Multi-modal transformer architecture

"Spatially Aware Multimodal Transformers for TextVQA" poster #3236 on Aug. 27!

Yash Kant (@yash2kant), Dhruv Batra (@DhruvBatraDB), Peter Anderson (@panderson_me), Devi Parikh (@deviparikh), Jiasen Lu (@jiasenlu), Harsh Agrawal(@harsh_092)https://t.co/Qz1BIQquNp#ECCV2020 pic.twitter.com/oThr9MlmGj

— Allen Institute for AI (@allen_ai) August 26, 2020