Connecting Vision and Language plays an essential role in Generative Intelligence. For this
reason, large research efforts have been devoted to image captioning, ie describing images …

This article offers a comprehensive review of the research on Natural Language Generation
(NLG) over the past two decades, especially in relation to data-to-text generation and text-to …

The automatic generation of radiology reports has the potential to assist radiologists in the
time-consuming task of report writing. Existing methods generate the full report from image …

Existing research addresses scene graph generation (SGG)—a critical technology for scene
understanding in images—from a detection perspective, ie., objects are detected using …

Abstract Scene Graph Generation, which generally follows a regular encoder-decoder
pipeline, aims to first encode the visual contents within the given image and then parse them …

The limited availability of annotated data often hinders real-world applications of machine
learning. To efficiently learn from small quantities of multimodal data, we leverage the …

Most text-driven human motion generation methods employ sequential modeling
approaches, eg, transformer, to extract sentence-level text representations automatically and …

Scene graph is a structured representation of a scene that can clearly express the objects,
attributes, and relationships between objects in the scene. As computer vision technology …

Graph Neural Networks (GNNs) have gained momentum in graph representation learning
and boosted the state of the art in a variety of areas, such as data mining (eg, social network …

Abstract Human-Object Interaction Detection tackles the problem of joint localization and
classification of human object interactions. Existing HOI transformers either adopt a single …