1 result found Sort:

rentainhe
TRAR-VQA rentainhe
18
65
mit
3
[ICCV 2021] Official implementation of the paper "TRAR: Routing the Attention Spans in Transformers for Visual Question Answering"
clevr vqav2 pytorch iccv2021 official attention multi-modal transformer visualization multi-modality dynamic-network local-and-global vision-and-language multi-modal-learning multi-scale-features visual-question-answering
Created 2021-07-23
61 commits to main branch, last one 3 years ago