vidore/arxivqa_test_subsampled_ocr_chunk
Viewer
•
Updated
•
1.44k
•
44
ViDoRe Chunk OCR (baseline)
The original ViDoRe benchmark was passed to Unstructured to partition each page into chunks. Visual chunks are OCRized with tesseract.
-
-
vidore/docvqa_test_subsampled_ocr_chunk
Viewer • Updated • 1.24k • 42 -
vidore/infovqa_test_subsampled_ocr_chunk
Viewer • Updated • 2.78k • 41 -
vidore/tabfquad_test_subsampled_ocr_chunk
Viewer • Updated • 636 • 35 -
vidore/tatdqa_test_ocr_chunk
Viewer • Updated • 8.54k • 42 -
vidore/shiftproject_test_ocr_chunk
Viewer • Updated • 2.05k • 37 -
vidore/syntheticDocQA_artificial_intelligence_test_ocr_chunk
Viewer • Updated • 1.9k • 78 -
vidore/syntheticDocQA_energy_test_ocr_chunk
Viewer • Updated • 2.29k • 67 -
vidore/syntheticDocQA_government_reports_test_ocr_chunk
Viewer • Updated • 1.9k • 60 -
vidore/syntheticDocQA_healthcare_industry_test_ocr_chunk
Viewer • Updated • 2.17k • 61