MORAN_v2
Scene Text Recognizer
A deep learning framework for scene text recognition with rectification and attention mechanisms.
MORAN: A Multi-Object Rectified Attention Network for Scene Text Recognition
639 stars
24 watching
152 forks
Language: Python
last commit: 8 months ago attention-mechanismimage-deformationimage-rectificationscene-textscene-text-recognition
Related projects:
Repository | Description | Stars |
---|---|---|
| An implementation of a recurrent convolutional neural network for scene labeling | 5 |
| Provides pre-trained deep learning models for scene classification on the Places365 dataset | 1,935 |
| A Python package implementing an interpretable machine learning model for text classification with visualization tools | 336 |
| A research project focused on developing algorithms and models to accurately detect and recognize text in images and videos from various scenes. | 368 |
| A deep learning framework for semantic segmentation with spatial attention mechanisms | 218 |
| A Python implementation of a depth-induced multi-scale recurrent attention network for RGB-D saliency detection | 105 |
| An image classification model for recognizing physical places and locations | 41 |
| Unsupervised feature learning by image inpainting using Generative Adversarial Networks (GANs) | 887 |
| An approach to reduce object hallucinations in large vision-language models by contrasting output distributions derived from original and distorted visual inputs | 222 |
| A deep neural network architecture that predicts visual features from text to improve image and video caption retrieval | 69 |
| A deep learning framework for object detection tasks using a novel neural network architecture | 355 |
| A software framework for scene graph parsing with global context using PyTorch and Visual Genome data. | 526 |
| Develops CTC-based text recognition models with neural network architectures | 259 |
| A Gluon implementation of Residual Attention Network for image classification tasks | 108 |
| Deep learning-based system to recognize and classify 12306 captcha images | 281 |