@prefix dcat: . @prefix dct: . @prefix foaf: . @prefix hydra: . @prefix vcard: . @prefix xsd: . a hydra:PagedCollection ; hydra:firstPage "https://service.tib.eu/3wave/ldmservice/catalog.ttl?page=1" ; hydra:itemsPerPage 100 ; hydra:lastPage "https://service.tib.eu/3wave/ldmservice/catalog.ttl?page=1" ; hydra:totalItems 6 . a dcat:Dataset ; dct:description """# A Neural Approach for Text Extraction from Scholarly Figures\r This is the readme for the supplemental data for our ICDAR 2019 paper.\r \r You can read our paper via IEEE here: https://ieeexplore.ieee.org/document/8978202\r \r If you found this dataset useful, please consider citing our paper:\r \r @inproceedings{DBLP:conf/icdar/MorrisTE19,\r author = {David Morris and\r Peichen Tang and\r Ralph Ewerth},\r title = {A Neural Approach for Text Extraction from Scholarly Figures},\r booktitle = {2019 International Conference on Document Analysis and Recognition,\r {ICDAR} 2019, Sydney, Australia, September 20-25, 2019},\r pages = {1438--1443},\r publisher = {{IEEE}},\r year = {2019},\r url = {https://doi.org/10.1109/ICDAR.2019.00231},\r doi = {10.1109/ICDAR.2019.00231},\r timestamp = {Tue, 04 Feb 2020 13:28:39 +0100},\r biburl = {https://dblp.org/rec/conf/icdar/MorrisTE19.bib},\r bibsource = {dblp computer science bibliography, https://dblp.org}\r }\r \r This work was financially supported by the German Federal Ministry of Education and Research (BMBF) and European Social Fund (ESF) (InclusiveOCW project, no. 01PE17004).\r ## Datasets\r We used different sources of data for testing, validation, and training. Our testing set was assembled by the work we cited by Böschen et al. We excluded the DeGruyter dataset, and use it as our validation dataset.\r ### Testing\r These datasets contain a readme with license information. Further information about the associated project can be found in the authors' published work we cited: https://doi.org/10.1007/978-3-319-51811-4_2\r ### Validation\r The DeGruyter dataset does not include the labeled images due to license restrictions. As of writing, the images can still be downloaded from DeGruyter via the links in the readme. Note that depending on what program you use to strip the images out of the PDF they are provided in, you may have to re-number the images.\r ### Training\r We used [label_generator](https://github.com/domoritz/label_generator)'s generated dataset, which the author made available on a requester-pays [amazon s3 bucket](s3://escience.washington.edu.viziometrics).\r We also used the Multi-Type Web Images dataset, which is mirrored [here](https://tianchi.aliyun.com/competition/introduction.htm?spm=5176.100066.0.0.3bcad780oQ9Ce4&raceId=231651).\r ## Code\r We have made our code available in `code.zip`. We will upload code, announce further news, and field questions via the [github repo](https://github.com/david-morris/Neural-Figure-Text).\r \r Our text detection network is adapted from [Argman's EAST implementation](https://github.com/argman/EAST). The `EAST/checkpoints/ours` subdirectory contains the trained weights we used in the paper.\r \r We used a tesseract script to run text extraction from detected text rows. This is inside our code `code.tar` as `text_recognition_multipro.py`.\r \r We used a java script provided by Falk Böschen and adapted to our file structure. We included this as `evaluator.jar`.\r \r Parameter sweeps are automated by `param_sweep.rb`. This file also shows how to invoke all of these components.""" ; dct:identifier "ef96d2db-9cbe-4738-b7bf-da556e12bdc2" ; dct:issued "2022-03-16T07:44:15.166295"^^xsd:dateTime ; dct:modified "2022-03-16T07:44:15.166300"^^xsd:dateTime ; dct:publisher ; dct:title "A Neural Approach for Text Extraction from Scholarly Figures" ; dcat:contactPoint [ a vcard:Organization ; vcard:fn "David Morris, Peichen Tang, and Ralph Ewerth" ] ; dcat:creator dct:Agent ; dcat:distribution ; dcat:keyword "computer vision", "document analysis", "machine learning" ; dcat:landingPage . a dcat:Catalog ; dct:language "en" ; dct:modified "2026-02-26T15:39:24.816230"^^xsd:dateTime ; dct:title "LDM" ; dcat:dataset , , , , , ; foaf:homepage . a dcat:Dataset ; dct:description "Example usage of CAD visualization in 2D and 3D using CKAN Views." ; dct:identifier "476cdf71-1048-4a6f-a28a-58fff547dae5" ; dct:issued "2017-11-23T17:37:00.362900"^^xsd:dateTime ; dct:modified "2022-06-13T06:54:09.827455"^^xsd:dateTime ; dct:publisher ; dct:title "Example CAD Visualizations" ; dcat:contactPoint [ a vcard:Organization ; vcard:fn "Autodesk" ] ; dcat:creator dct:Agent ; dcat:distribution , , ; dcat:keyword "2D", "3D", "CAD", "dwg", "example", "visualization" ; dcat:landingPage . a dcat:Distribution ; dct:title "Example 3D .dwg file" ; dcat:accessURL ; dcat:byteSize 733036.0 . a dcat:Distribution ; dct:title "Example 2D .dwg file" ; dcat:accessURL ; dcat:byteSize 169807.0 . a dcat:Distribution ; dct:description "Example usage of CAD using Ckan View with information provided by PANGAEA." ; dct:format "ZIP" ; dct:title "PANGEA CAD example" ; dcat:accessURL ; dcat:byteSize 3414733.0 . a dcat:Dataset ; dct:description """Video about auto combustion reactions of STF50 with EDTA+CA: variying phi.\r Video about boundary value problem of a push rod. The video was published by Leibniz University Hannover.\r Video about boundary value problem of a spring. The video was published by Leibniz University Hannover.""" ; dct:identifier "54920aae-f322-4fca-bd09-cd091946632c" ; dct:issued "2017-11-24T13:42:19.407543"^^xsd:dateTime ; dct:modified "2026-02-26T15:39:24.816230"^^xsd:dateTime ; dct:publisher ; dct:title "Example Video Visualizations" ; dcat:contactPoint [ a vcard:Organization ; vcard:fn "John Doe" ] ; dcat:creator dct:Agent ; dcat:distribution , , , ; dcat:keyword "CA", "Combustion", "EDTA", "Experiment", "Reactions", "STF50", "Video" . a dcat:Distribution ; dct:format "ipynb" ; dct:title "Renewable energy analysis" ; dcat:accessURL ; dcat:byteSize 343644.0 . a dcat:Distribution ; dct:description "The video was published by Leibniz University Hannover." ; dct:format "WebM" ; dct:title "Boundary value problem of a push rod (WEBM)" ; dcat:accessURL ; dcat:byteSize 369844.0 ; dcat:mediaType "video/webm" . a dcat:Distribution ; dct:format "MP4" ; dct:title "STF50 autocombustions with varying Phi (MP4)" ; dcat:accessURL ; dcat:byteSize 71194509.0 ; dcat:mediaType "video/mp4" . a dcat:Distribution ; dct:description "The video was published by Leibniz University Hannover." ; dct:format "OGG" ; dct:title "Boundary value problem of a spring (OGG)" ; dcat:accessURL ; dcat:byteSize 543985.0 ; dcat:mediaType "audio/ogg" . a dcat:Dataset ; dct:description """This jupyter notebook runs live code performing a data exploration process\r """ ; dct:identifier "78353937-5859-4f0d-9b30-11a85c1a8682" ; dct:issued "2025-10-30T14:25:03.953079"^^xsd:dateTime ; dct:language "English" ; dct:modified "2025-10-30T14:33:18.219748"^^xsd:dateTime ; dct:publisher ; dct:title "Link Prediction example (JupyterNotebook)" ; dcat:contactPoint [ a vcard:Organization ; vcard:fn "Ariam Rivas" ; vcard:hasEmail ] ; dcat:creator dct:Agent, dct:creator ; dcat:distribution . a dcat:Distribution ; dct:description "Pattern Detection, Analysis and Explanation over Lung Cancer Knowledge Graph" ; dct:format "ipynb" ; dct:title "Symbolic Learning and Knowledge Graph Embeddings" ; dcat:accessURL ; dcat:byteSize 53025.0 . a dcat:Dataset ; dct:description "This is an example Dataset showing visualizations for documents in different formats. " ; dct:identifier "86b5446b-092a-4467-870c-b61b055d763f" ; dct:issued "2022-03-16T08:31:24.461479"^^xsd:dateTime ; dct:modified "2022-06-13T07:04:36.920112"^^xsd:dateTime ; dct:publisher ; dct:title "Example Documents Visualizations" ; dcat:contactPoint [ a vcard:Organization ; vcard:fn "John Doe" ] ; dcat:creator dct:Agent, dct:creator ; dcat:distribution , , , , , , . a dcat:Distribution ; dct:description "Just a GIF image for visualization." ; dct:format "GIF" ; dct:title "GIF image example" ; dcat:accessURL ; dcat:byteSize 3132208.0 ; dcat:mediaType "image/gif" . a dcat:Distribution ; dct:description """Intersection A with overlaid trajectory samples and background image.\r Image published by Leibniz University Hannover.""" ; dct:format "PNG" ; dct:title "PNG image example" ; dcat:accessURL ; dcat:byteSize 2085108.0 ; dcat:mediaType "image/png" . a dcat:Distribution ; dct:description """To analyse the stochastic properties of the laser tracker Leica AT960-LR, five fix points spatially distributed were continuously observed from three different positions in the 3D.\r Published by Leibniz University Hannover.""" ; dct:format "PDF" ; dct:title "Data Description (PDF)" ; dcat:accessURL ; dcat:byteSize 962808.0 ; dcat:mediaType "application/pdf" . a dcat:Distribution ; dct:description "This is just an example for visualization." ; dct:format "ODT" ; dct:title "OpenOffice Writer example (ODT) " ; dcat:accessURL ; dcat:byteSize 21423.0 ; dcat:mediaType "application/vnd.oasis.opendocument.text" . a dcat:Distribution ; dct:description "This is just an example file for visualization." ; dct:format "ODP" ; dct:title "Open Document Presentation (ODP)" ; dcat:accessURL ; dcat:byteSize 389789.0 ; dcat:mediaType "application/vnd.oasis.opendocument.presentation" . a dcat:Distribution ; dct:description """Picture of the GTEM 1250 cell.\r Image published by Leibniz University Hannover.""" ; dct:format "JPEG" ; dct:title "JPG Image example" ; dcat:accessURL ; dcat:byteSize 2437112.0 ; dcat:mediaType "image/jpeg" . a dcat:Distribution ; dct:description "This is just text for visualization." ; dct:format "TXT" ; dct:title "Text file example (TXT)" ; dcat:accessURL ; dcat:byteSize 2330.0 ; dcat:mediaType "text/plain" . a dcat:Dataset ; dct:description "This is an example Dataset showing visualizations for data in different formats." ; dct:identifier "d5d29173-addc-4e4d-af7b-59e3b147c817" ; dct:issued "2022-03-16T09:17:57.266750"^^xsd:dateTime ; dct:modified "2022-06-13T06:58:55.023676"^^xsd:dateTime ; dct:publisher ; dct:title "Example Data Formats Visualizations" ; dcat:contactPoint [ a vcard:Organization ; vcard:fn "John Doe" ] ; dcat:creator dct:Agent, dct:creator ; dcat:distribution , , , , , . a dcat:Distribution ; dct:description "This is just an example file of the format for visualization." ; dct:format "ODS" ; dct:title "Open Document Spreadsheet (ODS) Example" ; dcat:accessURL ; dcat:mediaType "application/vnd.oasis.opendocument.spreadsheet" . a dcat:Distribution ; dct:description "This is a XLSX file published by Leibniz University Hannover. " ; dct:format "XLSX" ; dct:title "XLSX Data Example" ; dcat:accessURL ; dcat:byteSize 32536.0 ; dcat:mediaType "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet" . a dcat:Distribution ; dct:description "This is a XML file published by Leibniz University Hannover." ; dct:format "XML" ; dct:title "XML Data Example" ; dcat:accessURL ; dcat:byteSize 9610.0 ; dcat:mediaType "application/xml" . a dcat:Distribution ; dct:description "This is a RDF file example generated from data published by Leibniz University Hannover. " ; dct:format "RDF" ; dct:title "RDF Data Example" ; dcat:accessURL ; dcat:byteSize 6203.0 ; dcat:mediaType "application/rdf+xml" . a dcat:Distribution ; dct:description "This is a JSON file published by Leibniz University Hannover. " ; dct:format "JSON" ; dct:title "JSON Data Example" ; dcat:accessURL ; dcat:byteSize 6211.0 ; dcat:mediaType "application/json" . a dcat:Distribution ; dct:description """All data are analysed and published 2020 under the title "Banker plants promote functional biodiversity and decrease populations of the cabbage whitefly Aleyrodes proletella".\r This dataset was published by Leibniz University Hannover.""" ; dct:format "CSV" ; dct:title "CSV Data Example" ; dcat:accessURL ; dcat:byteSize 2017.0 ; dcat:mediaType "text/csv" . a dcat:Distribution ; dct:format "ZIP" ; dct:title "code.zip" ; dcat:accessURL ; dcat:byteSize 798357692.0 ; dcat:mediaType "application/zip" . a foaf:Organization ; foaf:name "GOTTFRIED WILHELM LEIBNIZ UNIVERSITAET HANNOVER" . dct:creator dct:Agent dct:Agent ; foaf:Name "" . a foaf:Organization ; foaf:name "TIB" . dct:Agent dct:identifier ; foaf:Name "Ariam Rivas", "Autodesk", "David Morris, Peichen Tang, and Ralph Ewerth", "John Doe" .