Comparison of Visual Attention Networks for Semantic Image Segmentation in Reminiscence Therapy
- 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.
Author: | Liane Meßmer, Christoph ReichORCiDGND |
---|---|
URL: | https://www.thinkmind.org/articles/cognitive_2022_1_60_40029.pdf |
ISBN: | 978-1-61208-950-8 |
Parent Title (English): | COGNITIVE 2022 : The Fourteenth International Conference on Advanced Cognitive Technologies and Applications, April 24 - 28, 2022, Barcelona, Spain |
Document Type: | Conference Proceeding |
Language: | English |
Year of Completion: | 2022 |
Release Date: | 2022/11/07 |
Tag: | BLEU; Dementia health care; Image caption generation; METEOR; Visual attention networks |
First Page: | 34 |
Last Page: | 39 |
Open-Access-Status: | Open Access |
Licence (German): | ![]() |