Quantification of Visual Explainability (A03)

• Subject Area: Image and Language Processing, Computer Graphics and Visualisation, Human Computer Interaction, Ubiquitous and Wearable Computing
• Term: since 2015
• Project identifier: Deutsche Forschungsgemeinschaft (DFG) - Project number 251654672

We aim to extend the notion of quality quantification to visual explainability, meaning that not only a single visualization is assessed in terms of task-dependent readability and pattern saliency but instead in terms of how well multiple visualizations explain the data and analyzed phenomenon. The main goal is the development of visual explainability metrics, which are inherently user-centric metrics that account for the user's properties. The most influential user properties will be determined in user studies, creating a basis for developing an analysis framework.

• DFG Programme: CRC/Transregios
• Subproject of: TRR 161: Quantitative Methods for Visual Computing
• Applicant Institution: Universität Stuttgart
• Project Head: Professor Dr. Daniel Keim