Deep Multi-Module Based Language Priors Mitigation Model for Visual Question Answering

• Published in: 东华大学学报（英文版） Vol. 40; no. 6; pp. 684 - 694
• Main Authors: YU Shoujian, JIN Xueqin, WU Guowen, SHI Xiujin, ZHANG Hong
• Format: Journal Article
• Language: English
• Published: 31.12.2023
• Subjects: multimodal fusion; visual question answering(VQA); natural language processing; language priors; computer vision

TP391%TP3-05; The original intention of visual question answering(VQA)models is to infer the answer based on the relevant information of the question text in the visual image,but many VQA models often yield answers that are biased by some prior knowledge,especially the language priors.This paper pro...