{"id":"https://openalex.org/W4403791624","doi":"https://doi.org/10.1145/3664647.3681390","title":"Decoder Pre-Training with only Text for Scene Text Recognition","display_name":"Decoder Pre-Training with only Text for Scene Text Recognition","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791624","doi":"https://doi.org/10.1145/3664647.3681390"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681390","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681390","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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":null,"display_name":"Shuai Zhao","orcid":"https://orcid.org/0009-0007-3387-2293"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Zhao","raw_affiliation_strings":["School of Computer Science, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0007-3387-2293","affiliations":[{"raw_affiliation_string":"School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102915298","display_name":"Yongkun Du","orcid":"https://orcid.org/0009-0005-3114-2188"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongkun Du","raw_affiliation_strings":["School of Computer Science, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0005-3114-2188","affiliations":[{"raw_affiliation_string":"School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080463909","display_name":"Zhineng Chen","orcid":"https://orcid.org/0000-0003-1543-6889"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhineng Chen","raw_affiliation_strings":["School of Computer Science, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-1543-6889","affiliations":[{"raw_affiliation_string":"School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047962986","display_name":"Yu\u2013Gang Jiang","orcid":"https://orcid.org/0000-0002-1907-8567"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu-Gang Jiang","raw_affiliation_strings":["School of Computer Science, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-1907-8567","affiliations":[{"raw_affiliation_string":"School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5191","last_page":"5200"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9835000038146973,"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"}},{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9824000000953674,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7734076380729675},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6821925640106201},{"id":"https://openalex.org/keywords/text-recognition","display_name":"Text recognition","score":0.6048345565795898},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5754379630088806},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.556525707244873},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5456840991973877},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3300524950027466},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32302796840667725},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.17784461379051208}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7734076380729675},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6821925640106201},{"id":"https://openalex.org/C2983812711","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text recognition","level":3,"score":0.6048345565795898},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5754379630088806},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.556525707244873},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5456840991973877},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3300524950027466},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32302796840667725},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.17784461379051208},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681390","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681390","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1922126009","https://openalex.org/W1971822075","https://openalex.org/W1981283549","https://openalex.org/W1998042868","https://openalex.org/W2127141656","https://openalex.org/W2146835493","https://openalex.org/W2194187530","https://openalex.org/W2194775991","https://openalex.org/W2294053032","https://openalex.org/W2343052201","https://openalex.org/W2810983211","https://openalex.org/W2964065044","https://openalex.org/W2965066169","https://openalex.org/W2978036638","https://openalex.org/W3003868038","https://openalex.org/W3035449864","https://openalex.org/W3175855397","https://openalex.org/W3177505580","https://openalex.org/W3177684257","https://openalex.org/W3181186176","https://openalex.org/W3204479434","https://openalex.org/W3206651063","https://openalex.org/W4226329156","https://openalex.org/W4283821822","https://openalex.org/W4292825881","https://openalex.org/W4308021352","https://openalex.org/W4312879041","https://openalex.org/W4313156423","https://openalex.org/W4384918183","https://openalex.org/W4386065575","https://openalex.org/W4386185423","https://openalex.org/W4386410320","https://openalex.org/W4390873548","https://openalex.org/W4402772614","https://openalex.org/W4402774225"],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W3216976533","https://openalex.org/W100620283","https://openalex.org/W2495260952","https://openalex.org/W4366179611","https://openalex.org/W2996078371"],"abstract_inverted_index":{"Scene":[0],"text":[1,63,80,96,102,108,134,181],"recognition":[2,202],"(STR)":[3],"pre-training":[4],"methods":[5],"have":[6],"achieved":[7],"remarkable":[8,209],"progress,":[9],"primarily":[10],"relying":[11],"on":[12,36,54,175],"synthetic":[13,20],"datasets.":[14],"However,":[15],"the":[16,41,70,74,106,119,131,143,149,153,170,176,180,185,205],"domain":[17],"gap":[18],"between":[19],"and":[21,62,114,192,200,208],"real":[22,37,56,77,157],"images":[23,35,61,78],"poses":[24],"a":[25,65,88,163,214],"challenge":[26],"in":[27,64],"acquiring":[28],"feature":[29],"representations":[30,75,155],"that":[31,48,168],"align":[32,60],"well":[33],"with":[34,94],"scenes,":[38],"thereby":[39,183],"limiting":[40],"performance":[42,210],"of":[43,76,133,156,211],"these":[44],"methods.":[45],"We":[46],"note":[47],"vision-language":[49],"models":[50],"like":[51],"CLIP,":[52],"pre-trained":[53,186],"extensive":[55],"image-text":[57],"pairs,":[58],"effectively":[59,147],"unified":[66],"embedding":[67],"space,":[68],"suggesting":[69],"potential":[71,154],"to":[72,117,151,188],"derive":[73],"from":[79,142],"alone.":[81],"Building":[82],"upon":[83],"this":[84],"premise,":[85],"we":[86,161],"introduce":[87,162],"novel":[89,215],"method":[90],"named":[91],"Decoder":[92],"Pre-training":[93],"only":[95],"for":[97,217],"STR":[98,198,218],"(DPTR).":[99],"DPTR":[100],"treats":[101],"embeddings":[103,113,135,140,173],"produced":[104],"by":[105,136],"CLIP":[107,144],"encoder":[109],"as":[110],"pseudo":[111],"visual":[112,172],"uses":[115],"them":[116],"pre-train":[118],"decoder.":[120],"An":[121],"Offline":[122],"Randomized":[123],"Perturbation":[124],"(ORP)":[125],"strategy":[126],"is":[127,221],"introduced.":[128],"It":[129],"enriches":[130],"diversity":[132],"incorporating":[137],"natural":[138],"image":[139,145],"extracted":[141,171],"encoder,":[146],"directing":[148],"decoder":[150,187],"acquire":[152],"images.":[158],"In":[159],"addition,":[160],"Feature":[164],"Merge":[165],"Unit":[166],"(FMU)":[167],"guides":[169],"focusing":[174],"character":[177],"foreground":[178],"within":[179],"image,":[182],"enabling":[184],"work":[189],"more":[190],"efficiently":[191],"accurately.":[193],"Extensive":[194],"experiments":[195],"across":[196],"various":[197],"decoders":[199],"language":[201],"tasks":[203],"underscore":[204],"broad":[206],"applicability":[207],"DPTR,":[212],"providing":[213],"insight":[216],"pre-training.":[219],"Code":[220],"available":[222],"at":[223],"https://github.com/Topdu/OpenOCR.":[224]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}