Generating Question Relevant Captions to Aid Visual Question Answering
arXiv:1906.00513
Abstract
Visual question answering (VQA) and image captioning require a shared body of general knowledge connecting language and vision. We present a novel approach to improve VQA performance that exploits this connection by jointly generating captions that are targeted to help answer a specific visual question. The model is trained using an existing caption dataset by automatically determining question-relevant captions using an online gradient-based method. Experimental results on the VQA v2 challenge demonstrates that our approach obtains state-of-the-art VQA performance (e.g. 68.4% on the Test-standard set using a single model) by simultaneously generating question-relevant captions.
arXiv commentACL 2019 camera-ready
References in corpus (9)
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- Microsoft COCO Captions: Data Collection and Evaluation Server
- VQA: Visual Question Answering
- Exploring Models and Data for Image Question Answering
- Self-Critical Reasoning for Robust Visual Question Answering
- Discriminability objective for training descriptive captions
- Tell-and-Answer: Towards Explainable Visual Question Answering using Attributes and Captions
- Action Recognition with Joint Attention on Multi-Level Deep Features
- Faithful Multimodal Explanation for Visual Question Answering