MODELS -- Qvire (CulturalAI) -- Detecting quiremarks

<p>The weights of the models trained on the task of quiremark detection on medieval manuscripts. Specifically this archive contains the model weights of two detection approaches used in our&nbsp;work represented by different architectures (Faster RCNN and ViT), each of which is further represented by a set of five&nbsp;weights corresponding to the resulting models trained when performing the final evaluation on all 59 manuscripts in the form of 5-fold cross validation.</p> <p>The specific manuscripts used to train/eval the&nbsp;models in each fold are also specified in this archive.</p>