Douwe Kiela Suvrat Bhooshan Hamed Firooz Davide Testuggine Supervised Multimodal Bitransformers for Classifying Images and Text. 2019 ViGIL@NeurIPS https://vigilworkshop.github.io/static/papers/40.pdf conf/nips/2019vigil db/conf/nips/vigil2019.html#KielaBFT19