Automated Video Edition for Synchronized Mobile Recordings of Concerts

Albert Jiménez, Lluís Gómez, Joan Llobera

2022

Abstract

We propose a computer vision model that paves the road towards a system that automatically creates a video of a live concert by combining multiple recordings of the audience. The automatic edition system divides the edition problem in three parts: synchronize recordings with media streaming technology, selection of the scene cut position, and the selection of the next shot among the different contributions using an attention-based shot prediction model. We train the shot prediction model using camera transitions in professionally-edited videos of concerts, and evaluate it with both an accuracy metric and a human judgement study. Results show that our system selects the same video source as the ground truth in 38.8% of the cases when challenged with a random number of possible sources ranging between 5 and 10. For the rest of the samples, subjective preference among the selected image and the ground truth is at chance level for non-experts. Image editing experts do reflect better-than-chance performance, when asked to predict the following shot selected.

Paper Citation

in Harvard Style

Jiménez A., Gómez L. and Llobera J. (2022). Automated Video Edition for Synchronized Mobile Recordings of Concerts. In Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 4: VISAPP; ISBN 978-989-758-555-5, SciTePress, pages 941-948. DOI: 10.5220/0010847600003124

in Bibtex Style

@conference{visapp22,
author={Albert Jiménez and Lluís Gómez and Joan Llobera},
title={Automated Video Edition for Synchronized Mobile Recordings of Concerts},
booktitle={Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 4: VISAPP},
year={2022},
pages={941-948},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010847600003124},
isbn={978-989-758-555-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 4: VISAPP
TI - Automated Video Edition for Synchronized Mobile Recordings of Concerts
SN - 978-989-758-555-5
AU - Jiménez A.
AU - Gómez L.
AU - Llobera J.
PY - 2022
SP - 941
EP - 948
DO - 10.5220/0010847600003124
PB - SciTePress