Research Area:  Machine Learning
The recently emerged research of Visual Question Answering (VQA) has become a hot topic in computer vision. A key solution to VQA exists in how to fuse multimodal features extracted from image and question. In this paper, we show that combining visual relationship and attention together achieves more fine-grained feature fusion. Specifically, we design an effective and efficient module to reason complex relationship between visual objects. In addition, a bilinear attention module is learned for question guided attention on visual objects, which allows us to obtain more discriminative visual features. Given an image and a question in natural language, our VQA model learns visual relational reasoning network and attention network in parallel to fuse fine-grained textual and visual features, so that answers can be predicted accurately. Experimental results show that our approach achieves new state-of-the-art performance of single model on both VQA 1.0 and VQA 2.0 datasets.
Keywords:  
Multimodal fusion
Visual question answering
Visual relational reasoning
Attention mechanism
Author(s) Name:  Weifeng Zhang, Jing Yu, Hua Hu, Haiyang Hu, Zengchang Qin
Journal name:  Information Fusion
Conferrence name:  
Publisher name:  Elsevier
DOI:  10.1016/j.inffus.2019.08.009
Volume Information:  Volume 55, March 2020, Pages 116-126
Paper Link:   https://www.sciencedirect.com/science/article/abs/pii/S1566253518308248