Modelos de clasificación de emociones basados en CNN y ViT

Abstract

The present project focuses on comparing the performance of convolutional neural network (CNN) and vision transformer (ViT) models to classify emotions in facial images. The problem lies in the accuracy of CNNs, which still faces challenges, while ViTs have emerged as a promising alternative, highlighting the importance of addressing emotions in the context of mental health, as these can influence the ability to creative work and are linked to different clinical study conditions.