Question-guided hybrid convolution for visual question answering

• Main Authors: GAO, Peng, LU, Pan, LI, Hongsheng, LI, Shuang, LI, Yikang, HOI, Steven C. H., WANG, Xiaogang
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2018
• Subjects: VQA; Dynamic Parameter Prediction; Group Convolution; Databases and Information Systems; Theory and Algorithms
• Online Access: https://ink.library.smu.edu.sg/sis_research/4182; https://ink.library.smu.edu.sg/context/sis_research/article/5185/viewcontent/Question_GuidedHybridConvolution_2018_afv.pdf
• Institution: Singapore Management University

In this paper, we propose a novel Question-Guided Hybrid Convolution (QGHC) network for Visual Question Answering (VQA). Most state-of-the-art VQA methods fuse the high-level textual and visual features from the neural network and abandon the visual spatial information when learning multi-modal feat...