Team PA-VCG's Solution for Competition on Understanding Chinese College Entrance Exam Papers in ICDAR'25

TL;DR

This paper describes Team PA-VCG's winning solution for the ICDAR'25 competition on understanding Chinese exam papers, utilizing high-resolution image processing, multi-image input, and domain-specific post-training to improve OCR accuracy.

Contribution

The paper introduces a novel combination of high-resolution processing, multi-image input, and domain-specific post-training strategies for document understanding in complex exam papers.

Findings

Achieved 89.6% accuracy, winning the competition.

Post-training strategies significantly improved OCR performance.

Effective handling of dense OCR extraction and complex layouts.

Abstract

This report presents Team PA-VGG's solution for the ICDAR'25 Competition on Understanding Chinese College Entrance Exam Papers. In addition to leveraging high-resolution image processing and a multi-image end-to-end input strategy to address the challenges of dense OCR extraction and complex document layouts in Gaokao papers, our approach introduces domain-specific post-training strategies. Experimental results demonstrate that our post-training approach achieves the most outstanding performance, securing first place with an accuracy rate of 89.6%.