The State of the Art in Creating Visualization Corpora for Automated Chart Analysis
arXiv:2305.14525 · doi:10.1111/cgf.14855
Abstract
We present a state-of-the-art report on visualization corpora in automated chart analysis research. We survey 56 papers that created or used a visualization corpus as the input of their research techniques or systems. Based on a multi-level task taxonomy that identifies the goal, method, and outputs of automated chart analysis, we examine the property space of existing chart corpora along five dimensions: format, scope, collection method, annotations, and diversity. Through the survey, we summarize common patterns and practices of creating chart corpora, identify research gaps and opportunities, and discuss the desired properties of future benchmark corpora and the required tools to create them.
arXiv commentTo appear at EuroVis 2023
References in corpus (11)
- A Comprehensive Survey on Graph Neural Networks
- Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
- Learning Visual Importance for Graphic Designs and Data Visualizations
- A Survey on ML4VIS: Applying Machine Learning Advances to Data Visualization
- Towards Automated Infographic Design: Deep Learning-based Auto-Extraction of Extensible Timeline
- Searching the Visual Style and Structure of D3 Visualizations
- Structure-aware Visualization Retrieval
- VisImages: A Fine-Grained Expert-Annotated Visualization Dataset
- Learning Style Similarity for Searching Infographics
- ChartNet: Visual Reasoning over Statistical Charts using MAC-Networks
- Synthetically Trained Icon Proposals for Parsing and Summarizing Infographics