{ "access": { "embargo": { "active": false, "reason": null }, "files": "public", "record": "public", "status": "open" }, "created": "2019-10-11T16:20:57.053467+00:00", "custom_fields": { "meeting:meeting": { "acronym": "ICDAR", "dates": "20 -25 September", "title": "15th International Conference on Document Analysis and Recognition", "url": "https://icdar2019.org/" } }, "deletion_status": { "is_deleted": false, "status": "P" }, "files": { "count": 3, "enabled": true, "entries": { "IMG.zip": { "checksum": "md5:0ed9bcd2759e391202d64bd56edfc955", "ext": "zip", "id": "e7c7ed6d-aed6-44b8-a7a5-72e4fc85286a", "key": "IMG.zip", "metadata": null, "mimetype": "application/zip", "size": 27194383 }, "LG.zip": { "checksum": "md5:6d82935ac1f8d2b511c08aaf75593d25", "ext": "zip", "id": "f1ca1785-2ebc-4d25-8f25-43c5b2a5cfcf", "key": "LG.zip", "metadata": null, "mimetype": "application/zip", "size": 35539450 }, "LG_test.zip": { "checksum": "md5:429d8a488ace9b4203b8c131fed5ffd3", "ext": "zip", "id": "61b4c981-8260-4c70-a71f-a7aaa6733c20", "key": "LG_test.zip", "metadata": null, "mimetype": "application/zip", "size": 8512828 } }, "order": [], "total_bytes": 71246661 }, "id": "3483048", "is_draft": false, "is_published": true, "links": { "access": "https://zenodo.org/api/records/3483048/access", "access_links": "https://zenodo.org/api/records/3483048/access/links", "access_request": "https://zenodo.org/api/records/3483048/access/request", "access_users": "https://zenodo.org/api/records/3483048/access/users", "archive": "https://zenodo.org/api/records/3483048/files-archive", "archive_media": "https://zenodo.org/api/records/3483048/media-files-archive", "communities": "https://zenodo.org/api/records/3483048/communities", "communities-suggestions": "https://zenodo.org/api/records/3483048/communities-suggestions", "doi": "https://doi.org/10.5281/zenodo.3483048", "draft": "https://zenodo.org/api/records/3483048/draft", "files": "https://zenodo.org/api/records/3483048/files", "latest": "https://zenodo.org/api/records/3483048/versions/latest", "latest_html": "https://zenodo.org/records/3483048/latest", "media_files": "https://zenodo.org/api/records/3483048/media-files", "parent": "https://zenodo.org/api/records/3483047", "parent_doi": "https://zenodo.org/doi/10.5281/zenodo.3483047", "parent_html": "https://zenodo.org/records/3483047", "requests": "https://zenodo.org/api/records/3483048/requests", "reserve_doi": "https://zenodo.org/api/records/3483048/draft/pids/doi", "self": "https://zenodo.org/api/records/3483048", "self_doi": "https://zenodo.org/doi/10.5281/zenodo.3483048", "self_html": "https://zenodo.org/records/3483048", "self_iiif_manifest": "https://zenodo.org/api/iiif/record:3483048/manifest", "self_iiif_sequence": "https://zenodo.org/api/iiif/record:3483048/sequence/default", "versions": "https://zenodo.org/api/records/3483048/versions" }, "media_files": { "count": 0, "enabled": false, "entries": {}, "order": [], "total_bytes": 0 }, "metadata": { "creators": [ { "affiliations": [ { "name": "Rochester Institute of Technology" } ], "person_or_org": { "family_name": "Mahshad Mahdavi", "name": "Mahshad Mahdavi", "type": "personal" } } ], "description": "
InftyMCCDB-2 dataset is a modified version of InftyCDB-2 which contains mathematical expressions from scanned article pages.
\n\nThe original dataset has 21,056 math expressions. We remove formulas with matrices and grids, leaving 19,381 formulas. The dataset includes 213 symbol classes, and is split into two sets: training (12551 images), and testing (6830 images) with approximately the same distribution of symbol classes and relation classes. The expressions range in size from a single symbol to more than 75 symbols, with an average of 7.33 symbols per expression.
\n\nThe original InftyCDB-2 provides ground truth at the symbol level. We extracted connected component bounding boxes, and generated new ground truth for each image using a labeled adjacency matrix (`label graph') representation.
\n\nThe set of .lg (label graph) ground truth files are provided, along with a .png image for each expression.
", "publication_date": "2019-10-11", "publisher": "Zenodo", "references": [ { "reference": "@inproceedings{Mahdavi2019LPGAL, title={LPGA : Line-Of-Sight Parsing with Graph-based Attention for Math Formula Recognition}, author={Mahshad Mahdavi and Michael R. Condon and Kenny Davila}, year={2019} }" } ], "resource_type": { "id": "dataset", "title": { "de": "Datensatz", "en": "Dataset" } }, "rights": [ { "title": { "en": "" } } ], "subjects": [ { "subject": "Offline Recognition" }, { "subject": "Math recognition" }, { "subject": "Typeset Equations" } ], "title": "InftyMCCDB-2 dataset", "version": "0.0" }, "parent": { "access": { "owned_by": { "user": 79810 } }, "communities": { "default": "09e3eed7-885e-45a7-b388-7dfaf7fc579f", "entries": [ { "access": { "member_policy": "open", "members_visibility": "public", "record_policy": "open", "review_policy": "open", "visibility": "public" }, "children": { "allow": false }, "created": "2019-02-25T14:20:22.935346+00:00", "custom_fields": {}, "deletion_status": { "is_deleted": false, "status": "P" }, "id": "09e3eed7-885e-45a7-b388-7dfaf7fc579f", "links": {}, "metadata": { "curation_policy": "Add "IAPR-TC11" to the community list of your upload to be listed by us.
\n\nPlease consider submitting your contributions to http://datasets.iapr-tc11.org as well.
\n\nIAPR TC11 topics of Interest include, but are not limited to:
\n\n", "description": "The International Association for Pattern Recognition (IAPR) Technical Committee Number 11 is concerned with the theory and applications of Reading Systems.", "page": "
IAPR TC11 is the International Association for Pattern Recognition (IAPR) Technical Committee Number 11. IAPR TC11 is concerned with the theory and applications of Reading Systems. We seek to study and develop systems that recognize character content and structure in handwritten and typeset documents, images, and video.
\n\nOfficial website: http://www.iapr-tc11.org
\n\nIAPR TC11 is the International Association for Pattern Recognition (IAPR) Technical Committee Number 11. IAPR TC11 is concerned with the theory and applications of Reading Systems. We seek to study and develop systems that recognize character content and structure in handwritten and typeset documents, images, and video.
\n\nThe TC11 of the IAPR has spawned a number of lively activities in the area of pattern recognition: a journal (IJDAR), three conference series (ICDAR, ICFHR and DAS), maintaining collections of data sets and software, numerous workshops, and a project for benchmarking on-line handwriting recognizers. It also organizes a summer school to promote high quality educational activities related to Reading Systems and Graphics Recognition.
", "title": "IAPR-TC11: Association for Pattern Recognition Technical Committee Number 11", "type": { "id": "organization" }, "website": "http://www.iapr-tc11.org/" }, "revision_id": 1, "slug": "iapr-tc11", "updated": "2024-03-04T09:36:13.280524+00:00" } ], "ids": [ "09e3eed7-885e-45a7-b388-7dfaf7fc579f" ] }, "id": "3483047", "pids": { "doi": { "client": "datacite", "identifier": "10.5281/zenodo.3483047", "provider": "datacite" } } }, "pids": { "doi": { "client": "datacite", "identifier": "10.5281/zenodo.3483048", "provider": "datacite" }, "oai": { "identifier": "oai:zenodo.org:3483048", "provider": "oai" } }, "revision_id": 8, "stats": { "all_versions": { "data_volume": 16800753600.0, "downloads": 660, "unique_downloads": 336, "unique_views": 1131, "views": 1272 }, "this_version": { "data_volume": 16524279784.0, "downloads": 649, "unique_downloads": 331, "unique_views": 1124, "views": 1262 } }, "status": "published", "updated": "2020-01-24T19:25:52.359140+00:00", "versions": { "index": 1, "is_latest": true } }