Visual Question Generation

Problem Statement

• Give an image, the task is to generate natural Question based on the image.

Dataset

• Image Dataset-:MS-COCO and Question Dataset -: VQG-COCO

• Image Dataset-:Flickr and Question Dataset -: VQG-Bing

• Image Dataset-:Bing and Question Dataset -: VQG-Flickr

• Image Dataset-:MS-COCO and Question Dataset -: VQA-v1.0

• Image Dataset-:MS-COCO and Question Dataset -: Visual7W

Reference Paper for VQA

• Mostafazadeh, N., Misra, I., Devlin, J., Mitchell, M., He, X., & Vanderwende, L. (2016). Generating natural questions about an image. arXiv preprint arXiv:1603.06059.

• Zhang, S., Qu, L., You, S., Yang, Z., & Zhang, J. (2016). Automatic Generation of Grounded Visual Questions. arXiv preprint arXiv:1612.06530..

• Yang, Y., Li, Y., Fermuller, C., & Aloimonos, Y. (2015). Neural Self Talk: Image Understanding via Continuous Questioning and Answering. arXiv preprint arXiv:1512.03460.

• Mostafazadeh, N., Brockett, C., Dolan, B., Galley, M., Gao, J., Spithourakis, G. P., & Vanderwende, L. (2017). Image-grounded conversations: Multimodal context for natural question and response generation. arXiv preprint arXiv:1701.08251.

• Jain, Unnat, Ziyu Zhang, and Alexander Schwing. "Creativity: Generating Diverse Questions using Variational Autoencoders." arXiv preprint arXiv:1704.03493 (2017).