Leveraging large models for crafting narrative visualization: a survey

Y He, S Cao, Y Shi, Q Chen, K Xu, N Cao - arXiv preprint arXiv …, 2024 - arxiv.org
Narrative visualization effectively transforms data into engaging stories, making complex
information accessible to a broad audience. Large models, essential for narrative …

Chart4blind: An intelligent interface for chart accessibility conversion

O Moured, M Baumgarten-Egemole, K Müller… - Proceedings of the 29th …, 2024 - dl.acm.org
In a world driven by data visualization, ensuring the inclusive accessibility of charts for Blind
and Visually Impaired (BVI) individuals remains a significant challenge. Charts are usually …

TTC-QuAli: A Text-Table-Chart Dataset for Multimodal Quantity Alignment

H Dong, H Wang, A Zhou, Y Hu - … Conference on Web Search and Data …, 2024 - dl.acm.org
In modern documents, numerical information is often presented using multimodal formats
such as text, tables, and charts. However, the heterogeneity of these sources poses a …

SIMPLOT: Enhancing Chart Question Answering by Distilling Essentials

W Kim, S Park, Y In, S Han, C Park - arXiv preprint arXiv:2405.00021, 2024 - arxiv.org
Recently, interpreting complex charts with logical reasoning have emerged as challenges
due to the development of vision-language models. A prior state-of-the-art (SOTA) model …

AltChart: Enhancing VLM-based Chart Summarization Through Multi-Pretext Tasks

O Moured, J Zhang, MS Sarfraz… - arXiv preprint arXiv …, 2024 - arxiv.org
Chart summarization is a crucial task for blind and visually impaired individuals as it is their
primary means of accessing and interpreting graphical data. Crafting high-quality …

ChartReformer: Natural Language-Driven Chart Image Editing

P Yan, M Bhosale, J Lal, B Adhikari… - arXiv preprint arXiv …, 2024 - arxiv.org
Chart visualizations are essential for data interpretation and communication; however, most
charts are only accessible in image format and lack the corresponding data tables and …

mChartQA: A universal benchmark for multimodal Chart Question Answer based on Vision-Language Alignment and Reasoning

J Wei, N Xu, G Chang, Y Luo, BH Yu, R Guo - arXiv preprint arXiv …, 2024 - arxiv.org
In the fields of computer vision and natural language processing, multimodal chart question-
answering, especially involving color, structure, and textless charts, poses significant …

Evaluating Task-based Effectiveness of MLLMs on Charts

Y Wu, L Yan, Y Luo, Y Wang, N Tang - arXiv preprint arXiv:2405.07001, 2024 - arxiv.org
In this paper, we explore a forward-thinking question: Is GPT-4V effective at low-level data
analysis tasks on charts? To this end, we first curate a large-scale dataset, named …