google-research-datasets / screen2words
The dataset includes screen summaries that describes Android app screenshot's functionalities. It is used for training and evaluation of the screen2words models (our paper accepted by UIST'21 will be linked soon).
☆54Updated 3 years ago
Alternatives and similar repositories for screen2words:
Users that are interested in screen2words are comparing it to the libraries listed below
- Mobile App Tasks with Iterative Feedback (MoTIF): Addressing Task Feasibility in Interactive Visual Environments☆60Updated 7 months ago
- The dataset includes widget captions that describes UI element's functionalities. It is used for training and evaluation of the widget ca…☆20Updated 3 years ago
- Consists of ~500k human annotations on the RICO dataset identifying various icons based on their shapes and semantics, and associations b…☆28Updated 8 months ago
- ScreenQA dataset was introduced in the "ScreenQA: Large-Scale Question-Answer Pairs over Mobile App Screenshots" paper. It contains ~86K …☆107Updated last month
- It includes two datasets that are used in the downstream tasks for evaluating UIBert: App Similar Element Retrieval data and Visual Item …☆41Updated 3 years ago
- This repository contains the opensource version of the datasets were used for different parts of training and testing of models that grou…☆32Updated 4 years ago
- Official implementation for "You Only Look at Screens: Multimodal Chain-of-Action Agents" (Findings of ACL 2024)☆223Updated 8 months ago
- The dataset includes UI object type labels (e.g., BUTTON, IMAGE, CHECKBOX) that describes the semantic type of an UI object on Android ap…☆49Updated 3 years ago
- The Screen Annotation dataset consists of pairs of mobile screenshots and their annotations. The annotations are in text format, and desc…☆63Updated last year
- A curated mobile app design database☆60Updated 3 years ago
- (ICLR 2025) The Official Code Repository for GUI-World.☆53Updated 3 months ago
- Seq2act: Mapping Natural Language Instructions to Mobile UI Action Sequences from Google research☆13Updated 4 years ago
- GUICourse: From General Vision Langauge Models to Versatile GUI Agents☆103Updated 8 months ago
- ☆111Updated last year
- Recognize graphic user interface layout through grouping GUI elements according to their visual attributes☆40Updated 2 years ago
- ☆13Updated 10 months ago
- GUI Odyssey is a comprehensive dataset for training and evaluating cross-app navigation agents. GUI Odyssey consists of 7,735 episodes fr…☆96Updated 4 months ago
- Screen2Vec is a new self-supervised technique for generating more comprehensive semantic embeddings of GUI screens and components using t…☆69Updated last month
- A Universal Platform for Training and Evaluation of Mobile Interaction☆42Updated 3 weeks ago
- Official implementation for "Android in the Zoo: Chain-of-Action-Thought for GUI Agents" (Findings of EMNLP 2024)☆77Updated 5 months ago
- GPT-4V in Wonderland: LMMs as Smartphone Agents☆134Updated 8 months ago
- ☆32Updated 9 months ago
- VINS: Visual Search for Mobile User Interface Design☆36Updated 4 years ago
- [ICLR 2024] MetaTool Benchmark for Large Language Models: Deciding Whether to Use Tools and Which to Use☆85Updated last year
- ☆39Updated 8 months ago
- [ICLR'25 Oral] UGround: Universal GUI Visual Grounding for GUI Agents☆189Updated this week
- [EMNLP 2022] The baseline code for META-GUI dataset☆12Updated 8 months ago
- VisualWebArena is a benchmark for multimodal agents.☆318Updated 4 months ago
- [NeurIPS 2024] Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?☆119Updated 6 months ago
- The model, data and code for the visual GUI Agent SeeClick☆339Updated 4 months ago