Analysis of Hybrid Compositions in Animation Film with Weakly Supervised Learning
Abstract
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 into hybrid compositions in animation film.
Cite
Text
Portos et al. "Analysis of Hybrid Compositions in Animation Film with Weakly Supervised Learning." European Conference on Computer Vision Workshops, 2024. doi:10.1007/978-3-031-91572-7_5Markdown
[Portos et al. "Analysis of Hybrid Compositions in Animation Film with Weakly Supervised Learning." European Conference on Computer Vision Workshops, 2024.](https://mlanthology.org/eccvw/2024/portos2024eccvw-analysis/) doi:10.1007/978-3-031-91572-7_5BibTeX
@inproceedings{portos2024eccvw-analysis,
title = {{Analysis of Hybrid Compositions in Animation Film with Weakly Supervised Learning}},
author = {Portos, Mónica Apellaniz and Tamayo, Roberto Labadie and Stemmler, Claudius and Feyersinger, Erwin and Babic, Andreas and Bruckner, Franziska and Öhner, Vrääth and Zeppelzauer, Matthias},
booktitle = {European Conference on Computer Vision Workshops},
year = {2024},
pages = {67-85},
doi = {10.1007/978-3-031-91572-7_5},
url = {https://mlanthology.org/eccvw/2024/portos2024eccvw-analysis/}
}