Authors: Xiaobing Wang, Yi Yu, Haiyang Guo, Yingying Jiang
Description: We use RNN based adaptive representation for text detection. Given an input image, a text region proposal network is first used for extracting text proposals. Then, these proposals are verified and refined with a refinement network. Here, recurrent neural network based adaptive text region representation is proposed for text region refinement, where a pair of boundary points are predicted each time step until no new points are found. In this way, text regions of arbitrary shapes are detected and represented with adaptive number of boundary points. The backbone network is VGG16 with SE block used.
Besides, Mask RCNN is also used for text detection in our submission. We use the https://github.com/facebookresearch/Detectron and the backbone network is ResNext 101.