Pinned Repositories
GoMatching
GoMatching: A Simple Baseline for Video Text Spotting via Long and Short Term Matching
Rethinking-Text-Segmentation
[CVPR 2021] Rethinking Text Segmentation: A Novel Dataset and A Text-Specific Refinement Approach
DeepSolo
The official repo for [CVPR'23] "DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text Spotting" & [ArXiv'23] "DeepSolo++: Let Transformer Decoder with Explicit Points Solo for Multilingual Text Spotting"
I3CL
The official repo for [IJCV'22] "I3CL: Intra- and Inter-Instance Collaborative Learning for Arbitrary-shaped Scene Text Detection"
ViTAE-Transformer-Scene-Text-Detection
A comprehensive list [I3CL@IJCV'22, DPText-DETR@AAAI'23, DeepSolo(++)@ CVPR'23] of our research works related to scene text detection and spotting, including papers, codes. Note: The official repo for "I3CL: Intra- and Inter-Instance Collaborative Learning for Arbitrary-shaped ..." has been moved to: https://github.com/ViTAE-Transformer/I3CL
SRSTS
This is the official implementation of the paper "Decoupling recognition from detection: Single shot self-reliant scene text spotter" and "Single Shot Self-Reliant Scene Text Spotter by Decoupled yet Collaborative Detection and Recognition".
TextFuseNet
A PyTorch implementation of "TextFuseNet: Scene Text Detection with Richer Fused Features".
DPText-DETR
[AAAI'23 Oral] DPText-DETR: Towards Better Scene Text Detection with Dynamic Points in Transformer
GroundingDINO
Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"
Hi-SAM
[arXiv preprint] Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentation
ymy-k's Repositories
ymy-k/DPText-DETR
[AAAI'23 Oral] DPText-DETR: Towards Better Scene Text Detection with Dynamic Points in Transformer
ymy-k/Hi-SAM
[arXiv preprint] Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentation
ymy-k/GroundingDINO
Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"