Scene Graph Generation

Unpaired Image Captioning via Scene Graph Alignments

Most of the existing deep learning based image captioning methods are fully-supervised models, which require large-scale paired image-caption datasets. However, getting large scale image-caption paired data is labor-intensive and time-consuming. In …

Scene Graph Generation with External Knowledge and Image Reconstruction

Scene graph generation has received growing attention with advancement image understanding tasks such as object detection, attributes and relationship prediction, etc. However, existing datasets are biased in terms of object and relationship labels, …