{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/document-layout-analysis","name":"Document Layout Analysis","slug":"document-layout-analysis","description_markdown":"\"**Document Layout Analysis** is performed to determine physical structure of a document, that is, to determine document components. These document components can consist of single connected components-regions [...] of\r\npixels that are adjacent to form single regions [...] , or group\r\nof text lines. A text line is a group of characters, symbols,\r\nand words that are adjacent, “relatively close” to each other\r\nand through which a straight line can be drawn (usually with\r\nhorizontal or vertical orientation).\"  L. O'Gorman, \"The document spectrum for page layout analysis,\" in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 15, no. 11, pp. 1162-1173, Nov. 1993.\r\n\r\nImage credit: [PubLayNet: largest dataset ever for document layout analysis](https://arxiv.org/pdf/1908.07836v1.pdf)","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":99,"papers_with_code":47,"benchmarks":6,"benchmark_tables_in_archive":6,"benchmark_tables_shown":6,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":13,"subtasks":1,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/document-layout-analysis-on-publaynet-val","slug":"document-layout-analysis-on-publaynet-val","dataset":"PubLayNet val","dataset_url":"/dataset/publaynet","rows_in_archive":15,"metrics":["Overall","Text","Title","List","Table","Figure"],"first_row_in_archive_order":{"model":"VGT","paper_title":"Vision Grid Transformer for Document Layout Analysis","paper_url":"/paper/vision-grid-transformer-for-document-layout","paper_date":"2023-08-29","arxiv_id":"2308.14978","code_links":[{"title":"alibabaresearch/advancedliteratemachinery","url":"https://github.com/alibabaresearch/advancedliteratemachinery"}],"syntology":null}},{"leaderboard":"/sota/document-layout-analysis-on-u-diads-bib","slug":"document-layout-analysis-on-u-diads-bib","dataset":"U-DIADS-Bib","dataset_url":"/dataset/u-diads-bib","rows_in_archive":5,"metrics":["Class Average IoU","Class Average IoU (Few-shot setting)"],"first_row_in_archive_order":{"model":"CV-Group","paper_title":"ICDAR 2024 Competition on Few-Shot and Many-Shot Layout Segmentation of Ancient Manuscripts (SAM)","paper_url":"/paper/icdar-2024-competition-on-few-shot-and-many","paper_date":"2024-09-11","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/document-layout-analysis-on-d4la","slug":"document-layout-analysis-on-d4la","dataset":"D4LA","dataset_url":"/dataset/d4la","rows_in_archive":3,"metrics":[" mAP","Model Parameters"],"first_row_in_archive_order":{"model":"DoPTA","paper_title":"DoPTA: Improving Document Layout Analysis using Patch-Text Alignment","paper_url":"/paper/dopta-improving-document-layout-analysis","paper_date":"2024-12-17","arxiv_id":"2412.12902","code_links":[],"syntology":null}},{"leaderboard":"/sota/document-layout-analysis-on-document-layout","slug":"document-layout-analysis-on-document-layout","dataset":"Document Layout Recognition Challenge test","dataset_url":null,"rows_in_archive":3,"metrics":["Overall","Title","Text","Figure","Table","List"],"first_row_in_archive_order":{"model":"fglihai","paper_title":null,"paper_url":null,"paper_date":"","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/document-layout-analysis-on-document-layout-1","slug":"document-layout-analysis-on-document-layout-1","dataset":"Document Layout Recognition Challenge mini-dev","dataset_url":null,"rows_in_archive":3,"metrics":["Overall","Title","Text","Figure","Table","List"],"first_row_in_archive_order":{"model":"fglihai","paper_title":null,"paper_url":null,"paper_date":"","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/document-layout-analysis-on-rvl-cdip","slug":"document-layout-analysis-on-rvl-cdip","dataset":"RVL-CDIP","dataset_url":"/dataset/rvl-cdip","rows_in_archive":1,"metrics":["FAR","WAR"],"first_row_in_archive_order":{"model":"VisualWordGrid","paper_title":"VisualWordGrid: Information Extraction From Scanned Documents Using A Multimodal Approach","paper_url":"/paper/visualwordgrid-information-extraction-from-1","paper_date":"2020-10-05","arxiv_id":"2010.02358","code_links":[],"syntology":null}}],"datasets":[{"url":"/dataset/publaynet","name":"PubLayNet","full_name":"","num_papers_in_archive":123},{"url":"/dataset/rvl-cdip","name":"RVL-CDIP","full_name":"RVL-CDIP","num_papers_in_archive":107},{"url":"/dataset/docbank","name":"DocBank","full_name":"","num_papers_in_archive":34},{"url":"/dataset/diva-hisdb","name":"DIVA-HisDB","full_name":"","num_papers_in_archive":15},{"url":"/dataset/dsse-200","name":"DSSE-200","full_name":"","num_papers_in_archive":8},{"url":"/dataset/hjdataset","name":"HJDataset","full_name":"","num_papers_in_archive":5},{"url":"/dataset/vis30k","name":"VIS30K","full_name":"","num_papers_in_archive":5},{"url":"/dataset/d4la","name":"D4LA","full_name":"","num_papers_in_archive":3},{"url":"/dataset/u-diads-bib","name":"U-DIADS-Bib","full_name":"","num_papers_in_archive":2},{"url":"/dataset/icdar-2021-competition-on-historical-map","name":"ICDAR 2021","full_name":"","num_papers_in_archive":1},{"url":"/dataset/pero-layout-dataset","name":"PERO layout dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/urdudoc","name":"UrduDoc","full_name":"","num_papers_in_archive":1},{"url":"/dataset/opendataset","name":"opendataset","full_name":"","num_papers_in_archive":0}],"subtasks":[{"url":"/task/ms-ssim","name":"MS-SSIM"}],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":99,"of":99,"of_with_code":47,"tagged_in_all":99,"counts":{"archive_papers_tagged":99,"with_a_code_link":47,"where_syntology_ran_a_sample":7,"not_listed_spam_title":0,"listed":99,"listed_where_code_ran":7,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":6,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":6,"listed_every_run_a_failure_of_syntologys_instrument":1,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/training-data-efficient-image-transformers","slug":"training-data-efficient-image-transformers","title":"Training data-efficient image transformers & distillation through attention","date":"2020-12-23","arxiv_id":"2012.12877","repositories_listed":40,"syntology":{"n":19,"n_ran":12,"n_constructed":1,"n_ran_checked":9,"n_instrument":3,"n_unverified":7,"n_honours":1,"n_violates":0,"n_no_contract":8,"n_pointer_only":3,"phrase":"12 ran (of which 1 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/training-data-efficient-image-transformers#ran","syntology_url":"https://syntology.ai/paper/2012.12877","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2012.12877"}},"official":{"repos":["facebookresearch/deit"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/layoutlm-pre-training-of-text-and-layout-for","slug":"layoutlm-pre-training-of-text-and-layout-for","title":"LayoutLM: Pre-training of Text and Layout for Document Image Understanding","date":"2019-12-31","arxiv_id":"1912.13318","repositories_listed":19,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/layoutlm-pre-training-of-text-and-layout-for#ran","syntology_url":"https://syntology.ai/paper/1912.13318","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.13318"}},"official":{"repos":["microsoft/unilm"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/beit-bert-pre-training-of-image-transformers","slug":"beit-bert-pre-training-of-image-transformers","title":"BEiT: BERT Pre-Training of Image Transformers","date":"2021-06-15","arxiv_id":"2106.08254","repositories_listed":14,"syntology":{"n":11,"n_ran":6,"n_constructed":2,"n_ran_checked":4,"n_instrument":2,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"6 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/beit-bert-pre-training-of-image-transformers#ran","syntology_url":"https://syntology.ai/paper/2106.08254","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.08254"}},"official":{"repos":["microsoft/unilm"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/layoutlmv2-multi-modal-pre-training-for","slug":"layoutlmv2-multi-modal-pre-training-for","title":"LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding","date":"2020-12-29","arxiv_id":"2012.14740","repositories_listed":9,"syntology":null},{"url":"/paper/190807836","slug":"190807836","title":"PubLayNet: largest dataset ever for document layout analysis","date":"2019-08-16","arxiv_id":"1908.07836","repositories_listed":6,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":4,"n_instrument":6,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":13,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/190807836#ran","syntology_url":"https://syntology.ai/paper/1908.07836","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.07836"}},"official":{"repos":["ibm-aur-nlp/PubLayNet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/dhsegment-a-generic-deep-learning-approach","slug":"dhsegment-a-generic-deep-learning-approach","title":"dhSegment: A generic deep-learning approach for document segmentation","date":"2018-04-27","arxiv_id":"1804.10371","repositories_listed":5,"syntology":null},{"url":"/paper/doclaynet-a-large-human-annotated-dataset-for","slug":"doclaynet-a-large-human-annotated-dataset-for","title":"DocLayNet: A Large Human-Annotated Dataset for Document-Layout Analysis","date":"2022-06-02","arxiv_id":"2206.01062","repositories_listed":4,"syntology":null},{"url":"/paper/layoutlmv3-pre-training-for-document-ai-with","slug":"layoutlmv3-pre-training-for-document-ai-with","title":"LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking","date":"2022-04-18","arxiv_id":"2204.08387","repositories_listed":4,"syntology":null},{"url":"/paper/dit-self-supervised-pre-training-for-document","slug":"dit-self-supervised-pre-training-for-document","title":"DiT: Self-supervised Pre-training for Document Image Transformer","date":"2022-03-04","arxiv_id":"2203.02378","repositories_listed":4,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/dit-self-supervised-pre-training-for-document#ran","syntology_url":"https://syntology.ai/paper/2203.02378","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.02378"}},"official":{"repos":["microsoft/unilm"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/towards-end-to-end-unified-scene-text","slug":"towards-end-to-end-unified-scene-text","title":"Towards End-to-End Unified Scene Text Detection and Layout Analysis","date":"2022-03-28","arxiv_id":"2203.15143","repositories_listed":3,"syntology":{"n":15,"n_ran":8,"n_constructed":7,"n_ran_checked":8,"n_instrument":0,"n_unverified":7,"n_honours":0,"n_violates":1,"n_no_contract":7,"n_pointer_only":15,"phrase":"8 ran (of which 7 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/towards-end-to-end-unified-scene-text#ran","syntology_url":"https://syntology.ai/paper/2203.15143","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.15143"}},"official":{"repos":["google-research-datasets/hiertext","tensorflow/models"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/cdec-net-composite-deformable-cascade-network","slug":"cdec-net-composite-deformable-cascade-network","title":"CDeC-Net: Composite Deformable Cascade Network for Table Detection in Document Images","date":"2020-08-25","arxiv_id":"2008.10831","repositories_listed":3,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/cdec-net-composite-deformable-cascade-network#ran","syntology_url":"https://syntology.ai/paper/2008.10831","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.10831"}},"official":{"repos":["mdv3101/CDeCNet"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-large-dataset-of-historical-japanese","slug":"a-large-dataset-of-historical-japanese","title":"A Large Dataset of Historical Japanese Documents with Complex Layouts","date":"2020-04-18","arxiv_id":"2004.08686","repositories_listed":3,"syntology":null},{"url":"/paper/combining-visual-and-textual-features-for-1","slug":"combining-visual-and-textual-features-for-1","title":"Combining Visual and Textual Features for Semantic Segmentation of Historical Newspapers","date":"2020-02-14","arxiv_id":"2002.06144","repositories_listed":3,"syntology":null},{"url":"/paper/doclayout-yolo-enhancing-document-layout","slug":"doclayout-yolo-enhancing-document-layout","title":"DocLayout-YOLO: Enhancing Document Layout Analysis through Diverse Synthetic Data and Global-to-Local Adaptive Perception","date":"2024-10-16","arxiv_id":"2410.12628","repositories_listed":2,"syntology":null},{"url":"/paper/text-role-classification-in-scientific-charts","slug":"text-role-classification-in-scientific-charts","title":"Text Role Classification in Scientific Charts Using Multimodal Transformers","date":"2024-02-08","arxiv_id":"2402.14579","repositories_listed":2,"syntology":null},{"url":"/paper/docbank-a-benchmark-dataset-for-document","slug":"docbank-a-benchmark-dataset-for-document","title":"DocBank: A Benchmark Dataset for Document Layout Analysis","date":"2020-06-01","arxiv_id":"2006.01038","repositories_listed":2,"syntology":null},{"url":"/paper/class-agnostic-region-of-interest-matching-in","slug":"class-agnostic-region-of-interest-matching-in","title":"Class-Agnostic Region-of-Interest Matching in Document Images","date":"2025-06-26","arxiv_id":"2506.21055","repositories_listed":1,"syntology":null},{"url":"/paper/sfdla-source-free-document-layout-analysis","slug":"sfdla-source-free-document-layout-analysis","title":"SFDLA: Source-Free Document Layout Analysis","date":"2025-03-24","arxiv_id":"2503.18742","repositories_listed":1,"syntology":null},{"url":"/paper/pp-doclayout-a-unified-document-layout","slug":"pp-doclayout-a-unified-document-layout","title":"PP-DocLayout: A Unified Document Layout Detection Model to Accelerate Large-Scale Data Construction","date":"2025-03-21","arxiv_id":"2503.17213","repositories_listed":1,"syntology":null},{"url":"/paper/unihdsa-a-unified-relation-prediction","slug":"unihdsa-a-unified-relation-prediction","title":"UniHDSA: A Unified Relation Prediction Approach for Hierarchical Document Structure Analysis","date":"2025-03-20","arxiv_id":"2503.15893","repositories_listed":1,"syntology":null},{"url":"/paper/information-extraction-from-visually-rich-1","slug":"information-extraction-from-visually-rich-1","title":"Information Extraction from Visually Rich Documents Using Directed Weighted Graph Neural Network","date":"2024-09-11","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/pdftable-a-unified-toolkit-for-deep-learning","slug":"pdftable-a-unified-toolkit-for-deep-learning","title":"PdfTable: A Unified Toolkit for Deep Learning-Based Table Extraction","date":"2024-09-08","arxiv_id":"2409.05125","repositories_listed":1,"syntology":null},{"url":"/paper/daniel-a-fast-document-attention-network-for","slug":"daniel-a-fast-document-attention-network-for","title":"DANIEL: A fast Document Attention Network for Information Extraction and Labelling of handwritten documents","date":"2024-07-12","arxiv_id":"2407.09103","repositories_listed":1,"syntology":null},{"url":"/paper/rodla-benchmarking-the-robustness-of-document","slug":"rodla-benchmarking-the-robustness-of-document","title":"RoDLA: Benchmarking the Robustness of Document Layout Analysis Models","date":"2024-03-21","arxiv_id":"2403.14442","repositories_listed":1,"syntology":null},{"url":"/paper/detect-order-construct-a-tree-construction","slug":"detect-order-construct-a-tree-construction","title":"Detect-Order-Construct: A Tree Construction based Approach for Hierarchical Document Structure Analysis","date":"2024-01-22","arxiv_id":"2401.11874","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-weighted-graph-representation-for","slug":"multimodal-weighted-graph-representation-for","title":"Multimodal weighted graph representation for information extraction from visually rich documents.","date":"2024-01-05","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/dcqa-document-level-chart-question-answering","slug":"dcqa-document-level-chart-question-answering","title":"DCQA: Document-Level Chart Question Answering towards Complex Reasoning and Common-Sense Understanding","date":"2023-10-29","arxiv_id":"2310.18983","repositories_listed":1,"syntology":null},{"url":"/paper/docxchain-a-powerful-open-source-toolchain","slug":"docxchain-a-powerful-open-source-toolchain","title":"DocXChain: A Powerful Open-Source Toolchain for Document Parsing and Beyond","date":"2023-10-19","arxiv_id":"2310.12430","repositories_listed":1,"syntology":null},{"url":"/paper/appjsonify-an-academic-paper-pdf-to-json","slug":"appjsonify-an-academic-paper-pdf-to-json","title":"appjsonify: An Academic Paper PDF-to-JSON Conversion Toolkit","date":"2023-10-02","arxiv_id":"2310.01206","repositories_listed":1,"syntology":null},{"url":"/paper/document-ai-a-comparative-study-of","slug":"document-ai-a-comparative-study-of","title":"Document AI: A Comparative Study of Transformer-Based, Graph-Based Models, and Convolutional Neural Networks For Document Layout Analysis","date":"2023-08-29","arxiv_id":"2308.15517","repositories_listed":1,"syntology":null},{"url":"/paper/vision-grid-transformer-for-document-layout","slug":"vision-grid-transformer-for-document-layout","title":"Vision Grid Transformer for Document Layout Analysis","date":"2023-08-29","arxiv_id":"2308.14978","repositories_listed":1,"syntology":null},{"url":"/paper/a-graphical-approach-to-document-layout","slug":"a-graphical-approach-to-document-layout","title":"A Graphical Approach to Document Layout Analysis","date":"2023-08-03","arxiv_id":"2308.02051","repositories_listed":1,"syntology":null},{"url":"/paper/document-layout-annotation-database-and","slug":"document-layout-annotation-database-and","title":"Document Layout Annotation: Database and Benchmark in the Domain of Public Affairs","date":"2023-06-12","arxiv_id":"2306.10046","repositories_listed":1,"syntology":null},{"url":"/paper/selfdocseg-a-self-supervised-vision-based","slug":"selfdocseg-a-self-supervised-vision-based","title":"SelfDocSeg: A Self-Supervised vision-based Approach towards Document Segmentation","date":"2023-05-01","arxiv_id":"2305.00795","repositories_listed":1,"syntology":null},{"url":"/paper/paragraph2graph-a-gnn-based-framework-for","slug":"paragraph2graph-a-gnn-based-framework-for","title":"PARAGRAPH2GRAPH: A GNN-based framework for layout paragraph analysis","date":"2023-04-24","arxiv_id":"2304.11810","repositories_listed":1,"syntology":null},{"url":"/paper/badlad-a-large-multi-domain-bengali-document","slug":"badlad-a-large-multi-domain-bengali-document","title":"BaDLAD: A Large Multi-Domain Bengali Document Layout Analysis Dataset","date":"2023-03-09","arxiv_id":"2303.05325","repositories_listed":1,"syntology":null},{"url":"/paper/cte-a-dataset-for-contextualized-table","slug":"cte-a-dataset-for-contextualized-table","title":"CTE: A Dataset for Contextualized Table Extraction","date":"2023-02-02","arxiv_id":"2302.01451","repositories_listed":1,"syntology":null},{"url":"/paper/m6doc-a-large-scale-multi-format-multi-type","slug":"m6doc-a-large-scale-multi-format-multi-type","title":"M6Doc: A Large-Scale Multi-Format, Multi-Type, Multi-Layout, Multi-Language, Multi-Annotation Category Dataset for Modern Document Layout Analysis","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/doc2graph-a-task-agnostic-document","slug":"doc2graph-a-task-agnostic-document","title":"Doc2Graph: a Task Agnostic Document Understanding Framework based on Graph Neural Networks","date":"2022-08-23","arxiv_id":"2208.11168","repositories_listed":1,"syntology":null},{"url":"/paper/doc-gcn-heterogeneous-graph-convolutional","slug":"doc-gcn-heterogeneous-graph-convolutional","title":"Doc-GCN: Heterogeneous Graph Convolutional Networks for Document Layout Analysis","date":"2022-08-22","arxiv_id":"2208.10970","repositories_listed":1,"syntology":null},{"url":"/paper/docsegtr-an-instance-level-end-to-end","slug":"docsegtr-an-instance-level-end-to-end","title":"DocSegTr: An Instance-Level End-to-End Document Image Segmentation Transformer","date":"2022-01-27","arxiv_id":"2201.11438","repositories_listed":1,"syntology":null},{"url":"/paper/layoutreader-pre-training-of-text-and-layout","slug":"layoutreader-pre-training-of-text-and-layout","title":"LayoutReader: Pre-training of Text and Layout for Reading Order Detection","date":"2021-08-26","arxiv_id":"2108.11591","repositories_listed":1,"syntology":null},{"url":"/paper/docsynth-a-layout-guided-approach-for","slug":"docsynth-a-layout-guided-approach-for","title":"DocSynth: A Layout Guided Approach for Controllable Document Image Synthesis","date":"2021-07-06","arxiv_id":"2107.02638","repositories_listed":1,"syntology":null},{"url":"/paper/icdar-2021-competition-on-historical-map","slug":"icdar-2021-competition-on-historical-map","title":"ICDAR 2021 Competition on Historical Map Segmentation","date":"2021-05-27","arxiv_id":"2105.13265","repositories_listed":1,"syntology":null},{"url":"/paper/vsr-a-unified-framework-for-document-layout","slug":"vsr-a-unified-framework-for-document-layout","title":"VSR: A Unified Framework for Document Layout Analysis combining Vision, Semantics and Relations","date":"2021-05-13","arxiv_id":"2105.06220","repositories_listed":1,"syntology":null},{"url":"/paper/docextractor-an-off-the-shelf-historical","slug":"docextractor-an-off-the-shelf-historical","title":"docExtractor: An off-the-shelf historical document element extraction","date":"2020-12-15","arxiv_id":"2012.08191","repositories_listed":1,"syntology":null},{"url":"/paper/multi-task-handwritten-document-layout","slug":"multi-task-handwritten-document-layout","title":"Multi-Task Handwritten Document Layout Analysis","date":"2018-06-22","arxiv_id":"1806.08852","repositories_listed":1,"syntology":null},{"url":null,"slug":"from-codicology-to-code-a-comparative-study","title":"From Codicology to Code: A Comparative Study of Transformer and YOLO-based Detectors for Layout Analysis in Historical Documents","date":"2025-06-25","arxiv_id":"2506.20326","repositories_listed":0,"syntology":null},{"url":null,"slug":"scan-semantic-document-layout-analysis-for","title":"SCAN: Semantic Document Layout Analysis for Textual and Visual Retrieval-Augmented Generation","date":"2025-05-20","arxiv_id":"2505.14381","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-document-processing-pipeline-for-the","title":"A document processing pipeline for the construction of a dataset for topic modeling based on the judgments of the Italian Supreme Court","date":"2025-05-13","arxiv_id":"2505.08439","repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmarking-graph-neural-networks-for-1","title":"Benchmarking Graph Neural Networks for Document Layout Analysis in Public Affairs","date":"2025-05-12","arxiv_id":"2505.14699","repositories_listed":0,"syntology":null},{"url":"/paper/annopage-dataset-dataset-of-non-textual","slug":"annopage-dataset-dataset-of-non-textual","title":"AnnoPage Dataset: Dataset of Non-Textual Elements in Documents with Fine-Grained Categorization","date":"2025-03-28","arxiv_id":"2503.22526","repositories_listed":0,"syntology":null},{"url":null,"slug":"edocnet-efficient-datasheet-layout-analysis","title":"EDocNet: Efficient Datasheet Layout Analysis Based on Focus and Global Knowledge Distillation","date":"2025-02-23","arxiv_id":"2502.16541","repositories_listed":0,"syntology":null},{"url":null,"slug":"graph-based-document-structure-analysis","title":"Graph-based Document Structure Analysis","date":"2025-02-04","arxiv_id":"2502.02501","repositories_listed":0,"syntology":null},{"url":null,"slug":"docsam-unified-document-image-segmentation","title":"DocSAM: Unified Document Image Segmentation via Query Decomposition and Heterogeneous Mixed Learning","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/dopta-improving-document-layout-analysis","slug":"dopta-improving-document-layout-analysis","title":"DoPTA: Improving Document Layout Analysis using Patch-Text Alignment","date":"2024-12-17","arxiv_id":"2412.12902","repositories_listed":0,"syntology":null},{"url":"/paper/icdar-2024-competition-on-few-shot-and-many","slug":"icdar-2024-competition-on-few-shot-and-many","title":"ICDAR 2024 Competition on Few-Shot and Many-Shot Layout Segmentation of Ancient Manuscripts (SAM)","date":"2024-09-11","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"distildoc-knowledge-distillation-for-visually","title":"DistilDoc: Knowledge Distillation for Visually-Rich Document Applications","date":"2024-06-12","arxiv_id":"2406.08226","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupdla-towards-unsupervised-document-layout","title":"UnSupDLA: Towards Unsupervised Document Layout Analysis","date":"2024-06-10","arxiv_id":"2406.06236","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-unified-multi-granularity-text","title":"Towards Unified Multi-granularity Text Detection with Interactive Attention","date":"2024-05-30","arxiv_id":"2405.19765","repositories_listed":0,"syntology":null},{"url":null,"slug":"dlaformer-an-end-to-end-transformer-for","title":"DLAFormer: An End-to-End Transformer For Document Layout Analysis","date":"2024-05-20","arxiv_id":"2405.11757","repositories_listed":0,"syntology":null},{"url":null,"slug":"callico-a-versatile-open-source-document","title":"Callico: a Versatile Open-Source Document Image Annotation Platform","date":"2024-05-02","arxiv_id":"2405.01071","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-hybrid-approach-for-document-layout","title":"A Hybrid Approach for Document Layout Analysis in Document images","date":"2024-04-27","arxiv_id":"2404.17888","repositories_listed":0,"syntology":null},{"url":null,"slug":"autoie-an-automated-framework-for-information","title":"AutoIE: An Automated Framework for Information Extraction from Scientific Literature","date":"2024-01-30","arxiv_id":"2401.16672","repositories_listed":0,"syntology":null},{"url":"/paper/u-diads-bib-a-full-and-few-shot-pixel-precise","slug":"u-diads-bib-a-full-and-few-shot-pixel-precise","title":"U-DIADS-Bib: a full and few-shot pixel-precise dataset for document layout analysis of ancient manuscripts","date":"2024-01-16","arxiv_id":"2401.08425","repositories_listed":0,"syntology":null},{"url":null,"slug":"object-recognition-from-scientific-document","title":"Object Recognition from Scientific Document based on Compartment Refinement Framework","date":"2023-12-14","arxiv_id":"2312.09038","repositories_listed":0,"syntology":null},{"url":null,"slug":"bengali-document-layout-analysis-a-yolov8","title":"Bengali Document Layout Analysis -- A YOLOV8 Based Ensembling Approach","date":"2023-09-02","arxiv_id":"2309.00848","repositories_listed":0,"syntology":null},{"url":null,"slug":"document-layout-analysis-on-badlad-dataset-a","title":"Document Layout Analysis on BaDLAD Dataset: A Comprehensive MViTv2 Based Approach","date":"2023-08-31","arxiv_id":"2308.16571","repositories_listed":0,"syntology":null},{"url":null,"slug":"bengali-document-layout-analysis-with","title":"Bengali Document Layout Analysis with Detectron2","date":"2023-08-26","arxiv_id":"2308.13769","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-yolo-model-that-still-excels-in-document","title":"The YOLO model that still excels in document layout analysis","date":"2023-08-22","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"performance-enhancement-leveraging-mask-rcnn","title":"Performance Enhancement Leveraging Mask-RCNN on Bengali Document Layout Analysis","date":"2023-08-21","arxiv_id":"2308.10511","repositories_listed":0,"syntology":null},{"url":null,"slug":"framework-and-model-analysis-on-bengali","title":"Framework and Model Analysis on Bengali Document Layout Analysis Dataset: BaDLAD","date":"2023-08-15","arxiv_id":"2309.16700","repositories_listed":0,"syntology":null},{"url":"/paper/bridging-the-performance-gap-between-detr-and","slug":"bridging-the-performance-gap-between-detr-and","title":"Bridging the Performance Gap between DETR and R-CNN for Graphical Object Detection in Document Images","date":"2023-06-23","arxiv_id":"2306.13526","repositories_listed":0,"syntology":null},{"url":null,"slug":"m-6-doc-a-large-scale-multi-format-multi-type","title":"M$^{6}$Doc: A Large-Scale Multi-Format, Multi-Type, Multi-Layout, Multi-Language, Multi-Annotation Category Dataset for Modern Document Layout Analysis","date":"2023-05-15","arxiv_id":"2305.08719","repositories_listed":0,"syntology":null},{"url":null,"slug":"extracting-complex-named-entities-in-legal","title":"Extracting Complex Named Entities in Legal Documents via Weakly Supervised Object Detection","date":"2023-05-10","arxiv_id":"2305.05836","repositories_listed":0,"syntology":null},{"url":null,"slug":"detection-d-objets-dans-les-documents","title":"Détection d'Objets dans les documents numérisés par réseaux de neurones profonds","date":"2023-01-27","arxiv_id":"2301.11753","repositories_listed":0,"syntology":null},{"url":"/paper/efficient-few-shot-learning-for-pixel-precise","slug":"efficient-few-shot-learning-for-pixel-precise","title":"Efficient few-shot learning for pixel-precise handwritten document layout analysis","date":"2022-10-27","arxiv_id":"2210.15570","repositories_listed":0,"syntology":null},{"url":"/paper/transformer-based-approach-for-document","slug":"transformer-based-approach-for-document","title":"Transformer-based Approach for Document Understanding","date":"2022-10-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/unified-pretraining-framework-for-document","slug":"unified-pretraining-framework-for-document","title":"Unified Pretraining Framework for Document Understanding","date":"2022-04-22","arxiv_id":"2204.10939","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-graph-matching-for-modification","title":"Neural Graph Matching for Modification Similarity Applied to Electronic Document Comparison","date":"2022-04-12","arxiv_id":"2204.05486","repositories_listed":0,"syntology":null},{"url":null,"slug":"docbed-a-multi-stage-ocr-solution-for","title":"DocBed: A Multi-Stage OCR Solution for Documents with Complex Layouts","date":"2022-02-03","arxiv_id":"2202.01414","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-domain-document-layout-analysis-via","title":"Cross-Domain Document Layout Analysis Using Document Style Guide","date":"2022-01-24","arxiv_id":"2201.09407","repositories_listed":0,"syntology":null},{"url":null,"slug":"document-layout-analysis-with-aesthetic","title":"Document Layout Analysis with Aesthetic-Guided Image Augmentation","date":"2021-11-27","arxiv_id":"2111.13809","repositories_listed":0,"syntology":null},{"url":null,"slug":"document-ai-benchmarks-models-and","title":"Document AI: Benchmarks, Models and Applications","date":"2021-11-16","arxiv_id":"2111.08609","repositories_listed":0,"syntology":null},{"url":null,"slug":"document-image-layout-analysis-via-explicit","title":"Document Image Layout Analysis via Explicit Edge Embedding Network","date":"2021-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"vtlayout-fusion-of-visual-and-text-features","title":"VTLayout: Fusion of Visual and Text Features for Document Layout Analysis","date":"2021-08-12","arxiv_id":"2108.13297","repositories_listed":0,"syntology":null},{"url":null,"slug":"human-in-the-loop-document-layout-analysis","title":"Human-In-The-Loop Document Layout Analysis","date":"2021-08-04","arxiv_id":"2108.02095","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluation-of-a-region-proposal-architecture","title":"Evaluation of a Region Proposal Architecture for Multi-task Document Layout Analysis","date":"2021-06-22","arxiv_id":"2106.11797","repositories_listed":0,"syntology":null},{"url":null,"slug":"document-domain-randomization-for-deep","title":"Document Domain Randomization for Deep Learning Document Layout Extraction","date":"2021-05-20","arxiv_id":"2105.14931","repositories_listed":0,"syntology":null},{"url":null,"slug":"document-layout-analysis-via-dynamic-residual","title":"Document Layout Analysis via Dynamic Residual Feature Fusion","date":"2021-04-07","arxiv_id":"2104.02874","repositories_listed":0,"syntology":null},{"url":null,"slug":"bros-a-pre-trained-language-model-for","title":"BROS: A Pre-trained Language Model for Understanding Texts in Document","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"multiple-document-datasets-pre-training","title":"Multiple Document Datasets Pre-training Improves Text Line Detection With Deep Neural Networks","date":"2020-12-28","arxiv_id":"2012.14163","repositories_listed":0,"syntology":null},{"url":null,"slug":"vision-based-layout-detection-from-scientific","title":"Vision-Based Layout Detection from Scientific Literature using Recurrent Convolutional Neural Networks","date":"2020-10-18","arxiv_id":"2010.11727","repositories_listed":0,"syntology":null},{"url":"/paper/visualwordgrid-information-extraction-from-1","slug":"visualwordgrid-information-extraction-from-1","title":"VisualWordGrid: Information Extraction From Scanned Documents Using A Multimodal Approach","date":"2020-10-05","arxiv_id":"2010.02358","repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-detection-with-context-for-document","title":"Visual Detection with Context for Document Layout Analysis","date":"2019-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-document-clustering-by-removing","title":"Improving Document Clustering by Removing Unnatural Language","date":"2017-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/diva-hisdb-a-precisely-annotated-large","slug":"diva-hisdb-a-precisely-annotated-large","title":"DIVA-HisDB: A Precisely Annotated Large Dataset of Challenging Medieval Manuscripts","date":"2016-10-23","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"natural-language-inspired-approach-for","title":"Natural Language Inspired Approach for Handwritten Text Line Detection in Legacy Documents","date":"2012-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"parameter-free-geometric-document-layout","title":"Parameter-free Geometric Document Layout Analysis","date":"2001-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"syntology_records":7,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":7,"papers_where_code_ran_first_page":"/task/document-layout-analysis/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/task/document-layout-analysis/papers/ran/1","json":"/task/document-layout-analysis/papers/ran/1.json","rows":7}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"41616b4aff63dbc563bf019e1dc7b83178ed0aa35207e53f09c520f2cd778701","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}