Improving Handwritten Text Recognition via 3D Attention and Multi-Scale Training Article Swipe
The segmentation-free research efforts for addressing handwritten text recognition can be divided into three categories: connectionist temporal classification (CTC), hidden Markov model and encoder-decoder methods. In this paper, inspired by the above three modeling methods, we propose a new recognition network by using a novel three-dimensional (3D) attention module and global-local context information. Based on the feature maps of the last convolutional layer, a series of 3D blocks with different resolutions are split. Then, these 3D blocks are fed into the 3D attention module to generate sequential visual features. Finally, by fusing the visual features and the corresponding global-local context features, a well-designed representation can be obtained. Main canonical neural units including attention mechanisms, fully-connected layers, recurrent units and convolutional layers are efficiently organized into a network and can be jointly trained by the CTC loss and the cross-entropy loss. Experiments on the latest Chinese handwritten text datasets (the SCUT-HCCDoc and the SCUT-EPT) and one English handwritten text dataset (the IAM) show that the proposed method can achieve comparable results with the state-of-the-art methods. The code is available at https://github.com/Wukong90/3DAttention-MultiScaleTraining-for-HTR.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2410.18374
- https://arxiv.org/pdf/2410.18374
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4404306452
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4404306452Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2410.18374Digital Object Identifier
- Title
-
Improving Handwritten Text Recognition via 3D Attention and Multi-Scale TrainingWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2024Year of publication
- Publication date
-
2024-10-24Full publication date if available
- Authors
-
Zirui WangList of authors in order
- Landing page
-
https://arxiv.org/abs/2410.18374Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2410.18374Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2410.18374Direct OA link when available
- Concepts
-
Computer science, Training (meteorology), Scale (ratio), Speech recognition, Artificial intelligence, Artificial neural network, Pattern recognition (psychology), Natural language processing, Cartography, Geography, MeteorologyTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4404306452 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2410.18374 |
| ids.doi | https://doi.org/10.48550/arxiv.2410.18374 |
| ids.openalex | https://openalex.org/W4404306452 |
| fwci | |
| type | preprint |
| title | Improving Handwritten Text Recognition via 3D Attention and Multi-Scale Training |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10601 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9781000018119812 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1707 |
| topics[0].subfield.display_name | Computer Vision and Pattern Recognition |
| topics[0].display_name | Handwritten Text Recognition Techniques |
| topics[1].id | https://openalex.org/T14339 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9660999774932861 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1707 |
| topics[1].subfield.display_name | Computer Vision and Pattern Recognition |
| topics[1].display_name | Image Processing and 3D Reconstruction |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.6737703084945679 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C2777211547 |
| concepts[1].level | 2 |
| concepts[1].score | 0.6053546071052551 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q17141490 |
| concepts[1].display_name | Training (meteorology) |
| concepts[2].id | https://openalex.org/C2778755073 |
| concepts[2].level | 2 |
| concepts[2].score | 0.569080114364624 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q10858537 |
| concepts[2].display_name | Scale (ratio) |
| concepts[3].id | https://openalex.org/C28490314 |
| concepts[3].level | 1 |
| concepts[3].score | 0.5190675854682922 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q189436 |
| concepts[3].display_name | Speech recognition |
| concepts[4].id | https://openalex.org/C154945302 |
| concepts[4].level | 1 |
| concepts[4].score | 0.4680668115615845 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[4].display_name | Artificial intelligence |
| concepts[5].id | https://openalex.org/C50644808 |
| concepts[5].level | 2 |
| concepts[5].score | 0.44629982113838196 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q192776 |
| concepts[5].display_name | Artificial neural network |
| concepts[6].id | https://openalex.org/C153180895 |
| concepts[6].level | 2 |
| concepts[6].score | 0.4345845580101013 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q7148389 |
| concepts[6].display_name | Pattern recognition (psychology) |
| concepts[7].id | https://openalex.org/C204321447 |
| concepts[7].level | 1 |
| concepts[7].score | 0.3667636215686798 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q30642 |
| concepts[7].display_name | Natural language processing |
| concepts[8].id | https://openalex.org/C58640448 |
| concepts[8].level | 1 |
| concepts[8].score | 0.0617392361164093 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q42515 |
| concepts[8].display_name | Cartography |
| concepts[9].id | https://openalex.org/C205649164 |
| concepts[9].level | 0 |
| concepts[9].score | 0.05377680063247681 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q1071 |
| concepts[9].display_name | Geography |
| concepts[10].id | https://openalex.org/C153294291 |
| concepts[10].level | 1 |
| concepts[10].score | 0.0 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q25261 |
| concepts[10].display_name | Meteorology |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.6737703084945679 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/training |
| keywords[1].score | 0.6053546071052551 |
| keywords[1].display_name | Training (meteorology) |
| keywords[2].id | https://openalex.org/keywords/scale |
| keywords[2].score | 0.569080114364624 |
| keywords[2].display_name | Scale (ratio) |
| keywords[3].id | https://openalex.org/keywords/speech-recognition |
| keywords[3].score | 0.5190675854682922 |
| keywords[3].display_name | Speech recognition |
| keywords[4].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[4].score | 0.4680668115615845 |
| keywords[4].display_name | Artificial intelligence |
| keywords[5].id | https://openalex.org/keywords/artificial-neural-network |
| keywords[5].score | 0.44629982113838196 |
| keywords[5].display_name | Artificial neural network |
| keywords[6].id | https://openalex.org/keywords/pattern-recognition |
| keywords[6].score | 0.4345845580101013 |
| keywords[6].display_name | Pattern recognition (psychology) |
| keywords[7].id | https://openalex.org/keywords/natural-language-processing |
| keywords[7].score | 0.3667636215686798 |
| keywords[7].display_name | Natural language processing |
| keywords[8].id | https://openalex.org/keywords/cartography |
| keywords[8].score | 0.0617392361164093 |
| keywords[8].display_name | Cartography |
| keywords[9].id | https://openalex.org/keywords/geography |
| keywords[9].score | 0.05377680063247681 |
| keywords[9].display_name | Geography |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2410.18374 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4306400194 |
| locations[0].source.issn | |
| locations[0].source.type | repository |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | arXiv (Cornell University) |
| locations[0].source.host_organization | https://openalex.org/I205783295 |
| locations[0].source.host_organization_name | Cornell University |
| locations[0].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[0].license | |
| locations[0].pdf_url | https://arxiv.org/pdf/2410.18374 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | text |
| locations[0].license_id | |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | http://arxiv.org/abs/2410.18374 |
| locations[1].id | doi:10.48550/arxiv.2410.18374 |
| locations[1].is_oa | True |
| locations[1].source.id | https://openalex.org/S4306400194 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | True |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | arXiv (Cornell University) |
| locations[1].source.host_organization | https://openalex.org/I205783295 |
| locations[1].source.host_organization_name | Cornell University |
| locations[1].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[1].license | |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | |
| locations[1].is_accepted | False |
| locations[1].is_published | |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | https://doi.org/10.48550/arxiv.2410.18374 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5100687847 |
| authorships[0].author.orcid | https://orcid.org/0000-0003-0626-742X |
| authorships[0].author.display_name | Zirui Wang |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Wang, Zi-Rui |
| authorships[0].is_corresponding | True |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2410.18374 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2024-11-13T00:00:00 |
| display_name | Improving Handwritten Text Recognition via 3D Attention and Multi-Scale Training |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T10601 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9781000018119812 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1707 |
| primary_topic.subfield.display_name | Computer Vision and Pattern Recognition |
| primary_topic.display_name | Handwritten Text Recognition Techniques |
| related_works | https://openalex.org/W230091440, https://openalex.org/W2233261550, https://openalex.org/W2810751659, https://openalex.org/W258997015, https://openalex.org/W2997094352, https://openalex.org/W3216976533, https://openalex.org/W100620283, https://openalex.org/W2495260952, https://openalex.org/W4366179611, https://openalex.org/W2996078371 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2410.18374 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4306400194 |
| best_oa_location.source.issn | |
| best_oa_location.source.type | repository |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | arXiv (Cornell University) |
| best_oa_location.source.host_organization | https://openalex.org/I205783295 |
| best_oa_location.source.host_organization_name | Cornell University |
| best_oa_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| best_oa_location.license | |
| best_oa_location.pdf_url | https://arxiv.org/pdf/2410.18374 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | text |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | False |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | http://arxiv.org/abs/2410.18374 |
| primary_location.id | pmh:oai:arXiv.org:2410.18374 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4306400194 |
| primary_location.source.issn | |
| primary_location.source.type | repository |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | arXiv (Cornell University) |
| primary_location.source.host_organization | https://openalex.org/I205783295 |
| primary_location.source.host_organization_name | Cornell University |
| primary_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| primary_location.license | |
| primary_location.pdf_url | https://arxiv.org/pdf/2410.18374 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | text |
| primary_location.license_id | |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | http://arxiv.org/abs/2410.18374 |
| publication_date | 2024-10-24 |
| publication_year | 2024 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 37, 43, 63, 101, 125 |
| abstract_inverted_index.3D | 66, 75, 81 |
| abstract_inverted_index.In | 25 |
| abstract_inverted_index.at | 178 |
| abstract_inverted_index.be | 10, 105, 129 |
| abstract_inverted_index.by | 29, 41, 90, 132 |
| abstract_inverted_index.is | 176 |
| abstract_inverted_index.of | 58, 65 |
| abstract_inverted_index.on | 54, 141 |
| abstract_inverted_index.to | 84 |
| abstract_inverted_index.we | 35 |
| abstract_inverted_index.CTC | 134 |
| abstract_inverted_index.The | 0, 174 |
| abstract_inverted_index.and | 22, 49, 95, 118, 127, 136, 150, 153 |
| abstract_inverted_index.are | 71, 77, 121 |
| abstract_inverted_index.can | 9, 104, 128, 166 |
| abstract_inverted_index.fed | 78 |
| abstract_inverted_index.for | 4 |
| abstract_inverted_index.new | 38 |
| abstract_inverted_index.one | 154 |
| abstract_inverted_index.the | 30, 55, 59, 80, 92, 96, 133, 137, 142, 151, 163, 171 |
| abstract_inverted_index.(3D) | 46 |
| abstract_inverted_index.(the | 148, 159 |
| abstract_inverted_index.IAM) | 160 |
| abstract_inverted_index.Main | 107 |
| abstract_inverted_index.code | 175 |
| abstract_inverted_index.into | 12, 79, 124 |
| abstract_inverted_index.last | 60 |
| abstract_inverted_index.loss | 135 |
| abstract_inverted_index.maps | 57 |
| abstract_inverted_index.show | 161 |
| abstract_inverted_index.text | 7, 146, 157 |
| abstract_inverted_index.that | 162 |
| abstract_inverted_index.this | 26 |
| abstract_inverted_index.with | 68, 170 |
| abstract_inverted_index.Based | 53 |
| abstract_inverted_index.Then, | 73 |
| abstract_inverted_index.above | 31 |
| abstract_inverted_index.loss. | 139 |
| abstract_inverted_index.model | 21 |
| abstract_inverted_index.novel | 44 |
| abstract_inverted_index.these | 74 |
| abstract_inverted_index.three | 13, 32 |
| abstract_inverted_index.units | 110, 117 |
| abstract_inverted_index.using | 42 |
| abstract_inverted_index.(CTC), | 18 |
| abstract_inverted_index.Markov | 20 |
| abstract_inverted_index.blocks | 67, 76 |
| abstract_inverted_index.fusing | 91 |
| abstract_inverted_index.hidden | 19 |
| abstract_inverted_index.latest | 143 |
| abstract_inverted_index.layer, | 62 |
| abstract_inverted_index.layers | 120 |
| abstract_inverted_index.method | 165 |
| abstract_inverted_index.module | 48, 83 |
| abstract_inverted_index.neural | 109 |
| abstract_inverted_index.paper, | 27 |
| abstract_inverted_index.series | 64 |
| abstract_inverted_index.split. | 72 |
| abstract_inverted_index.visual | 87, 93 |
| abstract_inverted_index.Chinese | 144 |
| abstract_inverted_index.English | 155 |
| abstract_inverted_index.achieve | 167 |
| abstract_inverted_index.context | 51, 99 |
| abstract_inverted_index.dataset | 158 |
| abstract_inverted_index.divided | 11 |
| abstract_inverted_index.efforts | 3 |
| abstract_inverted_index.feature | 56 |
| abstract_inverted_index.jointly | 130 |
| abstract_inverted_index.layers, | 115 |
| abstract_inverted_index.network | 40, 126 |
| abstract_inverted_index.propose | 36 |
| abstract_inverted_index.results | 169 |
| abstract_inverted_index.trained | 131 |
| abstract_inverted_index.Finally, | 89 |
| abstract_inverted_index.datasets | 147 |
| abstract_inverted_index.features | 94 |
| abstract_inverted_index.generate | 85 |
| abstract_inverted_index.inspired | 28 |
| abstract_inverted_index.methods, | 34 |
| abstract_inverted_index.methods. | 24, 173 |
| abstract_inverted_index.modeling | 33 |
| abstract_inverted_index.proposed | 164 |
| abstract_inverted_index.research | 2 |
| abstract_inverted_index.temporal | 16 |
| abstract_inverted_index.SCUT-EPT) | 152 |
| abstract_inverted_index.attention | 47, 82, 112 |
| abstract_inverted_index.available | 177 |
| abstract_inverted_index.canonical | 108 |
| abstract_inverted_index.different | 69 |
| abstract_inverted_index.features, | 100 |
| abstract_inverted_index.features. | 88 |
| abstract_inverted_index.including | 111 |
| abstract_inverted_index.obtained. | 106 |
| abstract_inverted_index.organized | 123 |
| abstract_inverted_index.recurrent | 116 |
| abstract_inverted_index.addressing | 5 |
| abstract_inverted_index.comparable | 168 |
| abstract_inverted_index.sequential | 86 |
| abstract_inverted_index.Experiments | 140 |
| abstract_inverted_index.SCUT-HCCDoc | 149 |
| abstract_inverted_index.categories: | 14 |
| abstract_inverted_index.efficiently | 122 |
| abstract_inverted_index.handwritten | 6, 145, 156 |
| abstract_inverted_index.mechanisms, | 113 |
| abstract_inverted_index.recognition | 8, 39 |
| abstract_inverted_index.resolutions | 70 |
| abstract_inverted_index.global-local | 50, 98 |
| abstract_inverted_index.information. | 52 |
| abstract_inverted_index.connectionist | 15 |
| abstract_inverted_index.convolutional | 61, 119 |
| abstract_inverted_index.corresponding | 97 |
| abstract_inverted_index.cross-entropy | 138 |
| abstract_inverted_index.well-designed | 102 |
| abstract_inverted_index.classification | 17 |
| abstract_inverted_index.representation | 103 |
| abstract_inverted_index.encoder-decoder | 23 |
| abstract_inverted_index.fully-connected | 114 |
| abstract_inverted_index.state-of-the-art | 172 |
| abstract_inverted_index.segmentation-free | 1 |
| abstract_inverted_index.three-dimensional | 45 |
| abstract_inverted_index.https://github.com/Wukong90/3DAttention-MultiScaleTraining-for-HTR. | 179 |
| cited_by_percentile_year | |
| corresponding_author_ids | https://openalex.org/A5100687847 |
| countries_distinct_count | 0 |
| institutions_distinct_count | 1 |
| citation_normalized_percentile |