A Trainable Feature Extractor Module for Deep Neural Networks and Scanpath Classification

arXiv:2403.12493v1 Announce Type: cross
Abstract: Scanpath classification is an area in eye tracking research with possible applications in medicine, manufacturing as well as training systems for students in various domains. In this paper we propose a trainable feature extraction module for deep neural networks. The purpose of this module is to transform a scanpath into a feature vector which is directly useable for the deep neural network architecture. Based on the backpropagated error of the deep neural network, the feature …

abstract applications arxiv classification cs.cv cs.lg domains extraction feature feature extraction manufacturing medicine networks neural networks paper research students systems tracking training type