The web has become a fundamental tool for carrying out many activities spanning from
education to work and private life. For this reason, it must be accessible to every user …

People with visual impairments, particularly blind people face alot of difficulties browsing the
web with assistive technologies such as screen readers, when websites do not conform to …

Image captioning is the task of assigning phrases to images describing their visual content.
Two main approaches for image captioning are commonly used. On the one hand …

Current evaluation metrics for image description may be too coarse. We therefore propose a
series of binary forced-choice tasks that each focus on a different aspect of the captions. We …

Accessing images online is often difficult for users with vision impairments. This population
relies on text descriptions of images that vary based on website authors' accessibility …

Images have become an integral part of online media. This has enhanced self-expression
and the dissemination of knowledge, but it poses serious accessibility challenges. Adequate …

We present a new tree based approach to composing expressive image descriptions that
makes use of naturally occuring web images with captions. We investigate two related tasks …

Popular metrics used for evaluating image captioning systems, such as BLEU and CIDEr,
provide a single score to gauge the system's overall effectiveness. This score is often not …

Image accessibility on the web is the main focus of this study. Due to the lack of proper
image descriptions, it has been difficult to access intended information available on the …

Millions of people who are either blind or visually impaired have difficulty understanding the
content in an image. To address the problem textual image descriptions or captions are …