← all datasets

OCRBench

Emerging

3papers using it

2024first seen

🔎 Find this dataset

Papers using OCRBench (3)

Qianfan-vl: Domain-enhanced Universal Vision-language Models2025

Reid5o: Achieving Omni Multi-modal Person Re-identification In A Single Model2025

TextSquare: Scaling up Text-Centric Visual Instruction Tuning2024 · 1 cites

OCRBench — datasets — multimodal