… , and then a maximum entropy (ME) language model is used to arrange these words into a
… In this paper, we compare the merits of these different language modeling approaches for …

… for image captioning by utilizing pretrained language models (… image captioning. To our
knowledge, this is the first work that … large pretrained language models for image captioning. …

… statistical language modeling tasks and shows competitive performance in image captioning…
In this work, we present an image captioning model with language CNN to explore both …

… image captioning as a way to verbalize the information in the image, where the captions
are … Once the captions are generated, all the inference in our method is done using text-only …

… image captioning, provide a more comprehensive study on the scaling behavior via altering
data and model … as predicting the next token with language modeling, as shown in Figure 4 …

… for image captioning with multimodal neural language model… with structure-content neural
language model (SC-NLM). … which replaces feed-forward neural language model in [13]. …

… We observe that compared to the two cases where we do not use any pre-trained model
or use only the pre-trained language model (ie, BERT), using VLP significantly speedups the …

… a language model to generate the image captions. The recently proposed CLIP model contains
rich … it best for vision-language perception. Our key idea is that together with a pre-trained …

… Building on these developments, we propose to incorporate external language models
into visual captioning frameworks to aid and improve their capabilities both for description …

… To address this challenge, we leverage existing captions and explore augmenting them with
… the original captions using a large language model (LLM), yielding comprehensive image …