Image captioning, also called report generation in medical field, aims to describe visual
content of images in human language, which requires to model semantic relationship …

Methodologies that utilize Deep Learning offer great potential for applications that
automatically attempt to generate captions or descriptions about images and video frames …

Most existing Vision-and-Language (V&L) models rely on pre-trained visual encoders, using
a relatively small set of manually-annotated data (as compared to web-crawled data), to …

Abstract We propose Scene Graph Auto-Encoder (SGAE) that incorporates the language
inductive bias into the encoder-decoder image captioning framework for more human-like …

Vision Language Models (VLMs) have demonstrated remarkable performance in 2D vision
and language tasks. However, their ability to reason about spatial arrangements remains …

We present a novel attention mechanism: Causal Attention (CATT), to remove the ever-
elusive confounding effect in existing attention-based vision-language models. This effect …

Despite continuously improving performance, contemporary image captioning models are
prone to" hallucinating" objects that are not actually in a scene. One problem is that standard …

Despite improvements in performances on different natural language generation tasks, deep
neural models are prone to hallucinating facts that are incorrect or nonexistent. Different …

The advent of vision-language pre-training techniques enhanced substantial progress in the
development of models for image captioning. However, these models frequently produce …

Image captioning is an important task for benchmarking visual reasoning and for enabling
accessibility for people with vision impairments. However, as in many machine learning …