Tingquan/PP-OCRv5_mobile_rec
Image-to-Text • Updated • 8
Tingquan Gao
Tingquan
AI & ML interests
None yet
Recent Activity
authored a paper 1 day ago
RT-DocLayout: Real-Time End-to-End Document Layout Analysis with Reading Order in the Wild authored a paper 1 day ago
PP-OCRv6: From 1.5M to 34.5M Parameters, Surpassing Billion-Scale VLMs on OCR Tasks authored a paper 1 day ago
PP-OCRv5: A Specialized 5M-Parameter Model Rivaling Billion-Parameter Vision-Language Models on OCR TasksOrganizations
