Optimizing the Interactive Video Retrieval Tool Vibro for the Video Browser Showdown 2024
30th International Conference on MultiMedia Modeling (MMM 2024)
TL;DR
Vibro is an interactive video retrieval system that won the Video Browser Showdown in 2022 and 2023. This paper outlines its core concepts and recent updates for the 2024 competition. It also proposes an evaluation method used to optimize the system's embedding model for image- and text-to-image retrieval.
Abstract
Vibro (Video Browser) is an interactive video retrieval system and the winner of the Video Browser Showdown 2022 and 2023. This paper gives an overview of the underlying concepts of this tool and highlights the changes that were implemented for the upcoming competition of 2024. Additionally, we propose a way to evaluate retrieval engine performance for the specific use case of known-item search, by using logged query data from previous competitions. This evaluation helps in finding an optimal embedding model candidate for image- and text-to-image retrieval and making the right decisions to improve the current system.
BibTeX
If you use our work in your research, please cite our publication:
@inproceedings{10.1007/978-3-031-53302-0_33,
author = {Schall, Konstantin and Hezel, Nico and Barthel, Kai Uwe and Jung, Klaus},
title = {Optimizing the Interactive Video Retrieval Tool Vibro for the Video Browser Showdown 2024},
year = {2024},
isbn = {978-3-031-53301-3},
publisher = {Springer-Verlag},
address = {Berlin, Heidelberg},
url = {https://doi.org/10.1007/978-3-031-53302-0_33},
doi = {10.1007/978-3-031-53302-0_33},
booktitle = {MultiMedia Modeling: 30th International Conference, MMM 2024, Amsterdam, The Netherlands, January 29 – February 2, 2024, Proceedings, Part IV},
pages = {364–371},
numpages = {8},
keywords = {Content-based Video Retrieval, Exploration, Visualization, Image Browsing, Visual and Textual co-embeddings},
location = {Amsterdam, The Netherlands}
}