最新！CVPR 2021 OCR领域论文大盘点（22篇）

点击下方卡片，关注“CVer”公众号

AI/CV重磅干货，第一时间送达

转载自：CSIG文档图像分析与识别专委会

前言

CVer 正在盘点CVPR 2021上各个方向的工作，目前热度最高的视觉Transformer盘点，之前已经po出，详见：最新！CVPR 2021 视觉Transformer论文大盘点（43篇）。本文将分享CVPR 2021上OCR相关的论文盘点工作（文末附PDF下载）。

关于更多CVPR 2021的论文和开源代码，可见下面链接：

https://github.com/amusi/CVPR2021-Papers-with-Code

正文

今年CVPR论文已经可以在官网全文浏览（网址：

https://openaccess.thecvf.com/CVPR2021?day=all），据初步统计，CVPR 2021共收录与OCR直接相关的论文约22篇，覆盖文档图像处理、场景文字检测、场景文字识别、手写文字分析与识别、端到端文字识别、文档图像预训练模型、TextVQA、文本图像检索、OCR应用等多个方向。具体情况如下：

文字图像处理（超分辨率增强、文字分割、文档版面分析）：3篇

• Jingye Chen, Bin Li, Xiangyang Xue, Scene Text Telescope: Text-Focused Scene Image Super-Resolution, CVPR 2021

• Xingqian Xu, Zhifei Zhang, Zhaowen Wang, Brian Price, Zhonghao Wang, Humphrey Shi, Rethinking Text Segmentation: A Novel Dataset and a Text-Specific Refinement Approach, CVPR 2021

•  D. Arroyo, J Postels, F. Tombari, Variational Transformer Networks for Layout Generation, CVPR 2021

 

场景文字检测：5篇

• Wei Feng,  Fei Yin, Xu-Yao Zhang, Cheng-Lin Liu, Semantic-Aware Video Text Detection, CVPR 2021

• Yiqin Zhu, Jianyong Chen, Lingyu Liang, Zhanghui Kuang, Lianwen Jin, Wayne Zhang, Fourier Contour Embedding for Arbitrary-Shaped Text Detection, CVPR 2021

• Qi Wan, Haoqin Ji, and Linlin Shen, Self-Attention Based Text Knowledge Mining for Text Detection, CVPR 2021
  

• Pengwen Dai, Sanyi Zhang, Hua Zhang, Xiaochun Cao, Progressive Contour Regression for Arbitrary-Shape Scene Text Detection, CVPR 2021

• Minghang He, Minghui Liao, Zhibo Yang, et al., MOST: A Multi-Oriented Scene Text Detector With Localization Refinement, CVPR 2021

场景文字识别：5篇

• Ruijie Yan, Liangrui Peng, Shanyu Xiao, Gang Yao, Primitive Representation Learning for Scene Text Recognition, CVPR 2021

• Shancheng Fang, Hongtao Xie, Yuxin Wang, Zhendong Mao, Yongdong Zhang, Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognition, CVPR 2021

•  Aberdam, R Litman, et al., Sequence-to-Sequence Contrastive Learning for Text Recognition, CVPR 2021

• Nguyen Nguyen, Thu Nguyen, Vinh Tran, Minh-Triet Tran, et al., Dictionary-Guided Scene Text Recognition, CVPR 2021

• Jeonghun Baek, Yusuke Matsui, Kiyoharu Aizawa, What if We Only Use Real Datasets for Scene Text Recognition? Toward Scene Text Recognition With Fewer Labels, CVPR 2021

  

端到端文字识别：2篇

• Tianwei Wang, Yuanzhi Zhu,  Lianwen Jin, et al., Implicit Feature Alignment: Learn To Convert Text Recognizer to Text Spotter, CVPR 2021

• Jing Huang, Guan Pang, Rama Kovvuri, et al., A Multiplexed Network for End-to-End, Multilingual OCR, CVPR 2021

 

手写文字分析与识别：2篇

• Ayan Kumar Bhunia, Shuvozit Ghose,  Amandeep Kumar, et al., MetaHTR- Towards Writer-Adaptive Handwritten Text Recognition, CVPR 2021

• Ayan Kumar Bhunia, Pinaki Nath Chowdhury, Yongxin Yang, et al., Vectorization and Rasterization- Self-Supervised Learning for Sketch and Handwriting, CVPR 2021

 

其它（文档图像预训练模型，Text VQA、数据集，Retrieval , 应用）：5篇

• Peizhao Li, Jiuxiang Gu, Jason Kuen, Vlad I. Morariu, et al., SelfDoc: Self-Supervised Document Representation Learning, CVPR 2021

• Amanpreet Singh, Guan Pang, Mandy Toh, et al., TextOCR: Towards Large-Scale End-to-End Reasoning for Arbitrary-Shaped Scene Text, CVPR 2021

• Hao Wang, Xiang Bai, Mingkun Yang, Shenggao Zhu, Jing Wang, Wenyu Liu, Scene Text Retrieval via Joint Text Detection and Similarity Learning, CVPR 2021

•  Zhengyuan Yang, Yijuan Lu, Jianfeng Wang, et al., TAP: Text-Aware Pre-Training for Text-VQA and Text-Caption, CVPR 2021

• Jing Wang, Jinhui Tang, Mingkun Yang, Xiang Baia , and Jiebo Luo, Improving OCR-Based Image Captioning by Incorporating Geometrical Relationship, CVPR 2021

上述22篇论文的摘要及其方法主要框图摘录如下：

• 文字图像处理（超分辨率增强、文字分割、文档版面分析）：3篇

• 场景文字检测：5篇

• 场景文字识别：5篇

• 端到端文字识别：2篇

• 手写文字分析与识别：2篇

• 其它（文档图像预训练模型，Text VQA、数据集，Retrieva， 应用）：5篇

【温馨提示】关注本公众号，输入“CVPR OCR”可获取上述22篇论文的下载链接。

---

免责声明：（1）本文仅代表撰稿者观点，撰稿者不一定是原文作者，其个人理解及总结不一定准确及全面，论文完整思想及论点应以原论文为准。（2）本文观点不代表本公众号立场。 

上述22篇OCR论文下载
后台回复：CVPR OCR，即可下载上述论文PDF
CVPR和Transformer资料下载

后台回复：CVPR2021，即可下载CVPR 2021论文和代码开源的论文合集
后台回复：Transformer综述，即可下载最新的两篇Transformer综述PDF
CVer-OCR交流群成立
扫码添加CVer助手，可申请加入CVer-OCR 微信交流群，方向已涵盖：目标检测、图像分割、目标跟踪、人脸检测&识别、OCR、姿态估计、超分辨率、SLAM、医疗影像、Re-ID、GAN、NAS、深度估计、自动驾驶、强化学习、车道线检测、模型剪枝&压缩、去噪、去雾、去雨、风格迁移、遥感图像、行为识别、视频理解、图像融合、图像检索、论文投稿&交流、PyTorch和TensorFlow等群。
一定要备注：研究方向+地点+学校/公司+昵称（如OCR+上海+上交+卡卡），根据格式备注，可更快被通过且邀请进群
▲长按加小助手微信，进交流群▲点击上方卡片，关注CVer公众号
整理不易，请给CVer点赞和在看