Learning effective fusion of multi-modality features is at the heart of visual question answering. We propose a novel method of dynamically fusing multi-modal features with intra- and inter-modality information flow, which alternatively pass dynamic information between and across the visual and language modalities. It can robustly capture the high-level interactions between language and vision domains, thus significantly improves the performance of visual question answering. We also show that the proposed dynamic intra-modality attention flow conditioned on the other modality can dynamically modulate the intra-modality attention of the target modality, which is vital for multimodality feature fusion. Experimental evaluations on the VQA 2.0 dataset show that the proposed method achieves state-of-the-art VQA performance. Extensive ablation studies are carried out for the comprehensive analysis of the proposed method.
@article{arxiv.1812.05252,
title = {Dynamic Fusion with Intra- and Inter- Modality Attention Flow for Visual Question Answering},
author = {Gao Peng and Zhengkai Jiang and Haoxuan You and Pan Lu and Steven Hoi and Xiaogang Wang and Hongsheng Li},
journal= {arXiv preprint arXiv:1812.05252},
year = {2019}
}