badripatro / mdn-vqg Goto Github PK

1. Download VQG dataset from MicrosoftVQG site.
2. Create train,val and test json file.
3. Preprocess the MSCOCO image file using prepro/prepro_img.lua for joint model and prepro/prepro_img_att.lua for attention model.
4. Find the exemplar(Supporting and oppsing) Image using /data/knn_image.m
5. Run : th training.lua

@InProceedings{D18-1434,
  author = 	"Patro, Badri Narayana
		and Kumar, Sandeep
		and Kurmi, Vinod Kumar
		and Namboodiri, Vinay",
  title = 	"Multimodal Differential Network for Visual Question Generation",
  booktitle = 	"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing",
  year = 	"2018",
  publisher = 	"Association for Computational Linguistics",
  pages = 	"4002--4012",
  location = 	"Brussels, Belgium",
  url = 	"http://aclweb.org/anthology/D18-1434"
}