M Leotta, F Mori, M Ribaudo - Universal access in the information society, 2023 - Springer
… we associated a set of five textual descriptions: the first is the alternativetext written by the human contributors to the online encyclopedia Footnote 25 , while the other four are the …
Y Ming, N Hu, C Fan, F Feng… - IEEE/CAA Journal of …, 2022 - researchportal.port.ac.uk
… to generate image caption with impressive progress. To summarize the recent advances in imagecaptioning, we present a comprehensive review on imagecaptioning, covering both …
Z Jia, X Li - Proceedings of the 2020 international conference on …, 2020 - dl.acm.org
… image captioning with human in the loop. Different from automatedimagecaptioning where a given test image … , we have access to both the test image and a sequence of (incomplete) …
… Our system also extracts the alttext and imagecaptions in the DOM while the user is browsing a page using the browser extension. This allows the system to keep improving as more …
X Hu, Z Gan, J Wang, Z Yang, Z Liu… - Proceedings of the …, 2022 - openaccess.thecvf.com
… As some alttexts are too long, we split them up by punctuation marks, such as period and exclamation mark, and select the longest part. To filter out some rare or misspelled words, we …
… We measure CLIP-S’s capacity to reconstruct a set of 2.8K human judgments of alttext … Each alt-text was rated on a scale of 0 to 3 in terms of its probable utility as an alt-text. While the …
A Muehlbradt, SK Kane - ACM Transactions on Accessible Computing …, 2022 - dl.acm.org
… In this study, we explore contextual differences in imagecaptioning based on the domain, … general feedback about the process of imagecaptioning, imagecaptions, and the study, we …
A Tran, A Mathews, L Xie - … of the IEEE/CVF conference on …, 2020 - openaccess.thecvf.com
… set a new SOTA for news imagecaptioning. Our model can incorporate real-world knowledge about entities across different modalities and generate text with better linguistic diversity. …
… imagecaptioning models how “to read”, ie, allow us to design and train imagecaptioning algorithms which are able to process and include information from the text in the image. In …