{"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-image-classification","name":"Document Image Classification","slug":"document-image-classification","description_markdown":"Document image classification is the task of classifying documents based on images of their contents.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [Real-Time Document Image Classification using Deep CNN and Extreme Learning Machines](https://arxiv.org/pdf/1711.05862v1.pdf) )</span>","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":50,"papers_with_code":25,"benchmarks":8,"benchmark_tables_in_archive":8,"benchmark_tables_shown":8,"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":4,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/document-image-classification-on-rvl-cdip","slug":"document-image-classification-on-rvl-cdip","dataset":"RVL-CDIP","dataset_url":"/dataset/rvl-cdip","rows_in_archive":31,"metrics":["Accuracy","Parameters"],"first_row_in_archive_order":{"model":"EAML","paper_title":"EAML: Ensemble Self-Attention-based Mutual Learning Network for Document Image Classification","paper_url":"/paper/eaml-ensemble-self-attention-based-mutual","paper_date":"2023-05-11","arxiv_id":"2305.06923","code_links":[],"syntology":null}},{"leaderboard":"/sota/document-image-classification-on-tobacco-3482","slug":"document-image-classification-on-tobacco-3482","dataset":"Tobacco-3482","dataset_url":"/dataset/tobacco-3482","rows_in_archive":10,"metrics":["Accuracy","Memory"],"first_row_in_archive_order":{"model":"DocXClassifier-L","paper_title":"DocXClassifier: High Performance Explainable Deep Network for Document Image Classification","paper_url":"/paper/docxclassifier-high-performance-explainable","paper_date":"2022-03-17","arxiv_id":null,"code_links":[{"title":"saifullah3396/docxclassifier","url":"https://github.com/saifullah3396/docxclassifier"}],"syntology":null}},{"leaderboard":"/sota/document-image-classification-on-noisy-bangla","slug":"document-image-classification-on-noisy-bangla","dataset":"Noisy Bangla Numeral","dataset_url":null,"rows_in_archive":2,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"PCGAN-CHAR","paper_title":"PCGAN-CHAR: Progressively Trained Classifier Generative Adversarial Networks for Classification of Noisy Handwritten Bangla Characters","paper_url":"/paper/pcgan-char-progressively-trained-classifier","paper_date":"2019-08-11","arxiv_id":"1908.08987","code_links":[],"syntology":null}},{"leaderboard":"/sota/document-image-classification-on-noisy-bangla-1","slug":"document-image-classification-on-noisy-bangla-1","dataset":"Noisy Bangla Characters","dataset_url":null,"rows_in_archive":2,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"PCGAN-CHAR","paper_title":"PCGAN-CHAR: Progressively Trained Classifier Generative Adversarial Networks for Classification of Noisy Handwritten Bangla Characters","paper_url":"/paper/pcgan-char-progressively-trained-classifier","paper_date":"2019-08-11","arxiv_id":"1908.08987","code_links":[],"syntology":null}},{"leaderboard":"/sota/document-image-classification-on-aip","slug":"document-image-classification-on-aip","dataset":"AIP","dataset_url":null,"rows_in_archive":1,"metrics":["Top 1 Accuracy - Verb"],"first_row_in_archive_order":{"model":"ResNet-RS (ResNet-200 + RS training tricks)","paper_title":"Revisiting ResNets: Improved Training and Scaling Strategies","paper_url":"/paper/revisiting-resnets-improved-training-and","paper_date":"2021-03-13","arxiv_id":"2103.07579","code_links":[{"title":"rwightman/pytorch-image-models","url":"https://github.com/rwightman/pytorch-image-models"},{"title":"tensorflow/tpu","url":"https://github.com/tensorflow/tpu/tree/master/models/official/resnet/resnet_rs"},{"title":"nachiket273/pytorch_resnet_rs","url":"https://github.com/nachiket273/pytorch_resnet_rs"}],"syntology":null}},{"leaderboard":"/sota/document-image-classification-on-noisy-mnist","slug":"document-image-classification-on-noisy-mnist","dataset":"n-MNIST","dataset_url":"/dataset/n-mnist","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Pixel-level RC","paper_title":"Pixel-level Reconstruction and Classification for Noisy Handwritten Bangla Characters","paper_url":"/paper/pixel-level-reconstruction-and-classification","paper_date":"2018-06-21","arxiv_id":"1806.08037","code_links":[],"syntology":null}},{"leaderboard":"/sota/document-image-classification-on-noisy-mnist-1","slug":"document-image-classification-on-noisy-mnist-1","dataset":"Noisy MNIST","dataset_url":null,"rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"PCGAN-CHAR","paper_title":"PCGAN-CHAR: Progressively Trained Classifier Generative Adversarial Networks for Classification of Noisy Handwritten Bangla Characters","paper_url":"/paper/pcgan-char-progressively-trained-classifier","paper_date":"2019-08-11","arxiv_id":"1908.08987","code_links":[],"syntology":null}},{"leaderboard":"/sota/document-image-classification-on-sut","slug":"document-image-classification-on-sut","dataset":"SUT","dataset_url":"/dataset/sut","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"CNN","paper_title":"SUT: a new multi-purpose synthetic dataset for Farsi document image analysis","paper_url":"/paper/sut-a-new-multi-purpose-synthetic-dataset-for","paper_date":"2023-11-27","arxiv_id":null,"code_links":[{"title":"aliiafkari/SUT_Dataset","url":"https://github.com/aliiafkari/SUT_Dataset"}],"syntology":null}}],"datasets":[{"url":"/dataset/rvl-cdip","name":"RVL-CDIP","full_name":"RVL-CDIP","num_papers_in_archive":107},{"url":"/dataset/tobacco-3482","name":"Tobacco-3482","full_name":"","num_papers_in_archive":5},{"url":"/dataset/s-ved","name":"S-VED","full_name":"Sacrobosco Visual Element Dataset","num_papers_in_archive":3},{"url":"/dataset/sut","name":"SUT","full_name":"SUT: a new multi-purpose synthetic dataset for Farsi document image analysis","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/image-classification","name":"Image Classification"}],"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":50,"of":50,"of_with_code":25,"tagged_in_all":50,"counts":{"archive_papers_tagged":50,"with_a_code_link":25,"where_syntology_ran_a_sample":10,"not_listed_spam_title":0,"listed":50,"listed_where_code_ran":10,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":8,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":8,"listed_every_run_a_failure_of_syntologys_instrument":2,"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/roberta-a-robustly-optimized-bert-pretraining","slug":"roberta-a-robustly-optimized-bert-pretraining","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","date":"2019-07-26","arxiv_id":"1907.11692","repositories_listed":67,"syntology":{"n":48,"n_ran":37,"n_constructed":11,"n_ran_checked":36,"n_instrument":1,"n_unverified":11,"n_honours":2,"n_violates":0,"n_no_contract":34,"n_pointer_only":24,"phrase":"37 ran (of which 11 constructed an object rather than computing a result; 36 with no instrument failure: 2 honoured, 0 violated, 34 with no contract checked; 1 where Syntology's instrument failed) · 11 unverified","sample_list":"/paper/roberta-a-robustly-optimized-bert-pretraining#ran","syntology_url":"https://syntology.ai/paper/1907.11692","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.11692"}},"official":{"repos":["pytorch/fairseq"],"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/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/layoutxlm-multimodal-pre-training-for","slug":"layoutxlm-multimodal-pre-training-for","title":"LayoutXLM: Multimodal Pre-training for Multilingual Visually-rich Document Understanding","date":"2021-04-18","arxiv_id":"2104.08836","repositories_listed":6,"syntology":null},{"url":"/paper/lilt-a-simple-yet-effective-language","slug":"lilt-a-simple-yet-effective-language","title":"LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding","date":"2022-02-28","arxiv_id":"2202.13669","repositories_listed":5,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/lilt-a-simple-yet-effective-language#ran","syntology_url":"https://syntology.ai/paper/2202.13669","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.13669"}},"official":{"repos":["jpwang/lilt"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/donut-document-understanding-transformer","slug":"donut-document-understanding-transformer","title":"OCR-free Document Understanding Transformer","date":"2021-11-30","arxiv_id":"2111.15664","repositories_listed":5,"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/donut-document-understanding-transformer#ran","syntology_url":"https://syntology.ai/paper/2111.15664","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.15664"}},"official":{"repos":["clovaai/donut"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/cutting-the-error-by-half-investigation-of","slug":"cutting-the-error-by-half-investigation-of","title":"Cutting the Error by Half: Investigation of Very Deep CNN and Advanced Training Strategies for Document Image Classification","date":"2017-04-11","arxiv_id":"1704.03557","repositories_listed":5,"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/document-image-classification-with-intra","slug":"document-image-classification-with-intra","title":"Document Image Classification with Intra-Domain Transfer Learning and Stacked Generalization of Deep Convolutional Neural Networks","date":"2018-01-29","arxiv_id":"1801.09321","repositories_listed":4,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/document-image-classification-with-intra#ran","syntology_url":"https://syntology.ai/paper/1801.09321","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1801.09321"}},"official":null}},{"url":"/paper/revisiting-resnets-improved-training-and","slug":"revisiting-resnets-improved-training-and","title":"Revisiting ResNets: Improved Training and Scaling Strategies","date":"2021-03-13","arxiv_id":"2103.07579","repositories_listed":3,"syntology":null},{"url":"/paper/automatic-recognition-of-learning-resource","slug":"automatic-recognition-of-learning-resource","title":"Automatic Recognition of Learning Resource Category in a Digital Library","date":"2023-11-28","arxiv_id":"2401.12220","repositories_listed":2,"syntology":null},{"url":"/paper/ernie-layout-layout-knowledge-enhanced-pre","slug":"ernie-layout-layout-knowledge-enhanced-pre","title":"ERNIE-Layout: Layout Knowledge Enhanced Pre-training for Visually-rich Document Understanding","date":"2022-10-12","arxiv_id":"2210.06155","repositories_listed":2,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":5,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ernie-layout-layout-knowledge-enhanced-pre#ran","syntology_url":"https://syntology.ai/paper/2210.06155","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.06155"}},"official":{"repos":["PaddlePaddle/PaddleNLP"],"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/multimodal-adaptive-inference-for-document","slug":"multimodal-adaptive-inference-for-document","title":"Multimodal Adaptive Inference for Document Image Classification with Anytime Early Exiting","date":"2024-05-21","arxiv_id":"2405.12705","repositories_listed":1,"syntology":null},{"url":"/paper/sut-a-new-multi-purpose-synthetic-dataset-for","slug":"sut-a-new-multi-purpose-synthetic-dataset-for","title":"SUT: a new multi-purpose synthetic dataset for Farsi document image analysis","date":"2023-11-27","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/structextv2-masked-visual-textual-prediction","slug":"structextv2-masked-visual-textual-prediction","title":"StrucTexTv2: Masked Visual-Textual Prediction for Document Image Pre-training","date":"2023-03-01","arxiv_id":"2303.00289","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-side-tuning-for-document","slug":"multimodal-side-tuning-for-document","title":"Multimodal Side-Tuning for Document Classification","date":"2023-01-16","arxiv_id":"2301.07502","repositories_listed":1,"syntology":null},{"url":"/paper/docxclassifier-high-performance-explainable","slug":"docxclassifier-high-performance-explainable","title":"DocXClassifier: High Performance Explainable Deep Network for Document Image Classification","date":"2022-03-17","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/docformer-end-to-end-transformer-for-document","slug":"docformer-end-to-end-transformer-for-document","title":"DocFormer: End-to-End Transformer for Document Understanding","date":"2021-06-22","arxiv_id":"2106.11539","repositories_listed":1,"syntology":{"n":10,"n_ran":5,"n_constructed":5,"n_ran_checked":5,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified; every one of the 5 samples that ran constructed an object rather than computing a result","sample_list":"/paper/docformer-end-to-end-transformer-for-document#ran","syntology_url":"https://syntology.ai/paper/2106.11539","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.11539"}},"official":null}},{"url":"/paper/structurallm-structural-pre-training-for-form","slug":"structurallm-structural-pre-training-for-form","title":"StructuralLM: Structural Pre-training for Form Understanding","date":"2021-05-24","arxiv_id":"2105.11210","repositories_listed":1,"syntology":{"n":5,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 5 unverified","sample_list":"/paper/structurallm-structural-pre-training-for-form#ran","syntology_url":"https://syntology.ai/paper/2105.11210","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.11210"}},"official":{"repos":["alibaba/AliceMind"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":5,"ran_from_kinds":[]}}},{"url":"/paper/going-full-tilt-boogie-on-document","slug":"going-full-tilt-boogie-on-document","title":"Going Full-TILT Boogie on Document Understanding with Text-Image-Layout Transformer","date":"2021-02-18","arxiv_id":"2102.09550","repositories_listed":1,"syntology":null},{"url":"/paper/improving-accuracy-and-speeding-up-document","slug":"improving-accuracy-and-speeding-up-document","title":"Improving accuracy and speeding up Document Image Classification through parallel systems","date":"2020-06-16","arxiv_id":"2006.09141","repositories_listed":1,"syntology":null},{"url":"/paper/light-weighted-cnn-for-text-classification","slug":"light-weighted-cnn-for-text-classification","title":"Light-Weighted CNN for Text Classification","date":"2020-04-16","arxiv_id":"2004.07922","repositories_listed":1,"syntology":null},{"url":null,"slug":"zero-shot-prompting-and-few-shot-fine-tuning","title":"Zero-Shot Prompting and Few-Shot Fine-Tuning: Revisiting Document Image Classification Using Large Language Models","date":"2024-12-18","arxiv_id":"2412.13859","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":null,"slug":"docxplain-a-novel-model-agnostic","title":"DocXplain: A Novel Model-Agnostic Explainability Method for Document Image Classification","date":"2024-07-04","arxiv_id":"2407.03830","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":"cica-content-injected-contrastive-alignment","title":"CICA: Content-Injected Contrastive Alignment for Zero-Shot Document Image Classification","date":"2024-05-06","arxiv_id":"2405.03660","repositories_listed":0,"syntology":null},{"url":null,"slug":"layoutllm-large-language-model-instruction","title":"LayoutLLM: Large Language Model Instruction Tuning for Visually Rich Document Understanding","date":"2024-03-21","arxiv_id":"2403.14252","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-multi-modal-multilingual-benchmark-for","title":"A Multi-Modal Multilingual Benchmark for Document Image Classification","date":"2023-10-25","arxiv_id":"2310.16356","repositories_listed":0,"syntology":null},{"url":"/paper/transferdoc-a-self-supervised-transferable","slug":"transferdoc-a-self-supervised-transferable","title":"GlobalDoc: A Cross-Modal Vision-Language Framework for Real-World Document Image Retrieval and Classification","date":"2023-09-11","arxiv_id":"2309.05756","repositories_listed":0,"syntology":null},{"url":"/paper/layoutmask-enhance-text-layout-interaction-in","slug":"layoutmask-enhance-text-layout-interaction-in","title":"LayoutMask: Enhance Text-Layout Interaction in Multi-modal Pre-training for Document Understanding","date":"2023-05-30","arxiv_id":"2305.18721","repositories_listed":0,"syntology":null},{"url":"/paper/eaml-ensemble-self-attention-based-mutual","slug":"eaml-ensemble-self-attention-based-mutual","title":"EAML: Ensemble Self-Attention-based Mutual Learning Network for Document Image Classification","date":"2023-05-11","arxiv_id":"2305.06923","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-adversarial-robustness-on-document","title":"Evaluating Adversarial Robustness on Document Image Classification","date":"2023-04-24","arxiv_id":"2304.12486","repositories_listed":0,"syntology":null},{"url":null,"slug":"context-aware-classification-of-legal","title":"Context-Aware Classification of Legal Document Pages","date":"2023-04-05","arxiv_id":"2304.02787","repositories_listed":0,"syntology":null},{"url":"/paper/vlcdoc-vision-language-contrastive-pre","slug":"vlcdoc-vision-language-contrastive-pre","title":"VLCDoC: Vision-Language Contrastive Pre-Training Model for Cross-Modal Document Classification","date":"2022-05-24","arxiv_id":"2205.12029","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":"domain-agnostic-few-shot-learning-for","title":"Domain Agnostic Few-Shot Learning For Document Intelligence","date":"2021-10-29","arxiv_id":"2111.00007","repositories_listed":0,"syntology":null},{"url":"/paper/efficient-document-image-classification-using","slug":"efficient-document-image-classification-using","title":"Efficient Document Image Classification Using Region-Based Graph Neural Network","date":"2021-06-25","arxiv_id":"2106.13802","repositories_listed":0,"syntology":null},{"url":"/paper/toward-automatic-interpretation-of-3d-plots","slug":"toward-automatic-interpretation-of-3d-plots","title":"Toward Automatic Interpretation of 3D Plots","date":"2021-06-14","arxiv_id":"2106.07627","repositories_listed":0,"syntology":null},{"url":"/paper/visual-and-textual-deep-feature-fusion-for","slug":"visual-and-textual-deep-feature-fusion-for","title":"Visual and Textual Deep Feature Fusion for Document Image Classification","date":"2020-06-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-representation-learning-on","title":"Self-Supervised Representation Learning on Document Images","date":"2020-04-18","arxiv_id":"2004.10605","repositories_listed":0,"syntology":null},{"url":"/paper/pcgan-char-progressively-trained-classifier","slug":"pcgan-char-progressively-trained-classifier","title":"PCGAN-CHAR: Progressively Trained Classifier Generative Adversarial Networks for Classification of Noisy Handwritten Bangla Characters","date":"2019-08-11","arxiv_id":"1908.08987","repositories_listed":0,"syntology":null},{"url":"/paper/pixel-level-reconstruction-and-classification","slug":"pixel-level-reconstruction-and-classification","title":"Pixel-level Reconstruction and Classification for Noisy Handwritten Bangla Characters","date":"2018-06-21","arxiv_id":"1806.08037","repositories_listed":0,"syntology":null},{"url":null,"slug":"real-time-document-image-classification-using","title":"Real-Time Document Image Classification using Deep CNN and Extreme Learning Machines","date":"2017-11-03","arxiv_id":"1711.05862","repositories_listed":0,"syntology":null},{"url":"/paper/analysis-of-convolutional-neural-networks-for","slug":"analysis-of-convolutional-neural-networks-for","title":"Analysis of Convolutional Neural Networks for Document Image Classification","date":"2017-08-10","arxiv_id":"1708.03273","repositories_listed":0,"syntology":null},{"url":null,"slug":"document-image-classification-with-a-specific","title":"Document image classification, with a specific view on applications of patent images","date":"2016-01-13","arxiv_id":"1601.03295","repositories_listed":0,"syntology":null},{"url":"/paper/evaluation-of-deep-convolutional-nets-for","slug":"evaluation-of-deep-convolutional-nets-for","title":"Evaluation of Deep Convolutional Nets for Document Image Classification and Retrieval","date":"2015-02-25","arxiv_id":"1502.07058","repositories_listed":0,"syntology":null}],"syntology_records":11,"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":10,"papers_where_code_ran_first_page":"/task/document-image-classification/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-image-classification/papers/ran/1","json":"/task/document-image-classification/papers/ran/1.json","rows":10}],"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":"ca716815c316191b3c760d5c70aa9a41474f7e9c92d12c14dabe9819b53c2319","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}