Generating Question Relevant Captions to Aid Visual Question Answering

ACL 2019

Generating Question Relevant Captions to Aid Visual Question Answering

Jan 31, 2021
|
32 views
|
Details
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 better 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% in the Test-standard set using a single model) by simultaneously generating question-relevant captions. Authors: Jialin Wu, Zeyuan Hu, Raymond Mooney (University of Texas at Austin)

Comments
loading...