mlsanityData to 7 Oct 2026

Screen2Vec: Semantic Embedding of GUI Screens and GUI Components

arXiv 2101.11103 ↗First posted 11 Jan 2021cs.HCcited by 41

Not on the map. Why?

Abstract (arXiv)

Representing the semantics of GUI screens and components is crucial to data-driven computational methods for modeling user-GUI interactions and mining GUI designs. Existing GUI semantic representations are limited to encoding either the textual content, the visual design and layout patterns, or the app contexts. Many representation techniques also require significant manual data annotation efforts. This paper presents Screen2Vec, a new self-supervised technique for generating representations in embedding vectors of GUI screens and components that encode all of the above GUI features without requiring manual annotation using the context of user interaction traces. Screen2Vec is inspired by the word embedding method Word2Vec, but uses a new two-layer pipeline informed by the structure of GUIs and interaction traces and incorporates screen- and app-specific metadata. Through several sample downstream tasks, we demonstrate Screen2Vec's key useful properties: representing between-screen similarity through nearest neighbors, composability, and capability to represent user tasks.

Key facts. Cited by 41 papers in the map (data through 7 Oct 2026). First posted on arXiv 11 Jan 2021.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 6; 2022: 7; 2023: 6; 2024: 10; 2025: 8; 2026: 4.

41 papers.

Sort:

By area:

  1. 2021Screen2Words: Automatic Mobile UI Summarization with Multimodal Learningcited by 119
  2. 2022Jury Learning: Integrating Dissenting Voices into Machine Learning Modelscited by 115
  3. 2021CanvasVAE: Learning to Generate Vector Graphic Documentscited by 93
  4. 2022Enabling Conversational Interaction with Mobile UI using Large Language Modelscited by 66
  5. 2022A Dataset for Interactive Vision-Language Navigation with Unknown Command Feasibilitycited by 61
  6. 2023Explore, Select, Derive, and Recall: Augmenting LLM with Human-like Memory for Mobile Task Automationcited by 57
  7. 2024Mobile-Bench: An Evaluation Benchmark for LLM-based Mobile Agentscited by 56
  8. 2022Learning to Denoise Raw Mobile UI Layouts for Improving Datasets at Scalecited by 30
  9. 2021Mobile App Tasks with Iterative Feedback (MoTIF): Addressing Task Feasibility in Interactive Visual Environmentscited by 28
  10. 2021VUT: Versatile UI Transformer for Multi-Modal Multi-Task User Interface Modelingcited by 26
  11. 2022Towards Better Semantic Understanding of Mobile Interfacescited by 24
  12. 2025MobileSteward: Integrating Multiple App-Oriented Agents with Self-Evolution to Automate Cross-App Instructionscited by 16
29 more
  1. 2023UI Layout Generation with LLMs Guided by UI Grammarcited by 15
  2. 2024MobA: Multifaceted Memory-Enhanced Adaptive Planning for Efficient Mobile Task Automationcited by 14
  3. 2021Understanding Mobile GUI: from Pixel-Words to Screen-Sentencescited by 13
  4. 2023Automatic Macro Mining from Interaction Traces at Scalecited by 12
  5. 2025MP-GUI: Modality Perception with MLLMs for GUI Understandingcited by 12
  6. 2023Boosting GUI Prototyping with Diffusion Modelscited by 10
  7. 2022Predicting and Explaining Mobile UI Tappability with Vision Modeling and Saliency Analysiscited by 9
  8. 2021Creating User Interface Mock-ups from High-Level Text Descriptions with Deep-Learning Modelscited by 8
  9. 2024Graph4GUI: Graph Neural Networks for Representing Graphical User Interfacescited by 6
  10. 2025CHOP: Mobile Operating Assistant with Constrained High-frequency Optimized Subtask Planningcited by 6
  11. 2023DiLogics: Creating Web Automation Programs With Diverse Logicscited by 5
  12. 2024Tell Me What's Next: Textual Foresight for Generic UI Representationscited by 5
  13. 2024GUing: A Mobile GUI Search Engine using a Vision-Language Modelcited by 4
  14. 2024UI-JEPA: Towards Active Perception of User Intent through Onscreen User Activitycited by 4
  15. 2023Computational Approaches for App-to-App Retrieval and Design Consistency Checkcited by 3
  16. 2022GreaseVision: Rewriting the Rules of the Interfacecited by 2
  17. 2024HaHeAE: Learning Generalisable Joint Representations of Human Hand and Head Movements in Extended Realitycited by 2
  18. 2025MEGA-GUI: Multi-stage Enhanced Grounding Agents for GUI Elementscited by 2
  19. 2026IntentCUA: Learning Intent-level Representations for Skill Abstraction and Multi-Agent Planning in Computer-Use Agentscited by 2
  20. 2024AutoGameUI: Constructing High-Fidelity GameUI via Multimodal Correspondence Matchingcited by 1
  21. 2025Small Models, Big Results: Achieving Superior Intent Extraction through Decompositioncited by 1
  22. 2025Agent+P: Guiding UI Agents via Symbolic Planningcited by 1
  23. 2026Bridging Gulfs in UI Generation through Semantic Guidancecited by 1
  24. 2024Computer User Interface Understanding. A New Dataset and a Learning Frameworkcited by 0
  25. 2024AURORA: Navigating UI Tarpits via Automated Neural Screen Understandingcited by 0
  26. 2025ControlGUI: Guiding Generative GUI Exploration through Perceptual Visual Flowcited by 0
  27. 2025UISearch: Graph-Based Embeddings for Multimodal Enterprise UI Screenshots Retrievalcited by 0
  28. 2026A Benchmarking Framework for Context-aware XR Interfacescited by 0
  29. 2026GUITAR: Structured Failure Diagnosis of GUI Agents via State Transitionscited by 0