A5086745879- Advanced Image and Video Retrieval Techniques
- Vehicle License Plate Recognition
- Handwritten Text Recognition Techniques
- Advanced Neural Network Applications
- Domain Adaptation and Few-Shot Learning
- Natural Language Processing Techniques
- Multimodal Machine Learning Applications
- Video Analysis and Summarization
- Machine Learning and Data Classification
Nanjing University
2019-2023
University of Hong Kong
2019
Novel (United States)
2019
In this paper, we introduce an anchor-box free and single shot instance segmentation method, which is conceptually simple, fully convolutional can be used by easily embedding it into most off-the-shelf detection methods. Our termed PolarMask, formulates the problem as predicting contour of through center classification dense distance regression in a polar coordinate. Moreover, propose two effective approaches to deal with sampling high-quality examples optimization for regression,...
Scene text detection, an important step of scene reading systems, has witnessed rapid development with convolutional neural networks. Nonetheless, two main challenges still exist and hamper its deployment to real-world applications. The first problem is the trade-off between speed accuracy. second one model arbitrary-shaped instance. Recently, some methods have been proposed tackle but they rarely take entire pipeline into consideration, which may fall short in practical In this paper, we...
In this paper, we introduce an anchor-box free and single shot instance segmentation method, which is conceptually simple, fully convolutional can be used as a mask prediction module for segmentation, by easily embedding it into most off-the-shelf detection methods. Our termed PolarMask, formulates the problem center classification dense distance regression in polar coordinate. Moreover, propose two effective approaches to deal with sampling high-quality examples optimization regression,...
Scene text detection, an important step of scene reading systems, has witnessed rapid development with convolutional neural networks. Nonetheless, two main challenges still exist and hamper its deployment to real-world applications. The first problem is the trade-off between speed accuracy. second one model arbitrary-shaped instance. Recently, some methods have been proposed tackle but they rarely take entire pipeline into consideration, which may fall short in practical applications.In this...