Table 2.

Results for 1. EgoPlaceNet.v1 (fine-tuned on the selected training dataset from MINC+HUJI EgoSeg+GTOS) when applied to MAGFRA-W (validation accuracy at the end of the training process: 93.97$\%$), and 2. EgoPlaceNet-LOSO${}_n$ for participant n. LOSO${}_{\mathit{val}}$ indicates the validation accuracy at the end of the training process for each model. Darker shades of grey indicate higher per-class accuracies.