Authors: Longhuang Wu, Shangxuan Tian, Youxin Wang, Pengfei Xiong

Email: wlonghuang@gmail.com

Description: We propose a Complementary Proposal Network (CPN) that seamlessly and parallelly integrates semantic and geometric information for superior performance. This Result is achieved with single Swin-L backbone and multi-scale testing policy. No model ensemble is used.

Authors: Jian Ye, Zhe Chen, Juhua Liu and Bo Du

Affiliation: Wuhan University, The University of Sydney

Email: liujuhua@whu.edu.cn

Description: Arbitrary shape text detection in natural scenes is an extremely challenging task. Unlike existing text detection approaches that only perceive texts based on limited feature representations, we propose a novel framework, namely TextFuseNet, to exploit the use of richer features fused for text detection. More specifically, we propose to perceive texts from three levels of feature representations, i.e., character-, word- and global-level, and then introduce a novel text representation fusion technique to help achieve robust arbitrary text detection. The multi-level feature representation can adequately describe texts by dissecting them into individual characters while still maintaining their general semantics. TextFuseNet then collects and merges the texts’ features from different levels using a multi-path fusion architecture which can effectively align and fuse different representations. In practice, our proposed TextFuseNet can learn a more adequate description of arbitrary shapes texts, suppressing false positives and producing more accurate detection results. Our proposed framework can also be trained with weak supervision for those datasets that lack character-level annotations. Experiments on several datasets show that the proposed TextFuseNet achieves state-of-the-art performance. Specifically, we achieve an F-measure of 94.3% on ICDAR2013, 92.1% on ICDAR2015,87.1% on Total-Text and 86.6% on CTW-1500, respectively.

Authors: Tsinghua University and Hyundai Motor Group AIRS Company

Email: Shanyu Xiao: xiaosy19@mails.tsinghua.edu.cn

Description: We have built an end-to-end scene text spotter based on Mask R-CNN & Transformer. The ResNet-50 backbone and multiscale training/testing are used.