Method: GPT-4 Vision Turbo + Amazon Textract OCR - Task 3 - Infographics VQA - Document Visual Question Answering - Robust Reading Competition

method: GPT-4 Vision Turbo + Amazon Textract OCR2024-05-31

Authors: Unofficial

Description: GPT-4 Vision Turbo with 2048px images (longer side) and output of Amazon Textract OCR. See the paper for details.

@misc{borchmann2024notes, title={Notes on Applicability of GPT-4 to Document Understanding}, author={Łukasz Borchmann}, year={2024}, eprint={2405.18433}, archivePrefix={arXiv}, primaryClass={cs.CL} }