This repository contains the reference code for the paper Duel-Level Collaborative Transformer for Image Captioning.
please refer to m2 transformer
- Annotation. Download the annotation file annotation.zip
- Feature. You can download our ResNeXt-101 feature here. Access code: etrx.
[1] M2
[2] grid-feats-vqa
Thanks the original m2 and amazing work of grid-feats-vqa.