Creativity: Generating Diverse Questions Using Variational Autoencoders

@article{Jain2017CreativityGD,
  title={Creativity: Generating Diverse Questions Using Variational Autoencoders},
  author={Unnat Jain and Ziyu Zhang and A. Schwing},
  journal={2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2017},
  pages={5415-5424}
}
Generating diverse questions for given images is an important task for computational education, entertainment and AI assistants. Different from many conventional prediction techniques is the need for algorithms to generate a diverse set of plausible questions, which we refer to as creativity. In this paper we propose a creative algorithm for visual question generation which combines the advantages of variational autoencoders with long short-term memory networks. We demonstrate that our… Expand
Multimodal Differential Network for Visual Question Generation
Cross-Modal Generative Augmentation for Visual Question Answering
Evaluating for Diversity in Question Generation over Text
Improving Diversity of Image Captioning Through Variational Autoencoders and Adversarial Learning
  • Li Ren, Guo-Jun Qi, K. Hua
  • Computer Science
  • 2019 IEEE Winter Conference on Applications of Computer Vision (WACV)
  • 2019
Dual Learning for Visual Question Generation
D-PAGE: Diverse Paraphrase Generation
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 81 REFERENCES
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
Ask Your Neurons: A Neural-Based Approach to Answering Questions about Images
Generating Natural Questions About an Image
Describing Multimedia Content Using Attention-Based Encoder-Decoder Networks
Exploring Models and Data for Image Question Answering
Visual Madlibs: Fill in the blank Image Generation and Question Answering
Simple Baseline for Visual Question Answering
...
1
2
3
4
5
...