Bridging the Semantic Void: A Dual-branch RAG Framework to Enhance GUI Component Description for BVI Users
Open Access
- 13 April 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 90-101
Abstract
No abstract availableFunding Information
- National Natural Science Foundation of China (Grant No.6237 2408)
This publication has 31 references indexed in Scilit:
- OMNIPARSER: A Unified Framework for Text Spotting, Key Information Extraction and Table Recognition2024
- CogAgent: A Visual Language Model for GUI Agents2024
- Intern VL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks2024
- Reveal: Retrieval-Augmented Visual-Language Pre-Training with Multi-Source Multimodal Knowledge Memory2023
- Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data2021
- An insight into smartphone-based assistive solutions for visually impaired and blind people: issues, challenges and opportunitiesUniversal Access in the Information Society, 2020
- The Digital Divide and Older Adult Population Adoption, Use and Diffusion of Mobile Phones: a Quantitative StudyInformation Systems Frontiers, 2018
- Reverse Engineering Mobile Application User Interfaces with REMAUI (T)2015
- CIDEr: Consensus-based image description evaluation2015
- Learning visually grounded words and syntax of natural spoken languagePhonetics of the Origins and Evolution of Speech, 2001