BriefGPT.xyz
Aug, 2024
MSG-Chart: 多模态场景图用于图表问答
MSG-Chart: Multimodal Scene Graph for ChartQA
HTML
PDF
Yue Dai, Soyeon Caren Han, Wei Liu
TL;DR
本研究解决了自动图表问答中图表元素的复杂分布及数据模式难以识别的问题。提出的多模态场景图通过视觉图和文本图共同捕捉图表的结构和语义知识,显著提高了对图表元素的理解,进而在图表问答基准测试中表现优异。
Abstract
Automatic Chart Question Answering (
ChartQA
) is challenging due to the complex distribution of chart elements with patterns of the underlying data not explicitly displayed in charts. To address this challenge, we design a joint
→