CVPR 2022文档图像分析与识别相关论文26篇汇集简介

据初步统计，CVPR 2022共录用发表与OCR直接相关的论文约26篇，相比于去年（CVPR 2021，22篇）增加了4篇，表明此领域的研究热度在持续增加。26篇论文内容覆盖文档图像处理、场景文字检测、场景文字识别、端到端文字识别、表格分析与结构识别、文档图像理理解、字体生成、手写公式识别、自监督文本识别、OCR+CV应用等多个方向。具体情况如下（标*的论文开源了代码，标#的论文开源了数据集）：

附：CVPR 2022论文下载官网：https://openaccess.thecvf.com/CVPR2022?day=all

文字图像处理（场景文字分割、文字超分辨率、文档图像矫正）：4篇

• Xixi Xu, Zhongang Qi, Jianqi Ma, Honglun Zhang, Ying Shan, Xiaohu Qie, BTS: A Bi-Lingual Benchmark for Text Segmentation in the Wild（#）
• Jianqi Ma, Zhetong Liang, Lei Zhang，A Text Attention Network for Spatial Deformation Robust Scene Text Image Super-Resolution（*）
• Chuhui Xue, Zichen Tian, Fangneng Zhan, Shijian Lu, Song Bai, Fourier Document Restoration for Robust Document Dewarping and Recognition （#）
• Xiangwei Jiang, Rujiao Long, Nan Xue, Zhibo Yang, Cong Yao, Gui-Song Xia, Revisiting Document Image Dewarping by Grid Regularization（*）

   

场景文字检测：3篇

• Jingqun Tang, Wenqing Zhang, Hongye Liu, MingKun Yang, Bo Jiang, Guanglong Hu, Xiang Bai, Few Could Be Better Than All- Feature Sampling and Grouping for Scene Text Detection
• Sibo Song, Jianqiang Wan, Zhibo Yang, Jun Tang, Wenqing Cheng, Xiang Bai, Cong Yao, Vision-Language Pre-Training for Boosting Scene Text Detectors（*）
• Shangbang Long, Siyang Qin, Dmitry Panteleev, Alessandro Bissacco, Yasuhisa Fujii, Michalis Raptis, Towards End-to-End Unified Scene Text Detection and Layout Analysis（*#）

场景文字识别：2篇

• Chang Liu, Chun Yang,  Xu-Cheng Yin, Open-Set Text Recognition via Character-Context Decoupling（*#）
• Caiyuan Zheng, Hui Li, Seon-Min Rhee, Seungju Han, Jae-Joon Han, Peng Wang, Pushing the Performance Limit of Scene Text Recognizer Without Human Annotation  

端到端文字识别：3篇

• Mingxin Huang, Yuliang Liu, Zhenghao Peng, Chongyu Liu, Dahua Lin, Shenggao Zhu, Nicholas Yuan, Kai Ding, Lianwen Jin,  SwinTextSpotter: Scene Text Spotting Via Better Synergy Between Text Detection and Text Recognition（*）
• Xiang Zhang, Yongwen Su, Subarna Tripathi, Zhuowen Tu, Text Spotting Transformer （*）
• Yair Kittenplon, Inbal Lavi ,Sharon Fogel, Yarin Bar, R. Manmatha, Pietro Perona, Towards Weakly-Supervised Text Spotting using a Multi-Task Transformer

文档图像理解：3篇

• Zhangxuan Gu, Changhua Meng, Ke Wang, Jun Lan, Weiqiang Wang, Ming Gu, Liqing Zhang, XYLayoutLM: Towards Layout-Aware Multimodal Networks for Visually-Rich Document Understanding
• Ali Furkan Biten, Ron Litman, Yusheng Xie, Srikar Appalaraju, R. Manmatha, LaTr: Layout-Aware Transformer for Scene-Text VQA
• Yihao Ding, Zhe Huang, Runlin Wang, YanHang Zhang, Xianru Chen, Yuzhong Ma, Hyunsuk Chung, Soyeon Caren Han, V-Doc: Visual Questions Answers With Documents （#）

表格分析与结构识别：3篇

• Brandon Smock, Rohith Pesala, Robin Abraham, PubTables-1M: Towards Comprehensive Table Extraction From Unstructured Documents（*#）

• Hao Liu, Xin Li, Bing Liu, Deqiang Jiang, Yinsong Liu, Bo Ren, Neural Collaborative Graph Machines for Table Structure Recognition

• Ahmed Nassar, Nikolaos Livathinos, Maksym Lysak, Peter Staar, TableFormer: Table Structure Understanding with Transformers

数据合成：4篇

• Wei Liu, Fangyue Liu, Fei Ding, Qian He, Zili Yi, XMP-Font: Self-Supervised Cross-Modality Pre-training for Few-Shot Font Generation
• Yuxin Kong, Canjie Luo, Weihong Ma, Qiyuan Zhu, Shenggao Zhu, Nicholas Yuan, Lianwen Jin, Look Closer to Supervise Better: One-Shot Font Generation via Component-Based Discriminator
• Licheng Tang, Yiyang Cai, Jiaming Liu, Zhibin Hong, Mingming Gong, Minhu Fan, Junyu Han, Jingtuo Liu, Errui Ding, Jingdong Wang, Few-Shot Font Generation by Learning Fine-Grained Local Styles
• Yizhi Wang, Guo Pu, Wenhan Luo, Yexin Wang, Pengfei Xiong, Hongwen Kang, Zhouhui Lian, Aesthetic Text Logo Synthesis via Content-Aware Layout Inferring

其它（手写数学公式识别，自监督文本表征学习，OCR+CV新应用）：4篇

• Ye Yuan, Xiao Liu, Wondimu Dikubab, Hui Liu, Zhilong Ji, Zhongqin Wu,  Xiang Bai,  Syntax-Aware Network for Handwritten Mathematical Expression Recognition (*#)
• Canjie Luo, Lianwen Jin, Jingdong Chen, SimAN: Exploring Self-Supervised Representation Learning of Scene Text via Similarity-Aware Normalization
• Mengjun Cheng, Yipeng Sun, Longchao Wang,  Xiongwei Zhu, Kun Yao, Jie Chen, Guoli Song, Junyu Han, Jingtuo Liu, Errui Ding, Jingdong Wang, ViSTA: Vision and Scene Text Aggregation for Cross-Modal Retrieval
• Hao Wang, Junchao Liao, Tianheng Cheng, Zewen Gao, Hao Liu, Bo Ren, Xiang Bai, Wenyu Liu,  Knowledge Mining with Scene Text for Fine-Grained Recognition (*#)

内容中包含的图片若涉及版权问题，请及时与我们联系删除