Table Transformer Structure Recognition
Microsoft's Table Transformer Structure Recognition is a vision model that excels at detecting table structures, such as rows and columns, from images. It is built on the Transformer-based object detection architecture, equivalent to DETR, with a notable technical trait of applying layernorm before self- and cross-attention.
Input
Output
Context
1K
Max Output
-
Parameters
28.8M
Technical Specifications
Model TypeVision
Context Window1,024 tokens
Max Output TokensNot available
Parameters28.8M
Release DateOct 14, 2022
Training CutoffNot available
Licensemit
Open SourceYes
Input Modalities
Image
Output Modalities
Text
Capabilities
Resources & Links
Estimated GPU Requirements for Table Transformer Structure Recognition
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Jun 23, 2026
Start building with the right model.
Automatically route workloads to the right model for every task, every time.