Libro - Lifelog Search Browser

7th Annual ACM Workshop on the Lifelog Search Challenge (LSC '24)

Authors: Nico Hezel, Konstantin Schall, Bruno Schilling, Klaus Jung, Kai Uwe Barthel

TL;DR

This paper introduces Libro, a powerful tool for interactive image retrieval and browsing, which won the Runner-up and the Best New Entrant awards at the Lifelog Search Challenge 2024.

Abstract

Building on our success with the Vibro video search system in the Video Browser Showdown, we are beginning a new effort by applying our video search technologies to the Lifelog Search Challenge for the first time. Our approach is to treat the lifelog data collected on a given day as frames of a continuous video clip. While we have essentially adopted our text-to-image and image-to-image search from Vibro, we have introduced various metadata filters to complement our search capabilities. Our goal is to increase the efficiency of image searches within the lifelog dataset by integrating these improvements. Additionally, a graph-based visualization and exploration of the entire dataset is possible.

BibTeX

If you use our work in your research, please cite our publication:

@inproceedings{10.1145/3643489.3661124,
author = {Hezel, Nico and Schall, Konstantin and Schilling, Bruno and Jung, Klaus and Barthel, Kai Uwe},
title = {Libro - Lifelog Search Browser},
year = {2024},
isbn = {9798400705502},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3643489.3661124},
doi = {10.1145/3643489.3661124},
booktitle = {Proceedings of the 7th Annual ACM Workshop on the Lifelog Search Challenge},
pages = {70–75},
numpages = {6},
location = {Phuket, Thailand},
series = {LSC '24}
}