Spatio-temporal Models of Human Attention for Optimization of Information Visualizations (A07)

• Subject Area: Human Factors, Ergonomics, Human-Machine Systems ; Image and Language Processing, Computer Graphics and Visualisation, Human Computer Interaction, Ubiquitous and Wearable Computing
• Term: since 2019
• Project identifier: Deutsche Forschungsgemeinschaft (DFG) - Project number 251654672

Computational modeling of human attention is essential for optimizing information visualizations. In contrast to prior works that mainly focused on saliency or spatial attention modeling, this project focuses on spatio-temporal attention, i.e., scanpath prediction. We will develop novel methods to jointly predict saliency and scanpaths on both 2D and 3D information visualizations and propose suitable evaluation metrics. Since scanpaths are task- or goal-dependent, we will also develop approaches to predict user intents from scanpaths. Finally, using our attention models, we will develop novel methods to optimize information visualizations, e.g., for increased memorability or lower uncertainty in gaze-based analyses.

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