Multimodal Differential Network for Visual Question Generation
This addresses the challenge of visual question generation for AI systems, though it appears incremental as it builds on existing multimodal methods.
The paper tackles the problem of generating natural questions from images by using a Multimodal Differential Network to incorporate relevant visual and language contexts, resulting in substantial improvements over state-of-the-art benchmarks on metrics like BLEU, METEOR, ROUGE, and CIDEr.
Generating natural questions from an image is a semantic task that requires using visual and language modality to learn multimodal representations. Images can have multiple visual and language contexts that are relevant for generating questions namely places, captions, and tags. In this paper, we propose the use of exemplars for obtaining the relevant context. We obtain this by using a Multimodal Differential Network to produce natural and engaging questions. The generated questions show a remarkable similarity to the natural questions as validated by a human study. Further, we observe that the proposed approach substantially improves over state-of-the-art benchmarks on the quantitative metrics (BLEU, METEOR, ROUGE, and CIDEr).