{"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":"/method/trocr","slug":"trocr","name":"TrOCR","full_name":"TrOCR","full_name_withheld":false,"description_markdown":"**TrOCR** is an end-to-end [Transformer](https://paperswithcode.com/methods/category/transformers)-based OCR model for text recognition with pre-trained CV and NLP models. It leverages the [Transformer](https://paperswithcode.com/method/transformer) architecture for both image understanding and wordpiece-level text generation. It first resizes the input text image into $384 × 384$ and then the image is split into a sequence of 16 patches which are used as the input to image Transformers.  Standard Transformer architecture with the [self-attention mechanism](https://paperswithcode.com/method/scaled) is leveraged on both encoder and decoder parts, where wordpiece units are generated as the recognized text from the input image.","description_state":"present","introduced_year":null,"introduced_by":{"title":"TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models","paper":"/paper/trocr-transformer-based-optical-character","first_author":"Minghao Li","n_authors":9,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/trocr-transformer-based-optical-character"},"source":{"url":"https://arxiv.org/abs/2109.10282v5","title":"TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"OCR Models","url":"/methods/category/ocr-models","pwc_aliases":[]}],"n_papers_tagged":11,"archive_num_papers":11,"papers_newest_first":[{"paper":null,"slug":"tridis-a-comprehensive-medieval-and-early","title":"TRIDIS: A Comprehensive Medieval and Early Modern Corpus for HTR and NER","date":"2025-03-25","arxiv_id":"2503.22714","n_code_links":0,"syntology":null},{"paper":"/paper/early-evidence-of-how-llms-outperform","slug":"early-evidence-of-how-llms-outperform","title":"Early evidence of how LLMs outperform traditional systems on OCR/HTR tasks for historical records","date":"2025-01-20","arxiv_id":"2501.11623","n_code_links":1,"syntology":null},{"paper":"/paper/comparative-analysis-of-optical-character","slug":"comparative-analysis-of-optical-character","title":"Comparative analysis of optical character recognition methods for Sámi texts from the National Library of Norway","date":"2025-01-13","arxiv_id":"2501.07300","n_code_links":2,"syntology":null},{"paper":null,"slug":"leveraging-deep-learning-with-multi-head","title":"Leveraging Deep Learning with Multi-Head Attention for Accurate Extraction of Medicine from Handwritten Prescriptions","date":"2024-12-24","arxiv_id":"2412.18199","n_code_links":0,"syntology":null},{"paper":"/paper/spanish-trocr-leveraging-transfer-learning","slug":"spanish-trocr-leveraging-transfer-learning","title":"Spanish TrOCR: Leveraging Transfer Learning for Language Adaptation","date":"2024-07-09","arxiv_id":"2407.06950","n_code_links":1,"syntology":null},{"paper":null,"slug":"ospc-detecting-harmful-memes-with-large","title":"OSPC: Detecting Harmful Memes with Large Language Model as a Catalyst","date":"2024-06-14","arxiv_id":"2406.09779","n_code_links":0,"syntology":null},{"paper":"/paper/automatic-transcription-of-handwritten-old","slug":"automatic-transcription-of-handwritten-old","title":"Automatic Transcription of Handwritten Old Occitan Language","date":"2023-12-06","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"vulnerability-analysis-of-transformer-based","title":"Vulnerability Analysis of Transformer-based Optical Character Recognition to Adversarial Attacks","date":"2023-11-28","arxiv_id":"2311.17128","n_code_links":0,"syntology":null},{"paper":null,"slug":"extending-trocr-for-text-localization-free","title":"Extending TrOCR for Text Localization-Free OCR of Full-Page Scanned Receipt Images","date":"2022-12-11","arxiv_id":"2212.05525","n_code_links":0,"syntology":null},{"paper":"/paper/transformer-based-htr-for-historical","slug":"transformer-based-htr-for-historical","title":"Transformer-based HTR for Historical Documents","date":"2022-03-21","arxiv_id":"2203.11008","n_code_links":1,"syntology":null},{"paper":"/paper/trocr-transformer-based-optical-character","slug":"trocr-transformer-based-optical-character","title":"TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models","date":"2021-09-21","arxiv_id":"2109.10282","n_code_links":8,"syntology":{"ran":5,"of":6,"n_ran_checked":5,"n_instrument":0,"unverified":1,"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) · 1 unverified","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"]}}}],"papers_shown":11,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":11,"with_a_code_link":6,"where_syntology_ran_a_sample":1,"not_listed_spam_title":0,"listed":11,"listed_where_code_ran":1,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":1,"listed_every_run_a_failure_of_syntologys_instrument":0,"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"},"papers_where_code_ran":1,"papers_where_code_ran_first_page":"/method/trocr/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[{"order":"ran","page":1,"of":1,"url":"/method/trocr/papers/ran/1","json":"/method/trocr/papers/ran/1.json","rows":1}],"tasks":[{"task":"/task/optical-character-recognition","name":"Optical Character Recognition","papers":7},{"task":"/task/optical-character-recognition","name":"Optical Character Recognition (OCR)","papers":7},{"task":"/task/htr","name":"HTR","papers":4},{"task":"/task/handwritten-text-recognition","name":"Handwritten Text Recognition","papers":3},{"task":"/task/decoder","name":"Decoder","papers":2},{"task":"/task/language-modeling","name":"Language Modeling","papers":2},{"task":"/task/language-modelling","name":"Language Modelling","papers":2},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":2},{"task":"/task/adversarial-attack","name":"Adversarial Attack","papers":1},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":1},{"task":"/task/image-captioning","name":"Image Captioning","papers":1},{"task":"/task/image-generation","name":"Image Generation","papers":1},{"task":"/task/large-language-model","name":"Large Language Model","papers":1},{"task":"/task/cg","name":"NER","papers":1},{"task":"/task/named-entity-recognition-1","name":"Named Entity Recognition","papers":1},{"task":"/task/named-entity-recognition-ner","name":"Named Entity Recognition (NER)","papers":1},{"task":"/task/outlier-detection","name":"Outlier Detection","papers":1},{"task":"/task/scene-text-recognition","name":"Scene Text Recognition","papers":1},{"task":"/task/text-generation","name":"Text Generation","papers":1},{"task":"/task/named-entity-recognition","name":"named-entity-recognition","papers":1}],"tasks_shown":20,"n_tasks":20,"usage_by_year":[{"year":"2021","papers":1},{"year":"2022","papers":2},{"year":"2023","papers":2},{"year":"2024","papers":3},{"year":"2025","papers":3}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/trocr"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=TrOCR","read_at":"2026-10-05T01:03:13+00:00","query":"TrOCR","kind":"paper","have":"unknown_name","tier":null,"verified_implementation":null,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":null,"resolution":null,"resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":null,"archive_paper_arxiv_id":"2109.10282","repositories":null,"retrieve_with":null,"name_competition":{"verdict":"unresolved_bearers","may_be_wrong_sense":true,"bearers_found":2,"served":null,"leading_other_bearer":{"arxiv_id":"2109.10282","title":"TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models","citations":742,"named_by":["title_prefix"],"bearer_name":"TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models","ask_with":"have('2109.10282')"},"n_other_bearers_listed":2,"note":"Nothing resolved to 'TrOCR' by name, but 2 thing(s) here DECLARE that name -- most cited: the paper 'TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models' (arXiv:2109.10282, 742 citations). That is a RESOLUTION miss, not a coverage gap: the corpus holds the name under a spelling the lookup did not reach. Ask again with an entry of `also_named`."},"name_competition_text":"Nothing resolved to this name, but 2 entries in Syntology's graph carry it; the most cited is the paper “TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models” (arXiv:2109.10282, 742 citations). The lookup reads this as a miss of its own name matching, not a gap in coverage: the graph holds the name under a spelling the lookup did not reach.","near_matches":[],"code_nearby":[],"code_nearby_caption":null,"origin_paper":null,"line":"name not resolved (unknown_name). Other entries in Syntology's graph carry this name; the lookup's note below says what that means for this name.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"be5040a8078d98df442d1a8d0f58099eac559133b4cf12c76cea06f30c3d3abc","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}