most citedSceneGATE: Scene-Graph based co-Attention networks for TExt visual question answering

8 citations · 8 across the 1 of their papers we have counts for

collaborators

1 paper

cs.CV2022★ 8 cited

SceneGATE: Scene-Graph based co-Attention networks for TExt visual question answering

Feiqi Cao, Siwen Luo, Felipe Nunez +3

Most TextVQA approaches focus on the integration of objects, scene texts and question words by a simple transformer encoder. But this fails to capture the semantic relations betwee…