We present a new dataset of image caption annotations, Conceptual Captions, which
contains an order of magnitude more images than the MS-COCO dataset (Lin et al., 2014) …

Two recent approaches have achieved state-of-the-art results in image captioning. The first
uses a pipelined process where a set of candidate words is generated by a convolutional …

Recently, the state-of-the-art models for image captioning have overtaken human
performance based on the most popular metrics, such as BLEU, METEOR, ROUGE and …

Image captioning is a multimodal problem that has drawn extensive attention in both the
natural language processing and computer vision community. In this paper, we present a …

Diversity is one of the most important properties in image captioning, as it reflects various
expressions of important concepts presented in an image. However, the most popular …

Image captioning models typically follow an encoder-decoder architecture which uses
abstract image feature vectors as input to the encoder. One of the most successful …

Inspired by retrieval-augmented language generation and pretrained Vision and Language
(V&L) encoders, we present a new approach to image captioning that generates sentences …

Modern image captioning models are usually trained with text similarity objectives. However,
since reference captions in public datasets often describe the most salient common objects …

Automatically generating a natural language description of an image is a fundamental
problem in artificial intelligence. This task involves both computer vision and natural …

Image captioning refers to automatic generation of descriptive texts according to the visual
content of images. It is a technique integrating multiple disciplines including the computer …