Abstract
AbstractFilm post-production can be time- and money-inefficient. The reason is that a lot of the work involves a person or group of people, called metadata taggers, going through each individual piece of media and marking it up with relevant tags, such as the scene number, transcripts, and the type of shot for video footage. Such a task is particularly time-consuming for films with high shooting ratios (i.e., footage shot/footage shown). AutoTag automates much of the tagging process across 16 languages, saving both time and money. We describe the algorithms and implementation of AutoTag and report on some case studies.
Funder
National Science Foundation
New York University Abu Dhabi
Publisher
Springer Science and Business Media LLC
Subject
Computer Networks and Communications,Hardware and Architecture,Media Technology,Software
Reference23 articles.
1. Audio Video Sync Software Red Giant - PluralEyes by Maxon. https://www.maxon.net/en/red-giant/pluraleyes
2. Bansal S, Kamper H, Livescu K, Lopez A, Goldwater S (2018) Low-resource speech-to-text translation. Computing Research Repository
3. Berard A, Pietquin O, Servan C, Besacier L (2016) Listen and translate: a proof of concept for end-to-end speech-to-text translation. Computing Research Repository
4. Canini L, Benini S, Leonardi R (2011) Classifying cinematographic shot types. Multimedia Tools and Applications
5. Hasan MA, Xu M, He X (2014) Xu, C. Camera motion histogram descriptor and its application to cinematographic shot classification. IEEE Transactions on Circuits and Systems for Video Technology, Camhid