{"id":"https://openalex.org/W4385595326","doi":"https://doi.org/10.1145/3573128.3604897","title":"Multi-Task CTC for Joint Handwriting Recognition and Character Bounding Box Prediction","display_name":"Multi-Task CTC for Joint Handwriting Recognition and Character Bounding Box Prediction","publication_year":2023,"publication_date":"2023-08-04","ids":{"openalex":"https://openalex.org/W4385595326","doi":"https://doi.org/10.1145/3573128.3604897"},"language":"en","primary_location":{"id":"doi:10.1145/3573128.3604897","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1145/3573128.3604897","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Symposium on Document Engineering 2023","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060359867","display_name":"Curtis Wigington","orcid":"https://orcid.org/0009-0002-2051-0043"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Curtis Wigington","raw_affiliation_strings":["Adobe Research"],"raw_orcid":"https://orcid.org/0009-0002-2051-0043","affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5060359867"],"corresponding_institution_ids":["https://openalex.org/I1306409833"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"2","issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9962000250816345,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/unicode","display_name":"Unicode","score":0.8468579649925232},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8039905428886414},{"id":"https://openalex.org/keywords/handwriting-recognition","display_name":"Handwriting recognition","score":0.6637170314788818},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6387534141540527},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.587792694568634},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5785349011421204},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5581456422805786},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5238502025604248},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.5081169605255127},{"id":"https://openalex.org/keywords/intelligent-character-recognition","display_name":"Intelligent character recognition","score":0.49396783113479614},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4868618845939636},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.47677329182624817},{"id":"https://openalex.org/keywords/handwriting","display_name":"Handwriting","score":0.4625617265701294},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.45939087867736816},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4430699348449707},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.4361972510814667},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4252208471298218},{"id":"https://openalex.org/keywords/line","display_name":"Line (geometry)","score":0.41264110803604126},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.21981078386306763},{"id":"https://openalex.org/keywords/character-recognition","display_name":"Character recognition","score":0.21300795674324036}],"concepts":[{"id":"https://openalex.org/C500551929","wikidata":"https://www.wikidata.org/wiki/Q8819","display_name":"Unicode","level":2,"score":0.8468579649925232},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8039905428886414},{"id":"https://openalex.org/C112640561","wikidata":"https://www.wikidata.org/wiki/Q2440634","display_name":"Handwriting recognition","level":3,"score":0.6637170314788818},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6387534141540527},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.587792694568634},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5785349011421204},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5581456422805786},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5238502025604248},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.5081169605255127},{"id":"https://openalex.org/C44868376","wikidata":"https://www.wikidata.org/wiki/Q3099089","display_name":"Intelligent character recognition","level":4,"score":0.49396783113479614},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4868618845939636},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.47677329182624817},{"id":"https://openalex.org/C2779386606","wikidata":"https://www.wikidata.org/wiki/Q2393642","display_name":"Handwriting","level":2,"score":0.4625617265701294},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.45939087867736816},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4430699348449707},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.4361972510814667},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4252208471298218},{"id":"https://openalex.org/C198352243","wikidata":"https://www.wikidata.org/wiki/Q37105","display_name":"Line (geometry)","level":2,"score":0.41264110803604126},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.21981078386306763},{"id":"https://openalex.org/C2987247673","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Character recognition","level":3,"score":0.21300795674324036},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3573128.3604897","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1145/3573128.3604897","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Symposium on Document Engineering 2023","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6899999976158142,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2127141656","https://openalex.org/W2133059825","https://openalex.org/W2143786659","https://openalex.org/W2147933024","https://openalex.org/W2152928267","https://openalex.org/W2156338447","https://openalex.org/W2786429113","https://openalex.org/W2895359355","https://openalex.org/W2913059114","https://openalex.org/W2963271566","https://openalex.org/W3004388780","https://openalex.org/W3196547859"],"related_works":["https://openalex.org/W2544230285","https://openalex.org/W3217266680","https://openalex.org/W2218402054","https://openalex.org/W4384296853","https://openalex.org/W4386428871","https://openalex.org/W4220954837","https://openalex.org/W4327773476","https://openalex.org/W2011042697","https://openalex.org/W2135329887","https://openalex.org/W4366502683"],"abstract_inverted_index":{"Deep":[0],"learning":[1],"based":[2],"models":[3],"continue":[4],"to":[5],"push":[6],"the":[7,24,31,40,45,55,81,89],"frontier":[8],"of":[9,19,26,44,66],"OCR":[10],"and":[11,22,47,78,123,130],"Handwritten":[12],"Text":[13],"Recognition":[14],"(HTR)":[15],"both":[16],"in":[17],"terms":[18],"increasing":[20],"accuracy":[21,77],"minimizing":[23],"burden":[25],"data":[27,82],"annotation.":[28],"For":[29],"example,":[30],"CTC":[32],"loss":[33],"[3]":[34],"allows":[35],"for":[36],"line-level":[37,69],"training":[38,59],"without":[39,68],"explicit":[41,101],"spatial":[42],"positions":[43],"characters":[46],"words.":[48],"Other":[49],"recent":[50],"works":[51],"have":[52,74,93,99],"further":[53],"reduced":[54,80],"annotation":[56],"effort":[57],"by":[58],"systems":[60,98],"on":[61],"entire":[62],"paragraphs":[63],"or":[64,109],"pages":[65],"text":[67],"annotations.":[70],"While":[71],"these":[72,97],"techniques":[73],"greatly":[75],"increased":[76],"significantly":[79],"collection":[83],"burden,":[84],"useful":[85],"outputs":[86],"beyond":[87],"just":[88],"Unicode":[90],"character":[91],"prediction":[92],"been":[94],"lost.":[95],"Because":[96],"fewer":[100],"segmentation":[102],"steps,":[103],"they":[104],"do":[105],"not":[106,128],"produce":[107],"character-level":[108],"word-level":[110],"bounding":[111],"boxes.":[112],"As":[113],"a":[114],"result,":[115],"downstream":[116],"applications":[117],"such":[118],"as":[119],"highlighting,":[120],"redaction":[121],"tools,":[122],"basic":[124],"document":[125],"correction,":[126],"are":[127],"provided":[129],"must":[131],"be":[132],"obtained":[133],"with":[134],"other":[135],"methods.":[136]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}