A Vision-based Transfer Learning Approach for Recognizing Behavioral Symptoms in People with Dementia

Zachary Wharton, Erik Thomas, Bappaditya Debnath, Ardhendu Behera

Research output: Contribution to journalArticle (journal)peer-review

3 Citations (Scopus)
186 Downloads (Pure)


With an aging population that continues to grow, dementia is a major global health concern. It is a syndrome in which there is a deterioration in memory, thinking, behavior and the ability to perform activities of daily living. Depression and aggressive behavior are the most upsetting and challenging symptoms of dementia. Automatic recognition of these behaviors would not only be useful to alert family members and caregivers, but also helpful in planning and managing daily activities of people with dementia (PwD). In this work, we propose a vision-based approach that unifies transfer learning and deep convolutional neural network (CNN) for the effective recognition of behavioral symptoms. We also compare the performance of state-of-the-art CNN features with the hand-crafted HOG-feature, as well as their combination using a basic linear SVM. The proposed method is evaluated on a newly created dataset, which is based on the dementia storyline in ITVs Emmerdale episodes. The Alzheimer’s Society has described it as a “realistic portrayal” of the condition to raise awareness of the issues surrounding dementia.
Original languageEnglish
Pages (from-to)1-6
Journal2018 15th IEEE International Conference on Advanced Video and Signal-based Surveillance (AVSS) Proceedigs
Early online date14 Feb 2019
Publication statusE-pub ahead of print - 14 Feb 2019


  • Aggressive and depressive behavior recognition
  • Human-robot social interactions
  • Assistive technology for dementia
  • Health and social care
  • Video analysis and recognition
  • Transfer learning
  • Deep learning
  • CNN features


Dive into the research topics of 'A Vision-based Transfer Learning Approach for Recognizing Behavioral Symptoms in People with Dementia'. Together they form a unique fingerprint.

Cite this