gicheonkang / dan-visdial

✨ Official PyTorch Implementation for EMNLP'19 Paper, "Dual Attention Networks for Visual Reference Resolution in Visual Dialog"
https://www.aclweb.org/anthology/D19-1209
MIT License
45 stars 10 forks source link

Reproduce your result #6

Closed davidnvq closed 5 years ago

davidnvq commented 5 years ago

Thank you for publishing your code. it's such a great work appearing in EMNLP2019.

Could you provide us the pretrained model so that we can reproduce your result as reported in your paper?

Model NDCG MRR R@1 R@5 R@10 Mean
DAN 0.5759 0.6320 49.63 79.75 89.35 4.30
gicheonkang commented 5 years ago

Hi, @davidnvq
Sure, I updated the README.md file. You can download the pre-trained model to check the test-std performance. Thank you for your interests.