Skip to content

Latest commit

 

History

History
14 lines (10 loc) · 450 Bytes

README.md

File metadata and controls

14 lines (10 loc) · 450 Bytes
Raw

Bottom-Up Top-Down Attention for Image Captioning and Visual Question Answering (pytorch implementation)

This repository aims on implementing this CVPR2018 paper: Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering using PyTorch.

For simplification, region detection is done using YOLOv3 and only the image captioning model is implemented.

requirements:

hogehoge