The multi-modal fusion in visual question answering: a review of attention mechanisms

• Published in: PeerJ. Computer science Vol. 9; p. e1400
• Main Authors: Lu, Siyu, Liu, Mingzhe, Yin, Lirong, Yin, Zhengtong, Liu, Xuan, Zheng, Wenfeng
• Format: Journal Article
• Language: English
• Published: United States PeerJ. Ltd 30.05.2023; PeerJ Inc
• Subjects: Analysis; Artificial Intelligence; Attention; Attention mechanisms; Computational linguistics; Computer Vision; Fusion; Language processing; Machine vision; Multi-modal; Natural language interfaces; Visual question answering; VQA; Attention mechanisms; Multi-modal; Fusion; Visual question answering; Attention; VQA

Visual Question Answering (VQA) is a significant cross-disciplinary issue in the fields of computer vision and natural language processing that requires a computer to output a natural language answer based on pictures and questions posed based on the pictures. This requires simultaneous processing o...