RK-VQA: Rational knowledge-aware fusion-in-decoder for knowledge-based visual question answering

作者：Weipeng Chen, Xu Huang, Zifeng Liu, Jin Liu, Jin Liu, Lan Yo · 发表于：Information Fusion · 年份：2025 · DOI：10.1016/j.inffus.2025.102969 · 被引用次数：4 · 研究领域：Multimodal Machine Learning Applications、Advanced Image and Video Retrieval Techniques、Human Pose and Action Recognition