HIGHLIGHTS
- who: Maurizio Leotta from the DIBRIS, University of Genova, Genova, Italy have published the paper: Evaluating the effectiveness of automatic image captioning for web accessibility, in the Journal: (JOURNAL)
- what: The authors evaluate the correctness of their outputs by comparing the generated descriptions with human-defined references. If the authors focus on the accessibility of images, a good starting point is the tutorial which explains how to provide appropriate text alternatives based on the purpose of the images themselves which can be informative, decorative, functional (e_g, the image of an icon), simple, complex (e_g, a . . .
If you want to have access to all the content you need to log in!
Thanks :)
If you don't have an account, you can create one here.