DreamStruct: Understanding Slides and User Interfaces via Synthetic Data Generation
Abstract
Enabling machines to understand structured visuals like slides and user interfaces is essential for making them accessible to people with disabilities. However, achieving such understanding computationally has required manual data collection and annotation, which is time-consuming and labor-intensive. To overcome this challenge, we present a method to generate synthetic, structured visuals with target labels using code generation. Our method allows people to create datasets with built-in labels and train models with a small number of human-annotated examples. We demonstrate performance improvements in three tasks for understanding slides and UIs: recognizing visual elements, describing visual content, and classifying visual content types.
Cite
Text
Peng et al. "DreamStruct: Understanding Slides and User Interfaces via Synthetic Data Generation." Proceedings of the European Conference on Computer Vision (ECCV), 2024. doi:10.1007/978-3-031-72691-0_26Markdown
[Peng et al. "DreamStruct: Understanding Slides and User Interfaces via Synthetic Data Generation." Proceedings of the European Conference on Computer Vision (ECCV), 2024.](https://mlanthology.org/eccv/2024/peng2024eccv-dreamstruct/) doi:10.1007/978-3-031-72691-0_26BibTeX
@inproceedings{peng2024eccv-dreamstruct,
title = {{DreamStruct: Understanding Slides and User Interfaces via Synthetic Data Generation}},
author = {Peng, Yi-Hao and Huq, Faria and Jiang, Yue and Wu, Jason and Li, Xin Yue and Bigham, Jeffrey and Pavel, Amy},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
year = {2024},
doi = {10.1007/978-3-031-72691-0_26},
url = {https://mlanthology.org/eccv/2024/peng2024eccv-dreamstruct/}
}