Dual-Spatial Normalized Transformer for Image Captioning. Engineering Applications of Artificial Intelligence (EAAI 2023)
-
Updated
Sep 19, 2023 - Python
Dual-Spatial Normalized Transformer for Image Captioning. Engineering Applications of Artificial Intelligence (EAAI 2023)
Spatial text browser execution layer for AI agents. 10x cheaper than screenshots.
Geometric Data Encoding Demonstration (NOT SECURE)
User Manual
Convert web page screenshots into text for AI agents, enabling faster, cheaper processing without vision encoders.
To associate your repository with the spatial-encoding topic, visit your repo's landing page and select "manage topics."