CVPR 2018 Oral：Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering

题目：Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering 作者 : Peter Anderson , Xiaodong He , Chris Buehler , Damien Tency 论文地址[https://arxiv.org/abs/1707.07998] 1.解决的问题 I

>>阅读原文<<