… SMALLCAP, an image captioning model, prompted with captions retrieved from an external
datastore of text, based on the input image. This formulation of image captioning enables a …

… In this paper, we investigate the development of a retrieval component for image captioning.
… -augmented attention layer to predict tokens based on the past context and on text retrieved …

… Inspired by retrieval-augmented language generation and pretrained Vision and Language
(… to image captioning that generates sentences given the input image and a set of captions re…

… retrieval data set, which for image captioning can be up to billions of examples. To search
over this large memory bank rapidly, we adopt FAISS (Johnson, Douze, and Jegou 2019), an …

… We evaluate the robustness of a single retrievalaugmented image captioning model in
this study. Given variations in training process and model structures, the observed model …

… Large language models (LLMs)-based image captioning has the capability of describing …
retrievalaugmented image captioning method that prompts LLMs with object names retrieved …

… visually impaired people improve a human-computer interactions by introducing visual
concepts to a computer and create better features for information retrieval using images [2,3]. …

… image captioning benchmarks. We aim to demonstrate the superiority of our retrieval
augmentation … and relevance of generated captions through retrieving relevant knowledge from …

… Concretely, RAMP treats the retrieved captions as reference captions to augment the … the
image captioning model (generator) to incorporate informative content in retrieved captions into …

… In particular, we explore the benefits of augmenting artwork datasets for image captioning.
To this end, we leverage both textual descriptions of the paintings and a diffusion model to …