Analysis of Hybrid Compositions in Animation Film with Weakly Supervised Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Portos, Mónica Apellaniz, Labadie-Tamayo, Roberto, Stemmler, Claudius, Feyersinger, Erwin, Babic, Andreas, Bruckner, Franziska, Öhner, Vrääth, Zeppelzauer, Matthias
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912062018420736
author Portos, Mónica Apellaniz
Labadie-Tamayo, Roberto
Stemmler, Claudius
Feyersinger, Erwin
Babic, Andreas
Bruckner, Franziska
Öhner, Vrääth
Zeppelzauer, Matthias
author_facet Portos, Mónica Apellaniz
Labadie-Tamayo, Roberto
Stemmler, Claudius
Feyersinger, Erwin
Babic, Andreas
Bruckner, Franziska
Öhner, Vrääth
Zeppelzauer, Matthias
contents We present an approach for the analysis of hybrid visual compositions in animation in the domain of ephemeral film. We combine ideas from semi-supervised and weakly supervised learning to train a model that can segment hybrid compositions without requiring pre-labeled segmentation masks. We evaluate our approach on a set of ephemeral films from 13 film archives. Results demonstrate that the proposed learning strategy yields a performance close to a fully supervised baseline. On a qualitative level the performed analysis provides interesting insights on hybrid compositions in animation film.
format Preprint
id arxiv_https___arxiv_org_abs_2410_04789
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Analysis of Hybrid Compositions in Animation Film with Weakly Supervised Learning
Portos, Mónica Apellaniz
Labadie-Tamayo, Roberto
Stemmler, Claudius
Feyersinger, Erwin
Babic, Andreas
Bruckner, Franziska
Öhner, Vrääth
Zeppelzauer, Matthias
Computer Vision and Pattern Recognition
Artificial Intelligence
We present an approach for the analysis of hybrid visual compositions in animation in the domain of ephemeral film. We combine ideas from semi-supervised and weakly supervised learning to train a model that can segment hybrid compositions without requiring pre-labeled segmentation masks. We evaluate our approach on a set of ephemeral films from 13 film archives. Results demonstrate that the proposed learning strategy yields a performance close to a fully supervised baseline. On a qualitative level the performed analysis provides interesting insights on hybrid compositions in animation film.
title Analysis of Hybrid Compositions in Animation Film with Weakly Supervised Learning
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2410.04789