shannanyinxiang

South China University of TechnologyGuangzhou, China

Pinned Repositories

GPT-4V_OCR
Evaluation of the Optical Character Recognition (OCR) capabilities of GPT-4V(ision)
Language:Python122 8 54
PageNet
Official implementation of PageNet (IJCV 2022)
Language:Python80 2 611
SCUT-HEAD-Dataset-Release
SCUT HEAD is a large-scale head detection dataset, including 4405 images labeld with 111251 heads.
1 0 00
SPTS
Official implementation of SPTS: Single-Point Text Spotting (ACM MM 2022 Oral)
Language:Python138 7 1513
UPOCR
Official implementation of UPOCR: Towards unified pixel-level OCR interface (ICML 2024)
Language:Python45 2 44
ViTEraser
Official implementation of ViTEraser: Harnessing the Power of Vision Transformers for Scene Text Removal with SegMIM Pretraining (AAAI 2024)
Language:Python46 4 82

shannanyinxiang/SPTS
Official implementation of SPTS: Single-Point Text Spotting (ACM MM 2022 Oral)
Language:Python138 7 1513
shannanyinxiang/PageNet
Official implementation of PageNet (IJCV 2022)
Language:Python80 2 611
shannanyinxiang/ViTEraser
Official implementation of ViTEraser: Harnessing the Power of Vision Transformers for Scene Text Removal with SegMIM Pretraining (AAAI 2024)
Language:Python46 4 82
shannanyinxiang/UPOCR
Official implementation of UPOCR: Towards unified pixel-level OCR interface (ICML 2024)
Language:Python45 2 44
shannanyinxiang/SCUT-HEAD-Dataset-Release
SCUT HEAD is a large-scale head detection dataset, including 4405 images labeld with 111251 heads.
1 0 00