcopyright} 2013 IEEE.",

year = "2023",

doi = "10.1109/ACCESS.2023.3248284",

language = "English",

volume = "11",

pages = "30982--30995",

journal = "IEEE Access",

issn = "2169-3536",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

Tran, LD, Nguyen, MD, Dang-Nguyen, DT, Heller, S, Spiess, F, Lokoc, J, Peska, L, Nguyen, TN, Khan, OS, Duane, A, Jonsson, BP, Rossetto, L, Yen, AZ, Alateeq, A, Alam, N, Tran, MT, Healy, G, Schoeffmann, K & Gurrin, C 2023, 'Comparing Interactive Retrieval Approaches at the Lifelog Search Challenge 2021', IEEE Access, vol. 11, pp. 30982-30995. https://doi.org/10.1109/ACCESS.2023.3248284

TY - JOUR

T1 - Comparing Interactive Retrieval Approaches at the Lifelog Search Challenge 2021

AU - Tran, Ly Duyen

AU - Nguyen, Manh Duy

AU - Dang-Nguyen, Duc Tien

AU - Heller, Silvan

AU - Spiess, Florian

AU - Lokoc, Jakub

AU - Peska, Ladislav

AU - Nguyen, Thao Nhu

AU - Khan, Omar Shahbaz

AU - Duane, Aaron

AU - Jonsson, Bjorn Por

AU - Rossetto, Luca

AU - Yen, An Zi

AU - Alateeq, Ahmed

AU - Alam, Naushad

AU - Tran, Minh Triet

AU - Healy, Graham

AU - Schoeffmann, Klaus

AU - Gurrin, Cathal

PY - 2023

Y1 - 2023

N2 - The Lifelog Search Challenge (LSC) is an interactive benchmarking evaluation workshop for lifelog retrieval systems. The challenge was first organised in 2018 aiming to find the system that can quickly retrieve relevant lifelog images for a given semantic query. This paper provides an analysis of the performance of all 17 systems participating in the 4th LSC workshop held at the 2021 Annual ACM International Conference on Multimedia Retrieval (ICMR). LSC'21 was the largest effort at comparing different approaches to interactive lifelog retrieval systems seen thus far. Findings from the challenge suggest that many different interactive factors contribute to the success (or otherwise) of participating teams. In this paper, we provide an overview of the LSC'21 challenge, introduce each team's approach and explore these factors in depth and offer clues on how to develop a high-performing interactive lifelog search engine.

AB - The Lifelog Search Challenge (LSC) is an interactive benchmarking evaluation workshop for lifelog retrieval systems. The challenge was first organised in 2018 aiming to find the system that can quickly retrieve relevant lifelog images for a given semantic query. This paper provides an analysis of the performance of all 17 systems participating in the 4th LSC workshop held at the 2021 Annual ACM International Conference on Multimedia Retrieval (ICMR). LSC'21 was the largest effort at comparing different approaches to interactive lifelog retrieval systems seen thus far. Findings from the challenge suggest that many different interactive factors contribute to the success (or otherwise) of participating teams. In this paper, we provide an overview of the LSC'21 challenge, introduce each team's approach and explore these factors in depth and offer clues on how to develop a high-performing interactive lifelog search engine.

KW - analytics

KW - information retrieval

KW - Lifelog

KW - multimodal

UR - http://www.scopus.com/inward/record.url?scp=85149408005&partnerID=8YFLogxK

U2 - 10.1109/ACCESS.2023.3248284

DO - 10.1109/ACCESS.2023.3248284

M3 - Article

AN - SCOPUS:85149408005

SN - 2169-3536

VL - 11

SP - 30982

EP - 30995

JO - IEEE Access

JF - IEEE Access

ER -

Comparing Interactive Retrieval Approaches at the Lifelog Search Challenge 2021

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this