News - Data Science Chair

Our paper "Self-Supervised Multi-Task Pretraining Improves Image Aesthetic Assessment" got accepted for publication at "New Trends in Image Restoration and Enhancement workshop" (NTIRE) at CVPR 2021.

Der erste Neubau für das Forschungszentrum „Künstliche Intelligenz und Data Science“ CAIDAS der Uni Würzburg ist in Sicht. Der Freistaat Bayern hat dafür grünes Licht gegeben und stellt Mittel bereit.

Our group and Heiko Paeth's group developed a novel machine learning model to improve climate model precipitation estimates which we will present at the European Geosciences Union's (EGU's) General Assembly 2021 in a PICO presentation.

We have just submitted the final version of our full paper "Detecting Scenes in Fiction: A new Segmentation Task", which has been accepted for publication at EACL 2021.

Our group together with Heiko Paeth's group developed a novel machine learning model to improve climate model precipitation estimates for which we have received the Best ML Innovation Award on the Tackling Climate Change with Machine Learning Workshop at NeurIPS 2020.

The interactive web portal of the BigData@Geo project has been available since October 2018. After consultation with the cooperating small and medium-sized enterprises (SME), the portal has now been fundamentally revised.

Our paper "LM4KG: Improving Common Sense Knowledge Graphs with Language Models" concerning the enrichment of knowledge graphs through a pre-trained language model was presented at the International Semantic Web Conference (ISWC) 2020.

Our Music & AI Project was presented within the section "Mozart & KI" at Wuerzburg Web Week.

This teaching project wants to explore the ability of Artificial Intelligence and Machine Learning to understand the fundamental creative ideas of music and composition and is part of the Mozartfest initiative Mozart & KI.