… an image captioning model for the blind that specifically leverages text detected in the image.
2… -generator mechanism when generating captions to copy the detected text when needed. …

… image" captioning methods. In this paper, we discuss various methods of image captioning
… most common problems and challenges of image captioning. We provide a comprehensive …

… We present an image captioning model that combines image features with fine-grained
entities and object labels, and learns to produce fluent and informative image captions. …

… in image captioning has not reached a conclusive answer yet. This work aims at providing
a comprehensive overview of image captioning approaches, from visual encoding and text …

… learning and DALL·E [40] for the text-to-image generation task. This is mainly thanks to the
… described in alt-texts of web-crawled data. Inspired by this, research on image captioning is …

… In this section, we evaluate the robustness of the automatic image captioning metrics. For
this purpose, we employ the binary (two-alternative) forced choice task introduced in (Hodosh …

… the user enters a web page URL, and the alt text checker identifies any images without
alt text. WATAA then uses an image captioning model to generate automatic alt text for each …

… To assess the role of visual features extracted from CLIPlike models in image captioning, …
features in standard and more challenging image captioning settings. We use the commonly …

… benchmark datasets, including COCO Captions and Flickr30k Captions. We also use XGPT
to generate image captions as data augmentation for the image retrieval task and achieve …

… auxiliary text, such as generating or editing an image … image captioning. Note that our method
does not employ the CLIP’s textual encoder, since there is no input text, and the output text …