Home // COGNITIVE 2022, The Fourteenth International Conference on Advanced Cognitive Technologies and Applications // View article

Comparison of Visual Attention Networks for Semantic Image Segmentation in Reminiscence Therapy

Authors:
Liane-Marina Meßmer
Christoph Reich

Keywords: Visual Attention Networks; Image Caption Generation; Dementia Health Care; BLEU; METEOR

Abstract:
Due to the steadily increasing age of the entire population, the number of dementia patients is steadily growing. Reminiscence therapy is an important aspect of dementia care. It is crucial to include this area in digitization as well. Modern Reminiscence sessions consist of digital media content specifically tailored to a patient’s biographical needs. To enable an automatic selection of this content, the use of Visual Attention Networks for Semantic Image Segmentation is evaluated in this work. A detailed comparison of various Neural Networks is shown, evaluated by Metric for Evaluation of Translation with Explicit Ordering (METEOR) in addition to Billingual Evaluation Study (BLEU) Score. The most promising Visual Attention Network consists of a Xception Network as Encoder and a Gated Recurrent Unit Network as Decoder.etailed comparison of various Neural Networks is shown, evaluated by Metric for Evaluation of Translation with Explicit Ordering (METEOR) in addition to Billingual Evaluation Study (BLEU) Score. The most promising Visual Attention Network consists of a Xception Network as Encoder and a Gated Recurrent Unit Network as Decoder.

Pages: 34 to 39

Copyright: Copyright (c) IARIA, 2022

Publication date: April 24, 2022

Published in: conference

ISSN: 2308-4197

ISBN: 978-1-61208-950-8

Location: Barcelona, Spain

Dates: from April 24, 2022 to April 28, 2022