no code implementations • NAACL (maiworkshop) 2021 • Jaewoong Lee, Heejoon Lee, Hwanhee Lee, Kyomin Jung
Previous existing visual question answering (VQA) systems commonly use graph neural networks(GNNs) to extract visual relationships such as semantic relations or spatial relations.
no code implementations • 29 Sep 2021 • Jaeyoung Cheong, Heejoon Lee, Minjung Kang
Moreover, its performance can depend on which loss is used to train the model.