Abstract
Being able to describe any user interface (UI) screenshot in natural language can promote understanding of the main purpose of the UI, yet currently it cannot be accomplished with state-of-the-art captioning systems. We introduce XUI, a novel method inspired by the global precedence effect to create informative descriptions of UIs, starting with an overview and then providing fine-grained descriptions about the most salient elements. XUI builds upon computational models for topic classification, visual saliency prediction, and natural language generation. XUI provides descriptions with up to three different granularity levels that, together, describe what is in the interface and what the user can do with it. We found that XUI descriptions are highly readable, are perceived to accurately describe the UI, and score similarly to human-generated UI descriptions. XUI is available as open source software.
Research highlights
- A data-driven method to create informative descriptions of UI screenshots in natural language.
- Validation of the method via objective and subjective evaluations: our method compares favorably to human-generated captions.
- A set of reusable software libraries and computational models, to facilitate further research and applications.
Resources
- Paper (PDF, 7 MB)
- Supplementary materials (PDF, 780 KB)
- Software and trained models (ZIP, 454 MB)
- Datasets: XUI Caption · XUI Simple · XUI Detailed · MS Azure · Human
Citation
- Luis A. Leiva, Asutosh Hota, Antti Oulasvirta. Describing UI Screenshots in Natural Language. ACM Transactions on Intelligent Systems and Technology 14(1), 2022.
@Article{Leiva22_xui, author = {Luis A. Leiva and Asutosh Hota and Antti Oulasvirta}, title = {Describing UI Screenshots in Natural Language}, journal = {ACM Transactions on Intelligent Systems and Technology}, volume = {14}, number = {1}, year = {2022}, }
Disclaimer
Our software is free for scientific use (licensed under the MIT license). The software must not be distributed without prior permission of the authors. Please contact us if you are planning to use the software for commercial purposes. The authors are not responsible for any implication derived from the use of this software.