Exploring older adults' adoption and use of a tablet computer during COVID-19: Longitudinal study (Preprint)

UNSTRUCTURED As mobile computing technology evolves, such as a smartphone or a tablet computer, it increasingly offers features that may be particularly beneficial to older adults. However, the digital divide exists, and many older adults have been shown to have difficulty using these devices. The COVID-19 pandemic has magnified how much older adults need but are excluded from having access to and comfort with technologies to meet essential daily needs and overcome physical distancing restrictions. This study sought to understand how older adults who had never used a tablet computer learn to use it, what they want to use it for, and what barriers they experience as they continue to use it during social isolation by the COVID-19 pandemic. We conducted a series of semi-structured interviews with eight people aged 65 and older for 16 weeks, investigating older novice users’ learning and use of a tablet computer over time. The results show that our participants were willing to learn and successfully used a tablet for entertainment, social connectedness, and information-seeking purposes. However, it was not through acquiring sufficient digital skills but by incorporating the method they are already familiar with in its operation – Pen-and-paper. With these findings, we conclude by discussing how to help older adults better utilize digital devices for quality of later life.

Image captioning Bot

Image captioning means automatically generating a caption for an image with the development of deep learning, the combination of computer vision and natural language process has caught great attention in the last few years. Image captioning is a representative of this filed, which makes the computer learn to use one or more sentences to understand the visual content of an image. The meaningful description generation process of highlevel image semantics requires not only the recognition of the object and the scene, but the ability of analyzing the state, the attributes and the relationship among these objects. Neural network based methods are further divided into subcategories based on the specific framework they use. Each subcategory of neural network based methods are discussed in detail. After that, state of the art methods are compared on benchmark datasets. Following that, discussions on future research directions are presented.

Image Captioning Based on Deep Neural Networks

With the development of deep learning, the combination of computer vision and natural language process has aroused great attention in the past few years. Image captioning is a representative of this filed, which makes the computer learn to use one or more sentences to understand the visual content of an image. The meaningful description generation process of high level image semantics requires not only the recognition of the object and the scene, but the ability of analyzing the state, the attributes and the relationship among these objects. Though image captioning is a complicated and difficult task, a lot of researchers have achieved significant improvements. In this paper, we mainly describe three image captioning methods using the deep neural networks: CNN-RNN based, CNN-CNN based and Reinforcement-based framework. Then we introduce the representative work of these three top methods respectively, describe the evaluation metrics and summarize the benefits and major challenges.