AniVision Wins Best Paper Award at ECCV
Award for our innovative IC\M/T research project on visual composition in animated films
The project team of the FWF-DFG Waeve-funded AniVision project has been awarded the Best Paper Award at this year's "Vision for Art Workshop" during the European Conference on Computer Vision (ECCV) in Milan, Italy, one of the leading conferences in the field of computer vision.
Congratulations on this achievement!
AniVision is a transnational collaboration between our IC\M/T researchers Franziska Bruckner and Matthias Zeppelzauer, and Erwin Feyersinger and Claudius Stemmler from the University of Tübingen, Germany. Guided by the motto, "We make animation visible!", the digital humanities project AniVision uses machine learning and computer vision to explore a previously underrepresented area in the stylistic history of animation.
Innovative Research on Visual Composition in Animation
The awarded paper focuses on the automated analysis of visual composition in animated films, using labels developed by the project’s film scholars. “The main innovation of the paper is a novel approach that enables the training of machine learning models for stylistic analysis of images from a minimal number of previously labeled examples," said Zeppelzauer.
The reviewers praised the interdisciplinary approach, noting: "The paper's contribution to the field is significant, offering a new methodology for automated analysis that could assist scholars and archivists in studying and cataloging ephemeral films more efficiently."
Monica Apellaniz-Portos, currently pursuing her PhD on style analysis in historical film and imagery, presented the work at the workshop as one of the few invited oral presentations.
FH-Prof. Priv.-Doz. Dipl.-Ing. Mag. Dr. Matthias Zeppelzauer
Head ofMedia Computing Research Group
Institute of Creative\Media/Technologies Department of Media and Digital Technologies
FH-Prof. Mag. Mag. Dr. Franziska Bruckner
Senior ResearcherMedia Creation Research Group
Institute of Creative\Media/Technologies Department of Media and Digital Technologies