Fixation crops and saccade coordinates for Nortmann, Sulewski & Kietzmann (2025)

This dataset contains fixation crops and corresponding saccade coordinates derived from the MS-COCO dataset (Lin et al., 2014) using DeepGaze III (Kümmerer et al., 2022) predictions. The data was used in the study "Predictive remapping and allocentric coding as consequences of energy efficiency in recurrent neural network models of active vision" (Nortmann, Sulewski & Kietzmann, 2025) to train recurrent neural networks on human-like saccadic eye movement patterns.