5 papers
Flint: A Semantics-Driven Data Visualization Intermediate Language
Yunhai Wang, Kecheng Lu, Junhao Chen +2
We present Flint, an intermediate language that enables authors to create high-quality visualizations from concise, semantics-driven specifications without explicitly configuring l…
Generalization of CNNs on Relational Reasoning with Bar Charts
Zhenxing Cui, Lu Chen, Yunhai Wang +3
This paper presents a systematic study of the generalization of convolutional neural networks (CNNs) and humans on relational reasoning tasks with bar charts. We first revisit prev…
Color-Name Aware Optimization to Enhance the Perception of Transparent Overlapped Charts
Kecheng Lu, Lihang Zhu, Yunhai Wang +3
Transparency is commonly utilized in visualizations to overlay color-coded histograms or sets, thereby facilitating the visual comparison of categorical data. However, these charts…
SPAC-Net: Rethinking Point Cloud Completion with Structural Prior
Zizhao Wu, Jian Shi, Xuan Deng +4
Point cloud completion aims to infer a complete shape from its partial observation. Many approaches utilize a pure encoderdecoder paradigm in which complete shape can be directly p…
ChartInsights: Evaluating Multimodal Large Language Models for Low-Level Chart Question Answering
Yifan Wu, Lutao Yan, Leixian Shen +3
Chart question answering (ChartQA) tasks play a critical role in interpreting and extracting insights from visualization charts. While recent advancements in multimodal large langu…