… captioning models. We evaluate SATIC model on the challenging MSCOCO [3] image
captioning … We present three examples of generated image captions in Figure 3. From the top …

… image alt-text, they may be of little use as user-written alttext is … auto-generated image
captions, we present Image Explorer, a touch-based image exploration system that divides image …

… richness to allow the captioning model to properly ground … image, and show qualitatively
and quantitatively that this can improve grounding. We validate our method on image captioning…

… image captions are generated via a text decoder block. To test the performance of the Turkish
image captioning … a benchmark dataset consisting of Turkish image captions, was used. In …

… Abstract—Image captioning is the description of an image with natural language … of many
image captioning applications. In this study, a novel automatic image captioning system based …

… models for image captioning. However, these models frequently produce generic captions
and may … , we also assess the captions through image-to-text and text-to-image retrieval tasks. …

… Secondly, as we will show in our results for image captioning, RNNs tend to produce
lower … Next, we describe an alternative convolutional approach to image captioning which …

… In this paper, we review a number of transformer-based image captioning models leading
up to the current state-of-the-art. Other reviews of image captioning models have been …

… not structured primarily as an image captioning dataset, each … on the down-stream task of
image captioning [42]. Transformer-… of artwork images with the goal to generate image captions …

… Therefore, we attempt to create a specialized image-text matching task within the news
image captioning task to align vision features with entity-aware textual features. Furthermore, …