{"id":13409069,"url":"https://github.com/hwalsuklee/awesome-deep-text-detection-recognition","last_synced_at":"2025-05-15T11:05:49.640Z","repository":{"id":37502948,"uuid":"112569794","full_name":"hwalsuklee/awesome-deep-text-detection-recognition","owner":"hwalsuklee","description":"A curated list of resources for text detection/recognition (optical character recognition ) with deep learning methods.","archived":false,"fork":false,"pushed_at":"2021-08-10T07:54:23.000Z","size":1077,"stargazers_count":2528,"open_issues_count":10,"forks_count":511,"subscribers_count":150,"default_branch":"master","last_synced_at":"2025-05-05T16:08:59.935Z","etag":null,"topics":["awesome-list","awesome-lists","deep-learning","ocr","ocr-detection","ocr-paper","ocr-paper-list","ocr-papers","ocr-recognition","text-detection","text-detection-recognition","text-recognition"],"latest_commit_sha":null,"homepage":null,"language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/hwalsuklee.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2017-11-30T05:43:19.000Z","updated_at":"2025-05-03T10:44:36.000Z","dependencies_parsed_at":"2022-08-09T09:15:37.296Z","dependency_job_id":null,"html_url":"https://github.com/hwalsuklee/awesome-deep-text-detection-recognition","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hwalsuklee%2Fawesome-deep-text-detection-recognition","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hwalsuklee%2Fawesome-deep-text-detection-recognition/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hwalsuklee%2Fawesome-deep-text-detection-recognition/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hwalsuklee%2Fawesome-deep-text-detection-recognition/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/hwalsuklee","download_url":"https://codeload.github.com/hwalsuklee/awesome-deep-text-detection-recognition/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":254328385,"owners_count":22052632,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["awesome-list","awesome-lists","deep-learning","ocr","ocr-detection","ocr-paper","ocr-paper-list","ocr-papers","ocr-recognition","text-detection","text-detection-recognition","text-recognition"],"created_at":"2024-07-30T20:00:57.763Z","updated_at":"2025-05-15T11:05:49.602Z","avatar_url":"https://github.com/hwalsuklee.png","language":null,"funding_links":[],"categories":["Applications","Uncategorized","Others","References","Awesome lists","Related Awesome Resource","Computer Vision","OCR","Other Lists","Appendix: Object Detection for Natural Scene"],"sub_categories":["Computer Vision (CV)","Uncategorized","CTPN [paper:2016](https://arxiv.org/pdf/1609.03605.pdf)","TeX Lists","Papers"],"readme":"# awesome-deep-text-detection-recognition\nA curated list of awesome deep learning based papers on text detection and recognition.\n\n\u003cp align='center'\u003e\n\u003cimg src = '/overall_pi_chart.png' height=\"300px\"\u003e  \n\u003cimg src = '/overall_histogram.png' height=\"450px\"\u003e\n\u003c/p\u003e\n\n## Text Detection\n* Papers are sorted by published date.\n* IC is shorts for ICDAR.\n* Score is F1-score for localization task.\n  * (L) stands for score in [leader-board](http://rrc.cvc.uab.es/).\n  * If the reported score in leader-board is somewhat different from the paper, (L) is provided.\n* `*CODE` means official code and `CODE(M)` means that traiend model is provided.  \n\n*Conf.* | *Date* | *Title* | *IC13* | *IC15* | *Resources* |\n:---: | :---: |:--- | :---: | :---: | :---: |\n'14-ECCV\t| 14/10/07\t| [Robust Scene Text Detection with Convolution Neural Network Induced MSER Trees](\thttp://www.whuang.org/papers/whuang2014_eccv.pdf) |\n15-CVPR\t| 15/06/01\t| [Symmetry-based text line detection in natural scenes](https://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Zhang_Symmetry-Based_Text_Line_2015_CVPR_paper.pdf) | [0.8043](http://rrc.cvc.uab.es/?ch=2\u0026com=evaluation\u0026view=method_info\u0026task=1\u0026m=2197) | | [`PRJ`](http://mclab.eic.hust.edu.cn/~xbai/text/symmetry/SymmetryTextLineDetection.html) \u003cbr\u003e [`CODE`](https://github.com/stupidZZ/Symmetry_Text_Line_Detection) |  \n'16-TIP\t| 15/10/12 | [Text-Attentional Convolutional Neural Networks for Scene Text Detection](https://arxiv.org/pdf/1510.03283.pdf) |\t[0.8165](http://rrc.cvc.uab.es/?ch=2\u0026com=evaluation\u0026view=method_info\u0026task=1\u0026m=7187)\t| \n'15-ICCV\t| 15/12/13\t| [Text Flow : A Unified Text Detection System in Natural Scene Images](https://pdfs.semanticscholar.org/11a0/8ced22775a217ba78c566528ed44ea98e3e3.pdf)\t|0.8025 | \n'16-arXiv\t| 16/03/31\t| [Accurate Text Localization in Natural Image with Cascaded Convolutional TextNetwork](https://arxiv.org/pdf/1603.09423.pdf)\t| 0.86\t| |\n'16-CVPR\t| 16/04/14\t| [Multi-Oriented Text Detection with Fully Convolutional Networks](https://arxiv.org/pdf/1604.04018.pdf) | 0.83 | 0.54 | [`*TORCH(M)`](https://github.com/stupidZZ/FCN_Text)\n'16-CVPR\t| 16/04/22\t| [Synthetic Data for Text Localisation in Natural Images](http://www.robots.ox.ac.uk/~ankush/textloc.pdf)\t| 0.847 \u003cbr\u003e (L)[0.8359](http://rrc.cvc.uab.es/?ch=2\u0026com=evaluation\u0026view=method_info\u0026task=1\u0026m=3820) | | [`CODE`](https://github.com/ankush-me/SynthText) \u003cbr\u003e [`DB`](http://www.robots.ox.ac.uk/~vgg/data/scenetext/)\n'16-arXiv\t| 16/06/29\t| [Scene Text Detection Via Holistic, Multi-Channel Prediction](https://arxiv.org/pdf/1606.09002.pdf)\t|0.8433\t| 0.6477 | \n'16-ECCV\t| 16/09/12\t| [Detecting Text in Natural Image with Connectionist Text Proposal Network](https://arxiv.org/pdf/1609.03605.pdf) |\t[0.8215](http://rrc.cvc.uab.es/?ch=2\u0026com=evaluation\u0026view=method_info\u0026task=1\u0026m=13931)\t| [0.6085](http://rrc.cvc.uab.es/?ch=4\u0026com=evaluation\u0026view=method_info\u0026task=1\u0026m=13930) | [`*CAFFE(M)`](https://github.com/tianzhi0549/CTPN) \u003cbr\u003e [`CAFFE`](https://github.com/qingswu/CTPN) \u003cbr\u003e [`TF(M)`](https://github.com/eragonruan/text-detection-ctpn) \u003cbr\u003e [`TF`](https://github.com/Li-Ming-Fan/OCR-DETECTION-CTPN) \u003cbr\u003e [`DEMO`](http://textdet.com/) \u003cbr\u003e [`BLOG(CH)`](http://slade-ruan.me/2017/10/22/text-detection-ctpn/)\n'17-AAAI\t| 16/11/21\t|[TextBoxes: A fast text detector with a single deep neural network](https://arxiv.org/pdf/1611.06779.pdf) |\t0.85 \u003cbr\u003e (L)[0.8767](http://rrc.cvc.uab.es/?ch=2\u0026com=evaluation\u0026view=method_info\u0026task=1\u0026m=21928) | | [`*CAFFE(M)`](https://github.com/MhLiao/TextBoxes) \u003cbr\u003e [`TF`](https://github.com/shinjayne/shinTB) \u003cbr\u003e [`BLOG(KR)`](http://jaynewho.com/post/6)\n'18-TM\t| 17/03/03\t| [Arbitrary-Oriented Scene Text Detection via Rotation Proposals](https://arxiv.org/pdf/1703.01086.pdf)\t|\t[0.9125](http://rrc.cvc.uab.es/?ch=2\u0026com=evaluation\u0026view=method_info\u0026task=1\u0026m=15904)\t| [0.8020](http://rrc.cvc.uab.es/?ch=4\u0026com=evaluation\u0026view=method_info\u0026task=1\u0026m=17393)\t| [`*CAFFE`](https://github.com/mjq11302010044/RRPN)\n'17-CVPR\t| 17/03/04\t| [Deep Matching Prior Network: Toward Tighter Multi-oriented Text Detection](https://arxiv.org/pdf/1703.01425.pdf) | | [0.7064](http://rrc.cvc.uab.es/?ch=4\u0026com=evaluation\u0026view=method_info\u0026task=1\u0026m=13007)\n'17-CVPR\t| 17/03/19\t| [Detecting Oriented Text in Natural Images by Linking Segments](https://arxiv.org/pdf/1703.06520.pdf)\t|\t0.853\t| 0.75\t\u003cbr\u003e (L)[0.7636](http://rrc.cvc.uab.es/?ch=4\u0026com=evaluation\u0026view=method_info\u0026task=1\u0026m=29245)| [`*TF(M)`](https://github.com/bgshih/seglink) \u003cbr\u003e [`TF(M)`](https://github.com/dengdan/seglink) \u003cbr\u003e [`SLIDE`](http://mclab.eic.hust.edu.cn/~xbai/SpotlightPPT/TextDetection-seglink-spotlight-CVPR17.pdf) \u003cbr\u003e [`VIDEO`](https://www.youtube.com/watch?v=w0vZWUi-m0c) |\n'17-arXiv\t| 17/03/24 |\t[Deep Direct Regression for Multi-Oriented Scene Text Detection](https://arxiv.org/pdf/1703.08289.pdf)\t| 0.86 |  0.81\t| \n'17-arXiv\t| 17/04/03\t| [Cascaded Segmentation-Detection Networks for Word-Level Text Spotting](https://arxiv.org/pdf/1704.00834.pdf)\t|\t0.86\t| 0.71 |\n'17-CVPR\t| 17/04/11\t| [EAST: An Efficient and Accurate Scene Text Detector](https://arxiv.org/pdf/1704.03155.pdf) | | 0.8072\t\u003cbr\u003e (L)[0.8038](http://rrc.cvc.uab.es/?ch=4\u0026com=evaluation\u0026view=method_info\u0026task=1\u0026m=29855) | [`TF(M)`](https://github.com/argman/EAST) \u003cbr\u003e [`TF`](https://github.com/AKSHAYUBHAT/EAST) \u003cbr\u003e [`PYTORCH(M)`](https://github.com/SakuraRiven/EAST) \u003cbr\u003e [`PYTORCH`](https://github.com/songdejia/EAST) \u003cbr\u003e [`DEMO`](http://east.zxytim.com/) \u003cbr\u003e [`KERAS(M)`](https://github.com/kurapan/EAST) \u003cbr\u003e [`VIDEO`](https://www.youtube.com/watch?v=o5asMTdhmvA)\n'17-ICIP\t| 17/05/15\t| [WordFence: Text Detection in Natural Images with Border Awareness](https://arxiv.org/pdf/1705.05483.pdf) |\t0.86 |\n'17-arXiv\t| 17/06/30\t| [R2CNN: Rotational Region CNN for Orientation Robust Scene Text Detection](https://arxiv.org/pdf/1706.09579.pdf) | 0.8773\t| 0.8254 | [`TF(M)`](https://github.com/DetectionTeamUCAS/R2CNN_Faster-RCNN_Tensorflow) \u003cbr\u003e [`CAFFE(M)`](https://github.com/beacandler/R2CNN)\n'17-CVPR\t| 17/07/21\t| [Multi-scale FCN with Cascaded Instance Aware Segmentation for Arbitrary Oriented Word Spotting In The Wild](http://openaccess.thecvf.com/content_cvpr_2017/papers/He_Multi-Scale_FCN_With_CVPR_2017_paper.pdf)\t|\t0.85\t| 0.63 | \n'17-arXiv\t| 17/08/17\t| [Deep Scene Text Detection with Connected Component Proposals](https://arxiv.org/pdf/1708.05133.pdf)\t| 0.919 | \n'17-ICCV\t| 17/08/22\t| [WordSup: Exploiting Word Annotations for Character based Text Detection](https://arxiv.org/pdf/1708.06720) |\t0.9064 |\t0.7816 |\n'17-ICCV\t| 17/09/01\t| [Single Shot Text Detector with Regional Attention](https://arxiv.org/pdf/1709.00138.pdf)\t|\t0.8704 |\t[0.7691](http://rrc.cvc.uab.es/?ch=4\u0026com=evaluation\u0026view=method_info\u0026task=1\u0026m=18294) | [`*CAFFE(M)`](https://github.com/BestSonny/SSTD) \u003cbr\u003e [`PYTORCH`](https://github.com/HotaekHan/SSTDNet) \u003cbr\u003e [`VIDEO`](https://www.youtube.com/watch?v=oBWVgz685-k) \n'17-arXiv\t| 17/09/11\t| [Fused Text Segmentation Networks for Multi-oriented Scene Text Detection](https://arxiv.org/pdf/1709.03272.pdf) | | [0.8414](http://rrc.cvc.uab.es/?ch=4\u0026com=evaluation\u0026view=method_info\u0026task=1\u0026m=30447)\t|\n'17-ICCV\t| 17/10/13\t| [WeText: Scene Text Detection under Weak Supervision](https://arxiv.org/pdf/1710.04826.pdf)\t| 0.869 \u003cbr\u003e (L)[0.8313](http://rrc.cvc.uab.es/?ch=2\u0026com=evaluation\u0026view=method_info\u0026task=1\u0026m=20665) |\n'17-ICCV\t| 17/10/22\t| [Self-organized Text Detection with Minimal Post-processing via Border Learning](http://openaccess.thecvf.com/content_ICCV_2017/papers/Wu_Self-Organized_Text_Detection_ICCV_2017_paper.pdf)\t| 0.84 | | [`*KERAS(M)`](https://gitlab.com/rex-yue-wu/ISI-PPT-Text-Detector)\n'17-ICDAR\t| 17/11/11\t| [Deep Residual Text Detection Network for Scene Text](https://arxiv.org/pdf/1711.04147.pdf)\t|\t0.9117 \u003cbr\u003e (L)[0.8925](http://rrc.cvc.uab.es/?ch=2\u0026com=evaluation\u0026view=method_info\u0026task=1\u0026m=21966) | \n'18-AAAI\t| 17/11/12\t| [Feature Enhancement Network: A Refined Scene Text Detector](https://arxiv.org/pdf/1711.04249.pdf)\t| [0.9161](http://rrc.cvc.uab.es/?ch=2\u0026com=evaluation\u0026view=method_info\u0026task=1\u0026m=28362) |\n'17-arXiv\t| 17/11/30\t| [ArbiText: Arbitrary-Oriented Text Detection in Unconstrained Scene](https://arxiv.org/pdf/1711.11249.pdf)\t|\t| 0.759 |\t\n'18-AAAI\t| 18/01/04\t| [PixelLink: Detecting Scene Text via Instance Segmentation](https://arxiv.org/pdf/1801.01315.pdf)\t|\t0.881 | [0.8519](http://rrc.cvc.uab.es/?ch=4\u0026com=evaluation\u0026view=method_info\u0026task=1\u0026m=30576)\t| [`*TF(M)`](https://github.com/ZJULearning/pixel_link) [`TF`](https://github.com/BowieHsu/tensorflow_ocr)\n'18-CVPR\t| 18/01/05\t| [FOTS: Fast Oriented Text Spotting with a Unified Network](https://arxiv.org/pdf/1801.01671.pdf)\t| [0.925](http://rrc.cvc.uab.es/?ch=2\u0026com=evaluation\u0026view=method_info\u0026task=1\u0026m=34624)\t| [0.8984](http://rrc.cvc.uab.es/?ch=4\u0026com=evaluation\u0026view=method_info\u0026task=1\u0026m=34625)\t|\t[`PYTORCH`](https://github.com/jiangxiluning/FOTS.PyTorch) \u003cbr\u003e [`PYTORCH`](https://github.com/xieyufei1993/FOTS) \u003cbr\u003e [`VIDEO`](https://www.youtube.com/watch?v=F7TTYlFr2QM) | \n'18-TIP\t| 18/01/09\t| [TextBoxes++: A Single-Shot Oriented Scene Text Detector](https://arxiv.org/pdf/1801.02765.pdf)\t| 0.88\t| 0.829 \u003cbr\u003e (L)[0.8475](http://rrc.cvc.uab.es/?ch=4\u0026com=evaluation\u0026view=method_info\u0026task=1\u0026m=29660) | [`*CAFFE(M)`](https://github.com/MhLiao/TextBoxes_plusplus)\n'18-CVPR\t| 18/02/27\t| [Multi-Oriented Scene Text Detection via Corner Localization and Region Segmentation](https://arxiv.org/pdf/1802.08948.pdf)\t| 0.88\t| 0.843 |[`*PYTORCH(M)`](https://github.com/lvpengyuan/corner)\n'18-CVPR\t| 18/03/09\t| [An end-to-end TextSpotter with Explicit Alighment and Attention](https://arxiv.org/pdf/1803.03474.pdf)\t| 0.9\t| 0.87 |[`*CAFFE(M)`](https://github.com/tonghe90/textspotter)\n'18-CVPR\t| 18/03/14\t| [Rotation-Sensitive Regression for Oriented Scene Text Detection](https://arxiv.org/pdf/1803.05265.pdf)\t| 0.89\t| 0.838 |\t[`*CAFFE(M)`](https://github.com/MhLiao/RRD)\n'18-arXiv\t| 18/04/08\t| [Detecting Multi-Oriented Text with Corner-based Region Proposals](https://arxiv.org/pdf/1804.02690.pdf) | 0.876\t| 0.845 | [`*CAFFE(M)`](https://github.com/xhzdeng/crpn)\n'18-arXiv\t| 18/04/24\t| [An Anchor-Free Region Proposal Network for Faster R-CNN based Text Detection Approaches](https://arxiv.org/pdf/1804.09003.pdf)\t| 0.92\t| 0.86\t|\n'18-IJCAI\t| 18/05/03\t| [IncepText: A New Inception-Text Module with Deformable PSROI Pooling for Multi-Oriented Scene Text Detection](https://arxiv.org/pdf/1805.01167.pdf)\t| | [0.9047](http://rrc.cvc.uab.es/?ch=4\u0026com=evaluation\u0026view=method_info\u0026task=1\u0026m=34989) |\t\n'18-arXiv\t| 18/06/07\t| [Shape Robust Text Detection with Progressive Scale Expansion Network](https://arxiv.org/pdf/1806.02559.pdf) | |\t\t[0.8721](http://rrc.cvc.uab.es/?ch=4\u0026com=evaluation\u0026view=method_info\u0026task=1\u0026m=37493)\t| [`PRJ`](https://github.com/whai362/PSENet)\n'18-ECCV\t| 18/07/04\t| [TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes](https://arxiv.org/pdf/1807.01544.pdf) | |\t0.826\t| [`PYTORCH`](https://github.com/princewang1994/TextSnake.pytorch)\n'18-ECCV\t| 18/07/06\t| [Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes](https://arxiv.org/pdf/1807.02242.pdf) | 0.917\t| 0.86 |\n'18-ECCV\t| 18/07/10\t| [Accurate Scene Text Detection through Border Semantics Awareness and Bootstrapping](https://arxiv.org/pdf/1807.03547.pdf) |\t0.892\t|\n'19-AAAI    | 18/11/21  | [Scene Text Detection with Supervised Pyramid Context Network](https://arxiv.org/pdf/1811.08605.pdf)  | 0.921 | 0.872 | \n'19-TIP | 18/12/04 | [TextField: Learning A Deep Direction Field for Irregular Scene Text Detection](https://arxiv.org/pdf/1812.01393.pdf) | | 0.824 | [`*CAFFE(M)`](https://github.com/YukangWang/TextField)\n'19-CVPR | 19/03/21 | [Towards Robust Curve Text Detection with Conditional Spatial Expansion](https://arxiv.org/pdf/1903.08836.pdf) | | | |  \n'19-CVPR | 19/03/28 | [Shape Robust Text Detection with Progressive Scale Expansion Network](https://arxiv.org/pdf/1903.12473.pdf) | | 0.857 | [`TF(M)`](https://github.com/liuheng92/tensorflow_PSENet)\n'19-CVPR | 19/04/03 | [Character Region Awareness for Text Detection](https://arxiv.org/pdf/1904.01941.pdf) | 0.952 | 0.869 |[`*PYTORCH(M)`](https://github.com/clovaai/CRAFT-pytorch) \u003cbr\u003e [`VIDEO`](https://www.youtube.com/watch?v=HI8MzpY8KMI) \u003cbr\u003e [`PYTORCH`](https://github.com/guruL/Character-Region-Awareness-for-Text-Detection-) \u003cbr\u003e [`TF(M)`](https://github.com/namedysx/CRAFT-tensorflow) \u003cbr\u003e [`KERAS`](https://github.com/RubanSeven/CRAFT_keras) \u003cbr\u003e [`BLOG_CH`](https://medium.com/@xiaosean5408/craft簡介-character-region-awareness-for-text-detection-a5c782408f00) \u003cbr\u003e [`BLOG_KR`](https://data-newbie.tistory.com/187) \u003cbr\u003e [`BLOG_KR`](https://medium.com/qandastudy/character-region-awareness-for-text-detection-craft-review-a7542779e037) \u003cbr\u003e [`BLOG_KR`](https://github.com/chullhwan-song/Reading-Paper/issues/136)|  \n'19-CVPR | 19/04/13 | [Look More Than Once: An Accurate Detector for Text of Arbitrary Shapes Screen reader support enabled](https://arxiv.org/pdf/1904.06535.pdf) | | 0.877 | |  \n'19-CVPR | 19/06/16 | [Learning Shape-Aware Embedding for Scene Text Detection](http://jiaya.me/papers/textdetection_cvpr19.pdf) | | 0.877 | |  \n'19-CVPR | 19/06/16 | [Arbitrary Shape Scene Text Detection with Adaptive Text Region Representation](https://arxiv.org/pdf/1905.05980.pdf) | 0.917 | 0.876 | |  \n'19-ICCV | 19/08/16 | [Efficient and Accurate Arbitrary-Shaped Text Detection with Pixel Aggregation Network](https://arxiv.org/abs/1908.05900) | | 0.829 | |  \n'19-ICCV | 19/09/02 | [Geometry Normalization Networks for Accurate Scene Text Detection](https://arxiv.org/abs/1909.00794) | | 0.8852 | |  \n'19-AAAI | 19/11/20 | [Real-time Scene Text Detection with Differentiable Binarization](https://arxiv.org/abs/1911.08947) | | 0.847 | |  \n\u003cp align='center'\u003e\n\u003cimg src = '/detection_ic13_results.png' height = '550px'\u003e\n\u003cimg src = '/detection_ic15_results.png' height = '550px'\u003e\n\u003c/p\u003e\n\n## Text Recognition\n* Papers are sorted by published date.\n* IC is shorts for ICDAR.\n* Score is word-accuracy for recognition task.\n  * For results on IC03, IC13, and IC15 dataset, papers used different numbers of samples per paper,  \n  but we did not distinguish between them\n* `*CODE` means official code and `CODE(M)` means that trained model is provided.  \n\n*Conf.* | *Date* | *Title* | *SVT* | *IIIT5k* | *IC03* | *IC13* | *Resources* |\n:---: | :---: |:--- | :---: | :---: | :---: | :---: | :---: |\n'15-ICLR\t| 14/12/18\t| [Deep structured output learning for unconstrained text recognition](https://arxiv.org/pdf/1412.5903.pdf) |\t0.717 | |0.896\t| 0.818 | [`TF`](https://github.com/AlexandreSev/Structured_Data) \u003cbr\u003e [`SLIDE`](https://www.robots.ox.ac.uk/~vgg/publications/2015/Jaderberg15a/presentation.pdf) \u003cbr\u003e [`VIDEO`](https://www.youtube.com/watch?v=NYkG38RCoRg)\n'16-IJCV\t| 15/05/07\t| [Reading text in the wild with convolutional neural networks](https://arxiv.org/pdf/1412.1842.pdf)\t| 0.807\t|\t| \t0.933\t| 0.908 | [`KERAS`](https://github.com/mathDR/reading-text-in-the-wild)\n'16-AAAI\t| 15/06/14\t| [Reading Scene Text in Deep Convolutional Sequences](https://arxiv.org/pdf/1506.04395.pdf)\n'17-TPAMI\t| 15/07/21\t| [An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition](https://arxiv.org/pdf/1507.05717.pdf)\t| 0.808\t| 0.782 | 0.894\t| 0.867 | [`TORCH(M)`](https://github.com/bgshih/crnn)  \u003cbr\u003e [`TF`](https://github.com/weinman/cnn_lstm_ctc_ocr)  \u003cbr\u003e [`TF`](https://github.com/watsonyanghx/CNN_LSTM_CTC_Tensorflow) \u003cbr\u003e [`TF`](https://github.com/MaybeShewill-CV/CRNN_Tensorflow) \u003cbr\u003e [`TF`](https://github.com/bai-shang/OCR_TF_CRNN_CTC) \u003cbr\u003e [`PYTORCH`](https://github.com/meijieru/crnn.pytorch)  \u003cbr\u003e [`PYTORCH(M)`](https://github.com/BelBES/crnn-pytorch) \u003cbr\u003e [`BLOG(KR)`](https://medium.com/@mldevhong/%EB%85%BC%EB%AC%B8-%EB%B2%88%EC%97%AD-rcnn-an-end-to-end-trainable-neural-network-for-image-based-sequence-recognition-and-its-f6456886d6f8)\n'16-CVPR\t| 16/03/09  | [Recursive Recurrent Nets with Attention Modeling for OCR in the Wild](https://arxiv.org/pdf/1603.03101.pdf) |\t0.807 | 0.784\t| 0.887\t| 0.9 |\n'16-CVPR\t| 16/03/12\t| [Robust scene text recognition with automatic rectification](https://arxiv.org/pdf/1603.03915.pdf) |\t0.819\t| 0.819 | 0.901\t| 0.886 | [`PYTORCH`](https://github.com/marvis/ocr_attention) \u003cbr\u003e [`PYTORCH`](https://github.com/WarBean/tps_stn_pytorch) \n'16-CVPR\t| 16/06/27\t| [CNN-N-Gram for Handwriting Word Recognition](https://www.cs.tau.ac.il/~wolf/papers/CNNNGram.pdf) |\t0.8362 | | | | [`VIDEO`](https://www.youtube.com/watch?v=czc2Ipm3Bis)\n'16-BMVC\t| 16/09/19\t| [STAR-Net: A SpaTial Attention Residue Network for Scene Text Recognition](http://www.visionlab.cs.hku.hk/publications/wliu_bmvc16.pdf) |\t0.836\t| 0.833\t|\t0.899\t| 0.891 |\n'17-arXiv\t| 17/07/27\t| [STN-OCR: A single Neural Network for Text Detection and Text Recognition](https://arxiv.org/pdf/1707.08831.pdf) | 0.798\t| 0.86\t| |\t0.903 | [`*MXNET(M)`](https://github.com/Bartzi/stn-ocr) \u003cbr\u003e [`PRJ`](https://bartzi.de/research/stn-ocr) \u003cbr\u003e [`BLOG`](https://medium.com/@Synced/stn-ocr-a-single-neural-network-for-text-detection-and-text-recognition-220debe6ded4)\n'17-IJCAI\t| 17/08/19\t| [Learning to Read Irregular Text with Attention Mechanisms](https://faculty.ist.psu.edu/zzhou/paper/IJCAI17-IrregularText.pdf) |\n'17-arXiv\t| 17/09/06\t| [Scene Text Recognition with Sliding Convolutional Character Models](https://arxiv.org/pdf/1709.01727.pdf) |\t0.765\t| 0.816\t| 0.845 |\t0.852 |\n'17-ICCV\t| 17/09/07\t| [Focusing Attention: Towards Accurate Text Recognition in Natural Images](https://arxiv.org/pdf/1709.02054.pdf) |\t0.859 | 0.874 | 0.942 |\t0.933 |\n'18-CVPR\t| 17/11/12\t| [AON: Towards Arbitrarily-Oriented Text Recognition](https://arxiv.org/pdf/1711.04226.pdf) |\t0.828\t|0.87\t| 0.915\t||[`TF`](https://github.com/huizhang0110/AON)\n'17-NIPS\t| 17/12/04\t| [Gated Recurrent Convolution Neural Network for OCR](https://papers.nips.cc/paper/6637-gated-recurrent-convolution-neural-network-for-ocr.pdf)\t| 0.815\t| 0.808 | 0.978 | | [`*TORCH(M)`](https://github.com/Jianfeng1991/GRCNN-for-OCR)\n'18-AAAI\t| 18/01/04\t| [Char-Net: A Character-Aware Neural Network for Distorted Scene Text Recognition](http://www.visionlab.cs.hku.hk/publications/wliu_aaai18.pdf) |\t0.844\t| 0.836\t| 0.915 |\t0.908 |\n'18-AAAI\t| 18/01/04\t| [SqueezedText: A Real-time Scene Text Recognition by Binary Convolutional Encoder-decoder Network](https://pdfs.semanticscholar.org/0e59/f7d7e9c9380b425a94038c7a2500b2f6063a.pdf) | |\t0.87\t| 0.931 |\t0.929 |\n'18-CVPR\t| 18/05/09  | [Edit Probability for Scene Text Recognition](https://arxiv.org/pdf/1805.03384.pdf) | 0.875 | 0.883 | 0.946 | 0.944 |\n'18-TPAMI\t| 18/06/25\t| [ASTER: An Attentional Scene Text Recognizer with Flexible Rectification](http://122.205.5.5:8071/UpLoadFiles/Papers/ASTER_PAMI18.pdf) |\t0.936\t| 0.934 |\t0.945\t| 0.918\t| [`*TF(M)`](https://github.com/bgshih/aster) \u003cbr\u003e [`PYTORCH`](https://github.com/ayumiymk/aster.pytorch)\n'18-ECCV\t| 18/09/08\t| [Synthetically Supervised Feature Learning for Scene Text Recognition](http://openaccess.thecvf.com/content_ECCV_2018/papers/Yang_Liu_Synthetically_Supervised_Feature_ECCV_2018_paper.pdf) |\t0.871\t| 0.894\t| \t0.947\t| 0.94 |\n'19-AAAI    | 18/09/18  | [Scene Text Recognition from Two-Dimensional Perspective](https://arxiv.org/pdf/1809.06508.pdf)   | 0.821 | 0.92 | | 0.914 |\n'19-AAAI    | 18/11/02  | [Show, Attend and Read: A Simple and Strong Baseline for Irregular Text Recognition](https://arxiv.org/pdf/1811.00751.pdf)   | 0.845 | 0.915 | | 0.91 | [`*TORCH(M)`](https://github.com/wangpengnorman/SAR-Strong-Baseline-for-Text-Recognition)  \n'19-CVPR    | 18/12/14  | [ESIR: End-to-end Scene Text Recognition via Iterative Image Rectification](https://arxiv.org/pdf/1812.05824.pdf)   | 0.902 | 0.933 |  | 0.913 | [PRJ](https://github.com/fnzhan/ESIR)  \n'19-PR    | 19/01/10  | [MORAN: A Multi-Object Rectified Attention Network for Scene Text Recognition](https://arxiv.org/pdf/1901.03003.pdf)   | 0.883 | 0.912 | 0.950 | 0.924 | [`*PYTORCH(M)`](https://github.com/Canjie-Luo/MORAN_v2)  \n'19-ICCV | 19/04/03 | [What is wrong with scene text recognition model comparisons? dataset and model analysis](https://arxiv.org/pdf/1904.01906.pdf) | 0.875 | | 0.949 | 0.936 | [`*PYTORCH(M)`](https://github.com/clovaai/deep-text-recognition-benchmark) \u003cbr\u003e [`BLOG_KR`](https://data-newbie.tistory.com/156)\n'19-CVPR | 19/04/18 | [Aggregation Cross-Entropy for Sequence Recognition](https://arxiv.org/pdf/1904.08364.pdf) | 0.826 | 0.823 | 0.921 | 0.897 | [`*PYTORCH`](https://github.com/summerlvsong/Aggregation-Cross-Entropy) | \n'19-CVPR | 19/06/16 | [Sequence-to-Sequence Domain Adaptation Network for Robust Text Image Recognition](http://openaccess.thecvf.com/content_CVPR_2019/papers/Zhang_Sequence-To-Sequence_Domain_Adaptation_Network_for_Robust_Text_Image_Recognition_CVPR_2019_paper.pdf) | 0.845 | 0.838 | 0.921 | 0.918 | |\n'19-ICCV | 19/08/06 | [Symmetry-constrained Rectification Network for Scene Text Recognition](https://arxiv.org/abs/1908.01957) | 0.889 | 0.944 | 0.95  | 0.939 |  \n'20-AAAI | 19/12/28 | [TextScanner: Reading Characters in Order for Robust Scene Text Recognition](https://arxiv.org/abs/1912.12422) | 0.895 | 0.926 |       | 0.925 |  \n'20-AAAI | 19/12/21 | [Decoupled Attention Network for Text Recognition](https://arxiv.org/abs/1912.10205) | 0.892 | 0.943 | 0.95  | 0.939 | [`*PYTORCH(M)`](https://github.com/Wang-Tianwei/Decoupled-attention-network)  \n'20-AAAI | 20/02/04 | [GTC: Guided Training of CTC](https://arxiv.org/abs/2002.01276) | 0.929 | 0.955 | 0.952 | 0.943 |  \n\n\u003cp align='center'\u003e\n\u003cimg src = '/recognition_ic13_results.png' height = '550px'\u003e\n\u003cimg src = '/recognition_iiit5k_results.png' height = '550px'\u003e\n\u003c/p\u003e\n\n## End-to-End Text Recognition\n* Papers are sorted by published date.\n* IC is shorts for ICDAR.\n* Score is F1-score for generic task. \n    * (L) stands for score in [leader-board](http://rrc.cvc.uab.es/).\n* `*CODE` means official code and `CODE(M)` means that trained model is provided.\n\n*Conf.* | *Date* | *Title* | *IC03* | *IC13* | *IC15* | *Resources* |\n:---: | :---: |:--- | :---: | :---: | :---: | :---: |\n'12-ICPR    | 12/11/11  | [End-to-end text recognition with convolutional neural networks](https://ai.stanford.edu/~ang/papers/ICPR12-TextRecognitionConvNeuralNets.pdf)    | 0.67 | | | [`*CODE`](http://cs.stanford.edu/people/twangcat/ICPR2012_code/SceneTextCNN_demo.tar)\n'14-ECCV    | 14/09/06  | [Deep Features for Text Spotting](https://www.robots.ox.ac.uk/~vgg/publications/2014/Jaderberg14/jaderberg14.pdf) | 0.75  | | | [`PRJ`](http://www.robots.ox.ac.uk/~vgg/research/text/) \u003cbr\u003e [`MATLAB`](https://bitbucket.org/jaderberg/eccv2014_textspotting)\n'15-IJCV    | 15/05/07  | [Reading Text in the Wild with Convolutional Neural Networks](https://arxiv.org/pdf/1412.1842.pdf)    | 0.70  | 0.77 | | [`KERAS`](https://github.com/mathDR/reading-text-in-the-wild)\n'15-TPAMI   | 15/10/30  | [Real-time Lexicon-free Scene Text Localization and Recognition](http://cmp.felk.cvut.cz/~neumalu1/Neumann_TPAMI2015.pdf) | | 0.542 | 0.156 |\n'16-arXiv   | 16/04/10  | [TextProposals: a Text-specific Selective Search Algorithm for Word Spotting in the Wild](https://arxiv.org/pdf/1604.02619.pdf) | | 0.6843 | 0.4718 \u003cbr\u003e (L)[0.533](http://rrc.cvc.uab.es/?ch=4\u0026com=evaluation\u0026view=method_info\u0026task=4\u0026m=7807) | [`*CAFFE(M)`](https://github.com/lluisgomez/TextProposals)\n'17-AAAI    | 16/11/21  | [TextBoxes: A fast text detector with a single deep neural network](https://arxiv.org/pdf/1611.06779.pdf) | | 0.84 | | [`TF`](https://github.com/shinjayne/shinTB) \u003cbr\u003e [`*CAFFE(M)`](https://github.com/MhLiao/TextBoxes) \u003cbr\u003e [`BLOG_KR`](http://jaynewho.com/post/6)\n'17-ICCV    | 17/07/13  | [Towards End-to-end Text Spotting with Convolution Recurrent Neural Network](https://arxiv.org/pdf/1707.03985.pdf) | | 0.8459 | | [`VIDEO`](https://www.youtube.com/watch?v=j0guWqBJ0lA)\n'17-ICCV    | 17/10/22  | [Deep TextSpotter An End-to-End Trainable Scene Text Localization and Recognition Framework](http://openaccess.thecvf.com/content_ICCV_2017/papers/Busta_Deep_TextSpotter_An_ICCV_2017_paper.pdf) | | 0.77 | 0.47 | [`VIDEO`](https://www.youtube.com/watch?v=VcNSQGO0j7s) \u003cbr\u003e [`*CAFFE(M)`](https://github.com/MichalBusta/DeepTextSpotter)\n'18-CVPR    | 18/01/05  | [FOTS: Fast Oriented Text Spotting with a Unified Network](https://arxiv.org/pdf/1801.01671.pdf) | | [0.8477](http://rrc.cvc.uab.es/?ch=2\u0026com=evaluation\u0026view=method_info\u0026task=4\u0026m=34627) | [0.6533](http://rrc.cvc.uab.es/?ch=4\u0026com=evaluation\u0026view=method_info\u0026task=4\u0026m=34626) | [`VIDEO`](https://www.youtube.com/watch?v=F7TTYlFr2QM) \u003cbr\u003e [`TF(M)`](https://github.com/Pay20Y/FOTS_TF)\n'18-TIP     | 18/01/09  | [TextBoxes++: A Single-Shot Oriented Scene Text Detector](https://arxiv.org/pdf/1801.02765.pdf) | | [0.8465](http://rrc.cvc.uab.es/?ch=2\u0026com=evaluation\u0026view=method_info\u0026task=4\u0026m=27895) | 0.519 | [`*CAFFE(M)`](https://github.com/MhLiao/TextBoxes_plusplus)\n'18-CVPR    | 18/03/09  | [An end-to-end TextSpotter with Explicit Alignment and Attention](https://arxiv.org/pdf/1803.03474.pdf) | | 0.86 | 0.63 | [`*CAFFE(M)`](https://github.com/tonghe90/textspotter)\n'18-TPAMI   | 18/06/25  | [ASTER: An Attentional Scene Text Recognizer with Flexible Rectification](http://122.205.5.5:8071/UpLoadFiles/Papers/ASTER_PAMI18.pdf) | | | 0.64 | [`*TF(M)`](https://github.com/bgshih/aster)\n'18-ECCV    | 18/07/06  | [Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes](https://arxiv.org/pdf/1807.02242.pdf) | | 0.865 | 0.624 |\n'19-ICCV    | 19/08/24  | [Towards Unconstrained End-to-End Text Spotting](https://arxiv.org/pdf/1908.09231.pdf) | | | 0.6994 | [`BLOG_KR`](https://www.notion.so/Towards-Unconstrained-End-to-End-Text-Spotting-0c66c692950f458e9a1323db2a79d143)  \n'19-ICCV    | 19/10/17  | [Convolutional Character Networks](https://arxiv.org/abs/1910.07954) | | | 0.7108 | [`*PYTORCH(M)`](https://github.com/MalongTech/research-charnet)  \n'19-ICCV    | 19/10/27  | [TextDragon: An End-to-End Framework for Arbitrary Shaped Text Spotting](http://openaccess.thecvf.com/content_ICCV_2019/papers/Feng_TextDragon_An_End-to-End_Framework_for_Arbitrary_Shaped_Text_Spotting_ICCV_2019_paper.pdf) | | | 0.6537 |  \n'20-AAAI    | 19/11/21  | [All You Need Is Boundary: Toward Arbitrary-Shaped Text Spotting](https://arxiv.org/pdf/1911.09550) | | 0.841 | 0.641 |  \n'20-AAAI    | 20/02/12  | [Text Perceptron: Towards End-to-End Arbitrary-Shaped Text Spotting](https://arxiv.org/abs/2002.06820) | | 0.858 | 0.651 |  \n\u003cp align='center'\u003e\n\u003cimg src = '/end2end_ic13_ic15_results.png' height = '400px'\u003e\n\u003c/p\u003e\n\n## Others\n* Papers are sorted by published date.\n* `*CODE` means official code and `CODE(M)` means that trained model is provided.\n\n*Conf.* | *Date* | *Title* | *Description* | *Resources* |\n:---: | :---: |:--- | :---: | :---: |\n'14-NIPS\t| 14/06/09  |   [Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition](https://arxiv.org/pdf/1406.2227.pdf) |\tDataset | [`PRJ`](http://www.robots.ox.ac.uk/~vgg/data/text/)\n'17-ECCV\t| 17/02/13  |\t[End-to-End Interpretation of the French Street Name Signs Dataset](https://arxiv.org/pdf/1702.03970.pdf) |\tDataset (FSNS) | [`*TF(M)`](https://github.com/tensorflow/models/tree/master/research/attention_ocr)\n'17-arXiv\t| 17/04/11\t|\t[Attention-based Extraction of Structured Information from Street View Imagery](https://arxiv.org/pdf/1704.03549.pdf) |\tFSNS | [`*TF(M)`](https://github.com/tensorflow/models/tree/master/research/attention_ocr) \u003cbr\u003e [`TF`](https://github.com/da03/Attention-OCR) \u003cbr\u003e [`TF`](https://github.com/emedvedev/attention-ocr) \u003cbr\u003e [`LUA`](https://github.com/da03/torch-Attention-OCR) \u003cbr\u003e [`BLOG_KR`](https://norman3.github.io/papers/docs/attention_ocr.html)\n'17-CVPR\t| 17/07/21\t|\t[Unambiguous Text Localization and Retrieval for Cluttered Scenes](http://openaccess.thecvf.com/content_cvpr_2017/papers/Rong_Unambiguous_Text_Localization_CVPR_2017_paper.pdf) |\tText Retrieval\n'17-AAAI\t| 17/10/22\t|\t[Detection and Recognition of Text Embedded in Online Images via Neural Context Models](http://s-space.snu.ac.kr/bitstream/10371/116866/1/aaai2017_cameraready.pdf) |\tDataset | [`PRJ`](https://github.com/cmkang/CTSN)\n'18-CVPR\t| 17/11/17\t|\t[Separating Style and Content for Generalized Style Transfer](https://arxiv.org/pdf/1711.06454.pdf) |\tFont Style\n'17-arXiv\t| 17/12/06\t|\t[Detecting Curve Text in the Wild New Dataset and New Solution](https://arxiv.org/pdf/1712.02170.pdf) |\tDataset (CTW 1500) | [`PRJ`](https://github.com/Yuliang-Liu/Curve-Text-Detector)\n'18-AAAI\t| 17/12/14\t|\t[SEE: Towards Semi-Supervised End-to-End Scene Text Recognition](https://arxiv.org/pdf/1712.05404.pdf) |\tFSNS | [`PRJ`](https://bartzi.de/research/see) \u003cbr\u003e [`*CHAINER(M)`](https://github.com/Bartzi/see)\n'17-CVPR\t| 18/06/07\t|\t[Learning to Extract Semantic Structure from Documents Using Multimodal Fully Convolutional Neural Networks](https://arxiv.org/pdf/1706.02337.pdf) |\tDocument Layout | [`PRJ`](http://personal.psu.edu/xuy111/projects/cvpr2017_doc.html)\n'18-CVPR\t| 18/06/19\t|\t[DocUNet: Document Image Unwarping via A Stacked U-Net](http://www.juew.org/publication/DocUNet.pdf) |\tDocument Dewarping | [`PRJ`](http://www3.cs.stonybrook.edu/~cvl/docunet.html)\n'18-CVPR\t| 18/06/19\t|\t[Document Enhancement using Visibility Detection](http://webee.technion.ac.il/~ayellet/Ps/18-KKT.pdf) |\tDocument Enhancement | [`PRJ`](http://cgm.technion.ac.il/Computer-Graphics-Multimedia/Software/VisibilityDetection/)\n'18-IJCAI\t| 18/06/22\t|\t[Multi-Task Handwritten Document Layout Analysis](https://arxiv.org/pdf/1806.08852.pdf) |\tDocument Layout\n'18-ECCV\t| 18/07/09\t|\t[Verisimilar Image Synthesis for Accurate Detection and Recognition of Texts in Scenes](https://arxiv.org/pdf/1807.03021.pdf) |\tDataset | [`PRJ`](https://github.com/fnzhan/Verisimilar-Image-Synthesis-for-Accurate-Detection-and-Recognition-of-Texts-in-Scenes)\n'19-AAAI\t| 18/12/03  |\t[EnsNet: Ensconce Text in the Wild](https://arxiv.org/pdf/1812.00723.pdf) | Text Removal |\t[`DB`](https://github.com/HCIILAB/Scene-Text-Removal)  \n'19-CVPR\t| 18/12/14  |\t[Spatial Fusion GAN for Image Synthesis](https://arxiv.org/pdf/1812.05840.pdf) | Dataset |\t[`DB`](https://github.com/fnzhan/SF-GAN)  \n'19-AAAI\t| 19/01/27  |\t[Hierarchical Encoder with Auxiliary Supervision for Table-to-text Generation: Learning Better Representation for Tables](https://www.aaai.org/Papers/AAAI/2019/AAAI-LiuT.3205.pdf) | TableToText |\t  \n'19-AAAI\t| 19/01/27  |\t[A Radical-aware Attention-based Model for Chinese Text Classification](https://www.aaai.org/Papers/AAAI/2019/AAAI-TaoH.5441.pdf) | Chinese Character Classification |\t  \n'19-CVPR | 19/02/25 | [Handwriting Recognition in Low-resource Scripts using Adversarial Learning](https://arxiv.org/pdf/1811.01396.pdf) | Handwritting Recognition | [`TF`](https://github.com/AyanKumarBhunia/Handwriting_Recogition_using_Adversarial_Learning)\n'19-CVPR\t| 19/03/27  |\t[Tightness-aware Evaluation Protocol for Scene Text Detection](https://arxiv.org/pdf/1904.00813.pdf) | Evaluation |\t[`CODE`](https://github.com/Yuliang-Liu/TIoU-metric)  \n'19-ICCV | 19/05/31 | [Scene Text Visual Question Answering](https://arxiv.org/pdf/1905.13648v2) | Dataset | [`ICDAR_DB`](https://rrc.cvc.uab.es/?ch=11)\n'19-CVPR\t| 19/06/16  |\t[DynTypo: Example-based Dynamic Text Effects Transfer](https://menyifang.github.io/projects/DynTypo/DynTypo_files/Paper_DynTypo_CVPR19.pdf) | Text Effects |\t[`PRJ`](https://menyifang.github.io/projects/DynTypo/DynTypo.html) \u003cbr\u003e [`VIDEO`](https://youtu.be/FkFQ6bV1s-o) \n'19-CVPR | 19/06/16 | [Typography with Decor: Intelligent Text Style Transfer](http://openaccess.thecvf.com/content_CVPR_2019/papers/Wang_Typography_With_Decor_Intelligent_Text_Style_Transfer_CVPR_2019_paper.pdf) | Text Effects | [`*PYTORCH(M)`](https://daooshee.github.io/Typography2019/) \n'19-CVPR | 19/06/16 | [An Alternative Deep Feature Approach to Line Level Keyword Spotting](http://openaccess.thecvf.com/content_CVPR_2019/papers/Retsinas_An_Alternative_Deep_Feature_Approach_to_Line_Level_Keyword_Spotting_CVPR_2019_paper.pdf) | Kyeword Spotting\n'19-ICCV | 19/07/23 | [GA-DAN: Geometry-Aware Domain Adaptation Network for Scene Text Detection and Recognition](https://arxiv.org/abs/1907.09653) | Domain Adaptation |  \n'19-ICCV | 19/09/17 | [Chinese Street View Text: Large-scale Chinese Text Reading with Partially Supervised Learning](https://arxiv.org/abs/1909.07808) | Dataset | [`ICDAR_DB`](https://rrc.cvc.uab.es/?ch=16)\n'19-ICCV | 19/10/02 | [Large-scale Tag-based Font Retrieval with Generative Feature Learning](https://arxiv.org/pdf/1909.02072.pdf) | Font Retrieval |  \n'19-ICCV | 19/10/27 | [TextPlace: Visual Place Recognition and Topological Localization Through Reading Scene Texts](http://openaccess.thecvf.com/content_ICCV_2019/papers/Hong_TextPlace_Visual_Place_Recognition_and_Topological_Localization_Through_Reading_Scene_ICCV_2019_paper.pdf) | Place Recognition | [`DB`](https://github.com/ziyanghong/dataset)\n'19-ICCV | 19/10/27 | [DewarpNet: Single-Image Document Unwarping With Stacked 3D and 2D Regression Networks](http://openaccess.thecvf.com/content_ICCV_2019/papers/Das_DewarpNet_Single-Image_Document_Unwarping_With_Stacked_3D_and_2D_Regression_ICCV_2019_paper.pdf) | Document Dewarping | [`*PYTORCH(M)`](https://github.com/cvlab-stonybrook/DewarpNet)\n\n## Other lists\n* OCR Paper Curation\n    * [HCIILAB-Detection](https://github.com/HCIILAB/Scene-Text-Detection)\n    * [HCIILAB-Recognition](https://github.com/HCIILAB/Scene-Text-Recognition)\n    * [HCIILAB-End2End](https://github.com/HCIILAB/Scene-Text-End2end)\n    * [whitelok](https://github.com/whitelok/image-text-localization-recognition)\n    * [tangzhenyu](https://github.com/tangzhenyu/Scene-Text-Understanding)\n    * [wanghaisheng](https://github.com/wanghaisheng/awesome-ocr)\n    * [ChanChiChoi](https://github.com/ChanChiChoi/awesome-ocr/blob/master/README.md)\n    * [handong1587](https://github.com/handong1587/handong1587.github.io/blob/master/_posts/deep_learning/2015-10-09-ocr.md)\n    * [hs105](https://github.com/hs105/Deep-Learning-for-OCR)\n\n## Tutorial Materials\n* Lecture slides\n    * [Irregular Text Detection and Recognition (CBDAR2019 keynote)](http://122.205.5.5:8071/~xbai/Talk_slice/IrregularText-CBDAR2019.pptx)\n    * [Deep Neural Networks for Scene Text Reading (IC17 Keynote)](http://u-pat.org/ICDAR2017/keynotes/ICDAR2017_Keynote_Prof_Bai.pdf)\n    * [Oriented Scene Text Detection Revisited (VALSE17 Invited Talk)](http://cloud.eic.hust.edu.cn:8071/~xbai/Talk_slice/Oriented-Scene-Text-Detection-Revisited_VALSE2017.pdf)\n    * [Scene Text Detection and Recognition (Joint course of Megvii Inc. \u0026 Peking Univ.)](https://zsc.github.io/megvii-pku-dl-course/slides/Lecture7(Text%20Detection%20and%20Recognition_20171031).pdf)\n    * [Classic Text Detectors](https://www.slideshare.net/anyline_io/text-detection-strategies)\n* Survey Paper\n    * [Scene text detection and recognition: recent advances and future trends](https://www.researchgate.net/profile/Xiang_Bai4/publication/286945604_Scene_text_detection_and_recognition_recent_advances_and_future_trends/links/57f720f408ae886b8981d364/Scene-text-detection-and-recognition-recent-advances-and-future-trends.pdf)\n\n## Acknowledgment\n* This work is done by OCR team in Clova AI powered by NAVER-LINE. NAVER-LINE is an Asian top internet company and develops Clova, a cloud-based AI-assistant platform.\n* This repository is scheduled to be updated regularly in accordance with schedules of major AI conferences.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhwalsuklee%2Fawesome-deep-text-detection-recognition","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhwalsuklee%2Fawesome-deep-text-detection-recognition","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhwalsuklee%2Fawesome-deep-text-detection-recognition/lists"}