GQA

GQA is a new dataset for real-world visual reasoning and compositional question answering, seeking to address key shortcomings of previous visual question answering (VQA) datasets.

Papers using GQA (3)

Towards Open-vocabulary Scene Graph Generation With Prompt-based Finetuning2022 · 43 citesWeakly Supervised Grounding For VQA In Vision-language Transformers2022 · 14 citesScene-Graph ViT: End-to-End Open-Vocabulary Visual Relationship Detection2024 · 1 cites