Deep Modular Bilinear Attention Network for Visual Question Answering

• Published in: Sensors (Basel, Switzerland) Vol. 22; no. 3; p. 1045
• Main Authors: Yan, Feng, Silamu, Wushouer, Li, Yanbing
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 28.01.2022; MDPI
• Subjects: attention mechanism; Bans; bilinear attention network; Language; multi-model; Natural Language Processing; Research Design; visual question answering; bilinear attention network; multi-model; visual question answering; attention mechanism

VQA (Visual Question Answering) is a multi-model task. Given a picture and a question related to the image, it will determine the correct answer. The attention mechanism has become a de facto component of almost all VQA models. Most recent VQA approaches use dot-product to calculate the intra-modali...