{"id":"https://openalex.org/W4387968066","doi":"https://doi.org/10.1145/3581783.3611755","title":"Scene Text Segmentation with Text-Focused Transformers","display_name":"Scene Text Segmentation with Text-Focused Transformers","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387968066","doi":"https://doi.org/10.1145/3581783.3611755"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3611755","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611755","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","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/A5080937507","display_name":"Haiyang Yu","orcid":"https://orcid.org/0000-0002-1717-0474"},"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":true,"raw_author_name":"Haiyang Yu","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-1717-0474","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069751835","display_name":"Xiaocong Wang","orcid":"https://orcid.org/0000-0002-3735-721X"},"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":"Xiaocong Wang","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-3735-721X","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055721838","display_name":"Ke Niu","orcid":"https://orcid.org/0009-0005-0181-924X"},"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":"Ke Niu","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0005-0181-924X","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100365239","display_name":"Bin Li","orcid":"https://orcid.org/0000-0002-9633-0033"},"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":"Bin Li","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-9633-0033","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003418019","display_name":"Xiangyang Xue","orcid":"https://orcid.org/0000-0002-4897-9209"},"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":"Xiangyang Xue","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-4897-9209","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5080937507"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":0.942,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.77657853,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2898","last_page":"2907"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9926000237464905,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9817000031471252,"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":0.805485188961029},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7871098518371582},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.6840729713439941},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5795646905899048},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5749821662902832},{"id":"https://openalex.org/keywords/text-detection","display_name":"Text detection","score":0.5574926733970642},{"id":"https://openalex.org/keywords/noisy-text-analytics","display_name":"Noisy text analytics","score":0.5166252255439758},{"id":"https://openalex.org/keywords/document-layout-analysis","display_name":"Document layout analysis","score":0.46748799085617065},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43510720133781433},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.41832998394966125},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34325748682022095},{"id":"https://openalex.org/keywords/text-graph","display_name":"Text graph","score":0.32796207070350647},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3213932514190674},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.26857858896255493},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.18264678120613098}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.805485188961029},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7871098518371582},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.6840729713439941},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5795646905899048},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5749821662902832},{"id":"https://openalex.org/C2983589003","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text detection","level":3,"score":0.5574926733970642},{"id":"https://openalex.org/C151375590","wikidata":"https://www.wikidata.org/wiki/Q17147076","display_name":"Noisy text analytics","level":4,"score":0.5166252255439758},{"id":"https://openalex.org/C72773152","wikidata":"https://www.wikidata.org/wiki/Q5287629","display_name":"Document layout analysis","level":3,"score":0.46748799085617065},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43510720133781433},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.41832998394966125},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34325748682022095},{"id":"https://openalex.org/C66945725","wikidata":"https://www.wikidata.org/wiki/Q18388823","display_name":"Text graph","level":3,"score":0.32796207070350647},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3213932514190674},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.26857858896255493},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.18264678120613098},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3611755","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611755","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8199999928474426,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G2612809889","display_name":null,"funder_award_id":"62176060","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G296198563","display_name":null,"funder_award_id":"2021SHZDZX0103","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3921780379","display_name":null,"funder_award_id":"20511100400","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"},{"id":"https://openalex.org/G4389483464","display_name":null,"funder_award_id":"2021SHZDZX0103","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"},{"id":"https://openalex.org/G763629385","display_name":null,"funder_award_id":"22511105000","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"},{"id":"https://openalex.org/F4320336023","display_name":"Program for Professor of Special Appointment (Eastern Scholar) at Shanghai Institutions of Higher Learning","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1903029394","https://openalex.org/W2081868602","https://openalex.org/W2084594934","https://openalex.org/W2124404372","https://openalex.org/W2133059825","https://openalex.org/W2152235937","https://openalex.org/W2193145675","https://openalex.org/W2339589954","https://openalex.org/W2412782625","https://openalex.org/W2593539516","https://openalex.org/W2784050770","https://openalex.org/W2962810613","https://openalex.org/W2963005009","https://openalex.org/W2963299604","https://openalex.org/W2963353821","https://openalex.org/W2964309882","https://openalex.org/W2991090032","https://openalex.org/W3010428518","https://openalex.org/W3014641072","https://openalex.org/W3028190090","https://openalex.org/W3100936573","https://openalex.org/W3102695566","https://openalex.org/W3106228955","https://openalex.org/W3106250896","https://openalex.org/W3109301572","https://openalex.org/W3118448193","https://openalex.org/W3131500599","https://openalex.org/W3170841864","https://openalex.org/W3180659539","https://openalex.org/W3199738066","https://openalex.org/W3213165621","https://openalex.org/W3213555225","https://openalex.org/W4226544595","https://openalex.org/W4304080333","https://openalex.org/W4312464225","https://openalex.org/W4312497550","https://openalex.org/W4312593844","https://openalex.org/W4386076354","https://openalex.org/W6600213211"],"related_works":["https://openalex.org/W2152349655","https://openalex.org/W2770471982","https://openalex.org/W2770474375","https://openalex.org/W2011580521","https://openalex.org/W1625494842","https://openalex.org/W4285055342","https://openalex.org/W2357267845","https://openalex.org/W3104052051","https://openalex.org/W4387968066","https://openalex.org/W3034105996"],"abstract_inverted_index":{"Text":[0],"segmentation":[1,24,33,89,95,178,193],"is":[2],"a":[3,123,130,176,210],"crucial":[4],"aspect":[5],"of":[6,50,68,119,149,184],"various":[7],"text-related":[8],"tasks,":[9],"including":[10],"text":[11,13,23,32,38,51,57,69,77,82,92,120,124,142,173,177,192],"erasing,":[12],"editing,":[14],"and":[15,34,94,114,157,170,218],"font":[16],"style":[17],"transfer.":[18],"In":[19,59,99],"recent":[20],"years,":[21],"multiple":[22],"datasets,":[25],"such":[26],"as":[27],"TextSeg":[28],"focusing":[29],"on":[30,36,190],"Latin":[31],"BTS":[35],"bilingual":[37],"segmentation,":[39,83],"have":[40],"been":[41],"proposed.":[42],"However,":[43],"existing":[44],"methods":[45,62,208],"either":[46],"disregard":[47],"the":[48,66,72,100,117,135,172,182,200,204],"annotations":[49,67],"location":[52,70,78],"or":[53],"directly":[54],"use":[55],"pre-trained":[56],"detectors.":[58],"general,":[60],"these":[61],"cannot":[63],"fully":[64],"utilize":[65],"in":[71,213],"datasets.":[73],"To":[74,180],"explicitly":[75],"incorporate":[76],"information":[79],"to":[80,137,141,152,166],"guide":[81],"we":[84,103,128,145,161,187],"propose":[85],"an":[86],"end-to-end":[87],"text-focused":[88,131],"framework,":[90,102],"where":[91],"detection":[93,125],"are":[96,221],"jointly":[97],"optimized.":[98],"proposed":[101,201],"first":[104],"extract":[105,153],"multi-level":[106,168],"global":[107],"visual":[108],"features":[109,169],"through":[110],"residual":[111],"convolution":[112],"blocks":[113],"then":[115],"predict":[116,171],"mask":[118,174],"areas":[121],"using":[122],"head.":[126,179],"Subsequently,":[127],"develop":[129],"module":[132],"that":[133,199],"compels":[134],"model":[136],"pay":[138],"more":[139],"attention":[140,150],"areas.":[143],"Specifically,":[144],"introduce":[146],"two":[147],"types":[148],"masks":[151],"corresponding":[154],"features:":[155],"text-aware":[156],"instance-aware":[158],"features.":[159],"Finally,":[160],"employ":[162],"hierarchical":[163],"Transformer":[164],"encoders":[165],"fuse":[167],"with":[175],"evaluate":[181],"effectiveness":[183],"our":[185],"method,":[186],"conduct":[188],"experiments":[189],"six":[191],"benchmarks.":[194],"The":[195,216],"experimental":[196],"results":[197],"demonstrate":[198],"method":[202],"outperforms":[203],"previous":[205],"state-of-the-art":[206],"(SOTA)":[207],"by":[209],"clear":[211],"margin":[212],"most":[214],"cases.":[215],"code":[217],"supplementary":[219],"materials":[220],"available":[222],"at":[223],"https://github.com/FudanVI/FudanOCR/tree/main/text-focused-Transformers":[224],"https://github.com/FudanVI/FudanOCR/tree/main/text-focused-Transformers.":[225]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}