Making the v in vqa matter: Elevating the role of image understanding in visual question answering. Goyal Y, Khot T, Summers-Stay D. Y Goyal, T Khot, D Summers-Stay… - Proceedings of the …, 2017 - openaccess.thecvf.com GSID: FF2PcVgEvv4J
Learning to reason: End-to-end module networks for visual question answering. Hu R, Andreas J, Rohrbach M. R Hu, J Andreas, M Rohrbach… - Proceedings of the …, 2017 - openaccess.thecvf.com GSID: XOTuvMKFIm4J
Making the v in vqa matter: Elevating the role of image understanding in visual question answering. Goyal Y, Khot T, Summers-Stay D. Y Goyal, T Khot, D Summers-Stay… - Proceedings of the …, 2017 - openaccess.thecvf.com GSID: FF2PcVgEvv4J
Film: Visual reasoning with a general conditioning layer. Perez E, Strub F, De H, Dumoulin V. E Perez, F Strub, H De Vries, V Dumoulin… - Proceedings of the …, 2018 - ojs.aaai.org GSID: OouENRu2JcwJ
A simple neural network module for relational reasoning. Santoro A, Raposo D, Barrett DG. A Santoro, D Raposo, DG Barrett… - Advances in neural …, 2017 - proceedings.neurips.cc GSID: pozT1_FQ0GkJ
