Filters








23 Hits in 2.0 sec

Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes [article]

Pengyuan Lyu, Minghui Liao, Cong Yao, Wenhao Wu, Xiang Bai
<span title="2018-08-01">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
An end-to-end trainable neural network model for scene text spotting is proposed. The proposed model, named as Mask TextSpotter, is inspired by the newly published work Mask R-CNN.  ...  Different from previous methods that also accomplish text spotting with end-to-end trainable deep neural networks, Mask TextSpotter takes advantage of simple and smooth end-to-end learning procedure, in  ...  Methodology The proposed method is an end-to-end trainable text spotter, which can handle various shapes of text.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1807.02242v2">arXiv:1807.02242v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/lylbcy4hzrgmxmhawtxcmgc23i">fatcat:lylbcy4hzrgmxmhawtxcmgc23i</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200824071952/https://arxiv.org/pdf/1807.02242v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/a2/0a/a20a00b3a1dcacf7b9b71dd6e3249de35d6f9ad7.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1807.02242v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes [article]

Minghui Liao, Pengyuan Lyu, Minghang He, Cong Yao, Wenhao Wu, Xiang Bai
<span title="2019-08-22">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
An end-to-end trainable neural network named as Mask TextSpotter is presented.  ...  Unifying text detection and text recognition in an end-to-end training fashion has become a new trend for reading text in the wild, as these two tasks are highly relevant and complementary.  ...  trainable neural network.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1908.08207v1">arXiv:1908.08207v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/q7k2ejs2xfdcnighybsh6sauua">fatcat:q7k2ejs2xfdcnighybsh6sauua</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200825194717/https://arxiv.org/pdf/1908.08207v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/37/54/375479213a9982ecf4363669bc36449ca11421a8.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1908.08207v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes [chapter]

Pengyuan Lyu, Minghui Liao, Cong Yao, Wenhao Wu, Xiang Bai
<span title="">2018</span> <i title="Springer International Publishing"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/2w3awgokqne6te4nvlofavy5a4" style="color: black;">Lecture Notes in Computer Science</a> </i> &nbsp;
An end-to-end trainable neural network model for scene text spotting is proposed. The proposed model, named as Mask TextSpotter, is inspired by the newly published work Mask R-CNN.  ...  Different from previous methods that also accomplish text spotting with end-to-end trainable deep neural networks, Mask TextSpotter takes advantage of simple and smooth end-to-end learning procedure, in  ...  Methodology The proposed method is an end-to-end trainable text spotter, which can handle various shapes of text.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-030-01264-9_5">doi:10.1007/978-3-030-01264-9_5</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/lk6uqziccvebbacm3qcjpepq5i">fatcat:lk6uqziccvebbacm3qcjpepq5i</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20180922011304/http://openaccess.thecvf.com:80/content_ECCV_2018/papers/Pengyuan_Lyu_Mask_TextSpotter_An_ECCV_2018_paper.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/ec/fa/ecfab7129c7bc95a7e285f1cf1aaa125da5c7c1f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-030-01264-9_5"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

An end-to-end TextSpotter with Explicit Alignment and Attention [article]

Tong He, Zhi Tian, Weilin Huang, Chunhua Shen, Yu Qiao, Changming Sun
<span title="2018-03-23">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
, together with a new RNN branch for word recognition, are integrated seamlessly into a single model which is end-to-end trainable.  ...  Our model achieves impressive results in end-to-end recognition on the ICDAR2015 dataset, significantly advancing most recent results, with improvements of F-measure from (0.54, 0.51, 0.47) to (0.82, 0.77  ...  Shen's participation was in part supported by an ARC Future Fellowship.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1803.03474v3">arXiv:1803.03474v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/3j6mnvtjsff3tappwjio4afwqq">fatcat:3j6mnvtjsff3tappwjio4afwqq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191018162220/https://arxiv.org/pdf/1803.03474v3.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/08/33/08331b420e1cdbf7a5e25af548a93191a8758b6c.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1803.03474v3" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Cluttered TextSpotter: An End-to-End Trainable Light- weight Scene Text Spotter for Cluttered Environment

Randheer Bagi, Tanima Dutta, Hari Prabhat Gupta
<span title="">2020</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/q7qi7j4ckfac7ehf3mjbso4hne" style="color: black;">IEEE Access</a> </i> &nbsp;
It is an end-to-end trainable deep neural network that uses local part information, global structural features, and context cue information of oriented region proposals for spotting text instances.  ...  The presence of partial occlusion or truncation artifact due to the cluttered background of scene images creates an obstacle in perceiving the text instances, which makes the process of spotting very complex  ...  FOTS [1] introduces feature sharing with rotated text proposals to develop an end-to-end trainable system for detection and recognition of scene text instances.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2020.3002808">doi:10.1109/access.2020.3002808</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/x4kbcajahrc5vgtuxsc6oyyjsa">fatcat:x4kbcajahrc5vgtuxsc6oyyjsa</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210429003938/https://ieeexplore.ieee.org/ielx7/6287639/8948470/09118889.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/64/d5/64d52cf205b0585e60b9a510e012322927750362.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2020.3002808"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> ieee.com </button> </a>

AE TextSpotter: Learning Visual and Linguistic Representation for Ambiguous Text Spotting [article]

Wenhai Wang, Xuebo Liu, Xiaozhong Ji, Enze Xie, Ding Liang, Zhibo Yang, Tong Lu, Chunhua Shen, Ping Luo
<span title="2021-07-06">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Scene text spotting aims to detect and recognize the entire word or sentence with multiple characters in natural images.  ...  Unlike previous works that merely employed visual features for text detection, this work proposes a novel text spotter, named Ambiguity Eliminating Text Spotter (AE TextSpotter), which learns both visual  ...  .: An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2008.00714v5">arXiv:2008.00714v5</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/iyd6akllorgbrni6zk5nxsbqrq">fatcat:iyd6akllorgbrni6zk5nxsbqrq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210711052512/https://arxiv.org/pdf/2008.00714v5.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/a0/5f/a05ffc4bf23cf6e064bf247ceb68030f4ae32afb.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2008.00714v5" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Context-Free TextSpotter for Real-Time and Mobile End-to-End Text Detection and Recognition [article]

Ryota Yoshihashi, Tomohiro Tanaka, Kenji Doi, Takumi Fujino, Naoaki Yamashita
<span title="2021-06-10">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In concept, end-to-end (E2E) text spotting is suitable for such purposes because it performs text detection and recognition in a single model.  ...  text spotters, with an acceptable transcription quality degradation compared to heavier ones.  ...  Acknowledgements We would like to thank Katsushi Yamashita, Daeju Kim, and members of the AI Strategy Office in SoftBank for helpful discussion.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2106.05611v1">arXiv:2106.05611v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/mok5fr5pzbhrbp24nwlle67wxi">fatcat:mok5fr5pzbhrbp24nwlle67wxi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210622032938/https://arxiv.org/pdf/2106.05611v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/b0/b9/b0b9563c5a6819f6edd9839a2c58aa2e09dc1a33.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2106.05611v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

An End-to-End TextSpotter with Explicit Alignment and Attention

Tong He, Zhi Tian, Weilin Huang, Chunhua Shen, Yu Qiao, Changming Sun
<span title="">2018</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ilwxppn4d5hizekyd3ndvy2mii" style="color: black;">2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition</a> </i> &nbsp;
, together with a new RNN branch for word recognition, are integrated seamlessly into a single model which is end-toend trainable.  ...  Our model obtains impressive results in end-to-end recognition on the ICDAR 2015 [19] , significantly advancing the most recent results [2] , with improvements of F-measure from (0.54, 0.51, 0.47) to (  ...  This inspires current work that develops a new text-alignment layer tailored for text instance which is a quadrilateral shape with arbitrary orientation.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvpr.2018.00527">doi:10.1109/cvpr.2018.00527</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/cvpr/HeTHS0S18.html">dblp:conf/cvpr/HeTHS0S18</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/m724gqh3dfeujidueeiys4tu5i">fatcat:m724gqh3dfeujidueeiys4tu5i</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190623134023/http://openaccess.thecvf.com/content_cvpr_2018/papers/He_An_End-to-End_TextSpotter_CVPR_2018_paper.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/24/15/2415c7bbe08fe58723181e09cbce4eed839a3933.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvpr.2018.00527"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Text Perceptron: Towards End-to-End Arbitrary-Shaped Text Spotting [article]

Liang Qiao, Sanli Tang, Zhanzhan Cheng, Yunlu Xu, Yi Niu, Shiliang Pu, Fei Wu
<span title="2021-10-25">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
To handle this incompatibility problem, in this paper we propose an end-to-end trainable text spotting approach named Text Perceptron.  ...  non-trainable pipeline strategies between text detection and text recognition will lead to suboptimal performances.  ...  Conclusion In this paper, we propose an end-to-end trainable text spotter named Text Perceptron aiming at spotting text with arbitrary-shapes.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2002.06820v2">arXiv:2002.06820v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/qv77ioltuzbuvdemmny5d4ke5a">fatcat:qv77ioltuzbuvdemmny5d4ke5a</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200321155017/https://arxiv.org/pdf/2002.06820v1.pdf" title="fulltext PDF download [not primary version]" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <span style="color: #f43e3e;">&#10033;</span> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2002.06820v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

A Feasible Framework for Arbitrary-Shaped Scene Text Recognition [article]

Jinjin Zhang, Wei Wang, Di Huang, Qingjie Liu, Yunhong Wang
<span title="2019-12-12">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this paper, we propose a feasible framework for multi-lingual arbitrary-shaped STR, including instance segmentation based text detection and language model based attention mechanism for text recognition  ...  Our STR algorithm not only recognizes Latin and Non-Latin characters, but also supports arbitrary-shaped text recognition.  ...  Mask TextSpotter [32] adopts Mask R-CNN based instance segmentation method for end-to-end trainable scene text spotting but need character level segmentation.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1912.04561v2">arXiv:1912.04561v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/5rtipn2hsjefjifv57ouizawoi">fatcat:5rtipn2hsjefjifv57ouizawoi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200911123022/https://arxiv.org/pdf/1912.04561v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/eb/0a/eb0aed0c70f84e6995589182d52189f8ffd5d034.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1912.04561v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Text Perceptron: Towards End-to-End Arbitrary-Shaped Text Spotting

Liang Qiao, Sanli Tang, Zhanzhan Cheng, Yunlu Xu, Yi Niu, Shiliang Pu, Fei Wu
<span title="2020-04-03">2020</span> <i title="Association for the Advancement of Artificial Intelligence (AAAI)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/wtjcymhabjantmdtuptkk62mlq" style="color: black;">PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE</a> </i> &nbsp;
To handle this incompatibility problem, in this paper we propose an end-to-end trainable text spotting approach named Text Perceptron.  ...  non-trainable pipeline strategies between text detection and text recognition will lead to suboptimal performances.  ...  Conclusion In this paper, we propose an end-to-end trainable text spotter named Text Perceptron aiming at spotting text with arbitrary-shapes.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1609/aaai.v34i07.6864">doi:10.1609/aaai.v34i07.6864</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/4jqpb3xktrc4jfvesivjs4ruoy">fatcat:4jqpb3xktrc4jfvesivjs4ruoy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201103095728/https://aaai.org/ojs/index.php/AAAI/article/download/6864/6718" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/cb/27/cb27cc7f82e197a12335d35780962b9f2511721a.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1609/aaai.v34i07.6864"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

ABCNet: Real-time Scene Text Spotting with Adaptive Bezier-Curve Network [article]

Yuliang Liu, Hao Chen, Chunhua Shen, Tong He, Lianwen Jin, Liangwei Wang
<span title="2020-02-25">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
features of a text instance with arbitrary shapes, significantly improving the precision compared with previous methods. 3) Compared with standard bounding box detection, our Bezier curve detection introduces  ...  These methods either are costly for character annotation or need to maintain a complex pipeline, which is often not suitable for real-time applications.  ...  Acknowledgements The authors would like to thank Huawei Technologies for the donation of GPU cloud computing resources.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2002.10200v2">arXiv:2002.10200v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ef7lsgcflfaqxcqsv7rjisfazu">fatcat:ef7lsgcflfaqxcqsv7rjisfazu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200321095652/https://arxiv.org/pdf/2002.10200v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/3d/a1/3da15c04db020c629aeb71b856cfdc7127b677ff.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2002.10200v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

An end-to-end text spotter with text relation networks

Jianguo Jiang, Baole Wei, Min Yu, Gang Li, Boquan Li, Chao Liu, Min Li, Weiqing Huang
<span title="2021-04-01">2021</span> <i title="Springer Science and Business Media LLC"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/nvdntm3qtfcjzjwo3aacs6zhtu" style="color: black;">Cybersecurity</a> </i> &nbsp;
Specifically, end-to-end spotting of scene text has attracted significant research attention, and relatively ideal accuracy has been achieved on several datasets.  ...  In this paper, we propose a novel graph-based method for intermediate semantic features enhancement, called Text Relation Networks.  ...  In public opinion analysis tasks, texts in images drawbacks, by handling detection and recognition with an end-to-end trainable neural network.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1186/s42400-021-00073-x">doi:10.1186/s42400-021-00073-x</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/b5qp5c5iynbufid625xt7cb7fe">fatcat:b5qp5c5iynbufid625xt7cb7fe</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210407060953/https://cybersecurity.springeropen.com/track/pdf/10.1186/s42400-021-00073-x.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/b6/c6/b6c618ea5b53943a3a593dfe4fb005ac662e81c0.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1186/s42400-021-00073-x"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> springer.com </button> </a>

Towards End-to-End Text Spotting in Natural Scenes [article]

Peng Wang, Hui Li, Chunhua Shen
<span title="2021-06-26">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The whole framework can be trained end-to-end and is able to handle text of arbitrary shapes. The convolutional features are calculated only once and shared by both detection and recognition modules.  ...  It provides the spatial location for each character, which not only helps local feature extraction in word recognition, but also indicates an orientation angle to refine text localization.  ...  [10] proposed the first end-to-end trainable framework for scene text spotting.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1906.06013v6">arXiv:1906.06013v6</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/6yijskgdkjd2tposdbgw7xtfvq">fatcat:6yijskgdkjd2tposdbgw7xtfvq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210729222529/https://arxiv.org/pdf/1906.06013v6.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/66/91/6691bd0dabaf995b88a664675519114599b6a21f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1906.06013v6" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Learning to Predict More Accurate Text Instances for Scene Text Detection [article]

XiaoQian Li, Jie Liu, ShuWu Zhang, GuiXuan Zhang
<span title="2020-04-16">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Nevertheless, there are still some difficulties for arbitrary shape text detection, especially for a simple and proper representation of arbitrary shape text instances.  ...  In this paper, a pixel-based text detector is proposed to facilitate the representation and prediction of text instances with arbitrary shapes in a simple manner.  ...  The network can be end-to-end trainable by the losses in Section 3.5.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1911.07423v2">arXiv:1911.07423v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/5ecnsizt3ja5lhne7uyzessjz4">fatcat:5ecnsizt3ja5lhne7uyzessjz4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200418002348/https://arxiv.org/pdf/1911.07423v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1911.07423v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 23 results