[ICCV 2021] Official implementation of the paper "TRAR: Routing the Attention Spans in Transformers for Visual Question Answering"
visualization
pytorch
transformer
attention
official
multi-modal
clevr
visual-question-answering
vision-and-language
dynamic-network
multi-modality
multi-modal-learning
multi-scale-features
vqav2
iccv2021
local-and-global
-
Updated
Oct 11, 2021 - Python