Papers of the day   All papers

Fusion of Detected Objects in Text for Visual Question Answering

Comments

Aug 27 2019 Rowan Zellers

I'm excited but also overwhelmed by all the recent work on vision+language representation learning 😅 Where to start? Check out B2T2 https://arxiv.org/abs/1908.05054. It's a simple model for VCR: pass text and resnet features to BERT. Yet it's highly effective: https://visualcommonsense.com/leaderboard https://t.co/1fXBAngCI4
1 replies, 118 likes


Aug 27 2019 William Wang

https://t.co/Cng1KgTMV0
1 replies, 12 likes


Aug 28 2019 Aakash Kumar Nain 🔎

So everything has a BERT now! Looks like Transformers are having their "imagenet" moment
0 replies, 6 likes


Aug 27 2019 Rogue 🌻. Bigham

https://t.co/OwqpzS1Yjx
0 replies, 2 likes


Dec 31 2019 HotComputerScience

Most popular computer science paper of the day: "Fusion of Detected Objects in Text for Visual Question Answering" https://hotcomputerscience.com/paper/fusion-of-detected-objects-in-text-for-visual-question-answering https://twitter.com/rown/status/1166392863212486657
0 replies, 1 likes


Content