Describing UI Screenshots in Natural Language
نویسندگان
چکیده
Being able to describe any user interface (UI) screenshot in natural language can promote understanding of the main purpose UI, yet currently it cannot be accomplished with state-of-the-art captioning systems. We introduce XUI, a novel method inspired by global precedence effect create informative descriptions UIs, starting an overview and then providing fine-grained about most salient elements. XUI builds upon computational models for topic classification, visual saliency prediction, generation (NLG). provides up three different granularity levels that, together, what is do it. found that are highly readable, perceived accurately score similarly human-generated UI descriptions. available as open-source software.
منابع مشابه
Describing Video Contents in Natural Language
This contribution addresses generation of natural language descriptions for human actions, behaviour and their relations with other objects observed in video streams. The work starts with implementation of conventional image processing techniques to extract high level features from video. These features are converted into natural language descriptions using context free grammar. Although featur...
متن کاملDescribing Complex Charts in Natural Language: A Caption Generation System
Graphical presentations can be used to communicate information in relational data sets succinctly and effectively. However, novel graphical presentations that represent many attributes and relationships are often difficult to understand completely until explained. Automatically generated graphical presentations must therefore either be limited to generating simple, conventionalized graphical pr...
متن کاملDescribing Just-UI Concepts Using a Task Notation
A proposal for describing Just-UI patterns using a task oriented notation (ConcurTaskTrees) is presented. This work provides a method to convert a given pattern into a task tree and the contrary, to detect Just-UI patterns in task models. This bridge makes it possible to establish links between concepts from one model to the other one.
متن کاملMdl: a Language for Binding Ui Models
The model-based approach to UI design and synthesis is complicated by the need to bind behavior that is specified in one model to corresponding behavior in another model. In the Mastermind project, the problem concerns the binding of user-task and presentation models. We designed a powerful task language called MDL, and we compile MDL models into code that reifies the structure of a task model....
متن کاملDescribing Additive Fluents in Action Language
An additive fluent is a fluent with numerical values such that the effect of several concurrently executed actions on it can be computed by adding the effects of the individual actions. We propose a method for describing effects of actions on additive fluents in the declarative language C+. An implementation of this language, called the Causal Calculator, can be used for the automation of examp...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: ACM Transactions on Intelligent Systems and Technology
سال: 2022
ISSN: ['2157-6904', '2157-6912']
DOI: https://doi.org/10.1145/3564702