Introduction to the Sixth Annual Lifelog Search Challenge, LSC’23

Gurrin, Cathal; Jónsson, Björn Þór; Dang-Nguyen, Duc-Tien; Healy, Graham; Lokoč, Jakub; Zhou, Liting; Rossetto, Luca; Tran, Minh–Triet; Hürst, Wolfgang; Bailer, Werner; Schoeffmann, Klaus

doi:10.1145/3591106.3592304

Cited by 27 publications

(2 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our multimodal retrieval case, we leverage the use of two distinct datasets: the AU-AIR dataset [4] and the LSC'23 dataset [11]. These datasets provide us with diverse modalities and rich content for performing comprehensive and accurate retrieval.…”

Section: Datasetsmentioning

confidence: 99%

Time-Quality Tradeoff of MuseHash Query Processing Performance

Pegia,

Lopez,

Moumtzidou

et al. 2024

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Nowadays, massive quantities of multimedia data, such as videos, images, text and audio, are generated by various applications on smartphones, drones and other devices. To facilitate efficient retrieval from these multimedia collections, we need (a) effective media representation and (b) efficient indexing and query processing approaches. Recently, the MuseHash approach was proposed, which can effectively represent a variety of modalities, improving on previous hashing-based approaches. However, the interaction of the MuseHash approach with existing indexing and query processing approaches has not been considered. This paper provides a systematic evaluation of a set of state-of-the-art approximate nearest neighbor search algorithms for image retrieval, when applied to the MuseHash approach, providing quantitative comparison results and evaluating the use of High-Performance Computing (HPC) infrastructures. An extensive set of experiments on a benchmark aerial dataset and on a real life-log dataset demonstrates the effectiveness of employing hashing and ANN techniques with HPC, resulting in reduced computational time.

show abstract

Section: Datasetsmentioning

confidence: 99%

Time-Quality Tradeoff of MuseHash Query Processing Performance

Pegia,

Lopez,

Moumtzidou

et al. 2024

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…Before we look at the available and possible ways to process that subset of personal information that we address here, it is worth looking at the broader field of lifelogging and its current status and challenges [7]. The best source of up-to-date progress on information access to lifelogs is the most recent of the annual lifelog search challenges (LSC), held in 2023 [2]. This is the sixth of the annual comparative benchmarking exercises for interactive lifelog search systems.…”

Section: Lifelogging: Extreme Personal Information Gatheringmentioning

confidence: 99%

Managing Personal Information

Smeaton

2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

There is an increasing awareness of the potential that our own self-gathered personal information has for our wellness and our health. This is partly because of our increasing awareness of what others -the major internet companies mainly -have been able to do with the personal information that they gather about us. The biggest hurdle to us using and usefully exploiting our own self-gathered personal data are the applications to support that. In this paper we highlight both the potential and the challenges associated with more widespread use of our own personal data by ourselves and we point at ways in which we believe this might happen. We use the work done in lifelogging and the annual Lifelog Search Challenge as an indicator of what we can do with our own data. We review the small number of existing systems which do allow aggregation of our own personal information and show how the use of large language models could make the management of our personal data more straightforward.

show abstract