ofexe / PMTD
☆17Updated this week
Related projects: ⓘ
- Scene text rectification using glyph and character alignment properties☆20Updated 6 years ago
- Unconstrained Text Detection with Box Supervisionand Dynamic Self-Training☆33Updated last year
- Project code for ACM MM2020 paper: "TextRay: Contour-based Geometric Modeling for Arbitrary-shaped Scene Text Detection"☆47Updated 11 months ago
- ☆39Updated 4 years ago
- Tools for ICDAR2019 competitions(fifth place)☆11Updated 5 years ago
- ITN Project codes and models for CVPR 2018 paper: Geometry-Aware Scene Text Detection with Instance Transformation Network☆40Updated 4 years ago
- Position sensitive PreciseRoIPooling without roi coordinates gradient backward☆16Updated 6 years ago
- using pvanet framework train mobilenet-v2 for objects detection, papaer: https://arxiv.org/abs/1611.08588☆13Updated 5 years ago
- Unofficial implementation for SOLO instance segmentation☆25Updated 4 years ago
- Rethinking Bottleneck Structure for Efficient Mobile Network Design☆13Updated 4 years ago
- Detectron with VoVNet(CVPRW'19) backbone networks☆17Updated 5 years ago
- FCOS: Fully Convolutional One-Stage Object Detection (ICCV'19) https://arxiv.org/abs/1904.01355☆39Updated 4 years ago
- ☆27Updated 3 years ago
- ☆14Updated 4 years ago
- The code of 《HAM: Hidden Anchor Mechanism for Scene Text Detection》☆11Updated 3 years ago
- ☆10Updated this week
- Experiment results of implement Cascade RCNN under Detectron☆14Updated 5 years ago
- Multi-Oriented Scene Text Detection via Corner Localization and Region Segmentation☆22Updated 6 years ago
- ☆25Updated 3 years ago
- Geometry Normalization Networks for Accurate Scene Text Detection (iccv 2019)☆21Updated 4 years ago
- Pytorch implementation of Quadratic Additive Angular Margin Loss for Face Recognition☆35Updated 3 years ago
- ContextLab: A Toolbox for Context Feature Augmentation developed with PyTorch☆39Updated 4 years ago
- ☆11Updated this week
- Pytorch 1.0 codes(including cuda codes) for Deformable Convolution Version 2☆19Updated 5 years ago
- ☆23Updated this week
- The code is based on resnet50. At present, the data set hmean in icdar2015 is about 80. A rough version will be sorted out and optimized …☆8Updated 5 years ago
- Reconstruct ORN for pytorch1.0☆9Updated 2 years ago
- ☆15Updated this week
- siamise networks☆14Updated 7 years ago
- ☆21Updated 4 years ago