{"id":"https://openalex.org/W4283802017","doi":"https://doi.org/10.1145/3524617","title":"Learning Pixel Affinity Pyramid for Arbitrary-Shaped Text Detection","display_name":"Learning Pixel Affinity Pyramid for Arbitrary-Shaped Text Detection","publication_year":2022,"publication_date":"2022-07-04","ids":{"openalex":"https://openalex.org/W4283802017","doi":"https://doi.org/10.1145/3524617"},"language":"en","primary_location":{"id":"doi:10.1145/3524617","doi":"https://doi.org/10.1145/3524617","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3524617","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","ccf-b","cwts-core","dongbi-b","jufo-2","ki-jl-2","norway-2","poland-100","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"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/A5090529050","display_name":"Zilong Fu","orcid":"https://orcid.org/0000-0002-2885-154X","observed_orcids":["https://orcid.org/0000-0002-2885-154X"]},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zilong Fu","raw_affiliation_strings":["University of Science and Technology of China, School of Information Science and Technology, HeFei, AnHui"],"raw_orcid":"https://orcid.org/0000-0002-2885-154X","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, School of Information Science and Technology, HeFei, AnHui","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078162380","display_name":"Hongtao Xie","orcid":"https://orcid.org/0000-0002-6249-5315","observed_orcids":["https://orcid.org/0000-0002-6249-5315","https://orcid.org/0000-0002-0163-9434"]},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongtao Xie","raw_affiliation_strings":["University of Science and Technology of China, School of Information Science and Technology, HeFei, AnHui"],"raw_orcid":"https://orcid.org/0000-0002-6249-5315","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, School of Information Science and Technology, HeFei, AnHui","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008604905","display_name":"Shancheng Fang","orcid":"https://orcid.org/0000-0002-3100-3664","observed_orcids":["https://orcid.org/0000-0002-3100-3664"]},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shancheng Fang","raw_affiliation_strings":["University of Science and Technology of China, School of Information Science and Technology, HeFei, AnHui"],"raw_orcid":"https://orcid.org/0000-0002-3100-3664","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, School of Information Science and Technology, HeFei, AnHui","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100427468","display_name":"Yuxin Wang","orcid":"https://orcid.org/0000-0002-0228-6220","observed_orcids":["https://orcid.org/0000-0002-0228-6220","https://orcid.org/0009-0000-0873-0436","https://orcid.org/0009-0000-9174-028X"]},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxin Wang","raw_affiliation_strings":["University of Science and Technology of China, School of Information Science and Technology, HeFei, AnHui"],"raw_orcid":"https://orcid.org/0000-0002-0228-6220","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, School of Information Science and Technology, HeFei, AnHui","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054620019","display_name":"Mengting Xing","orcid":"https://orcid.org/0000-0002-7285-6671","observed_orcids":["https://orcid.org/0000-0002-7285-6671"]},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengting Xing","raw_affiliation_strings":["University of Science and Technology of China, School of Information Science and Technology, HeFei, AnHui"],"raw_orcid":"https://orcid.org/0000-0002-7285-6671","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, School of Information Science and Technology, HeFei, AnHui","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046305086","display_name":"Yongdong Zhang","orcid":"https://orcid.org/0000-0002-1151-1792","observed_orcids":["https://orcid.org/0000-0002-1151-1792"]},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongdong Zhang","raw_affiliation_strings":["University of Science and Technology of China, School of Information Science and Technology, HeFei, AnHui"],"raw_orcid":"https://orcid.org/0000-0002-1151-1792","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, School of Information Science and Technology, HeFei, AnHui","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":1.3229,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.8060343,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":"19","issue":"1s","first_page":"1","last_page":"24"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9990000128746033,"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":0.9990000128746033,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0006000000284984708,"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/T12707","display_name":"Vehicle License Plate Recognition","score":0.00019999999494757503,"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/instance-segmentation","display_name":"instance segmentation","score":0.7379999756813049},{"id":"https://openalex.org/keywords/semantic-segmentation","display_name":"semantic segmentation","score":0.9210000038146973},{"id":"https://openalex.org/keywords/false-positive-reduction","display_name":"false positive reduction","score":0.6700000166893005},{"id":"https://openalex.org/keywords/natural-images","display_name":"natural images","score":0.5139999985694885}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7610023617744446},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.7546533942222595},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6921010613441467},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6622190475463867},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5740007162094116},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.5706575512886047},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5575754642486572},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5220417976379395},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5216898322105408},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.470255970954895},{"id":"https://openalex.org/C2983589003","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text detection","level":3,"score":0.4550609588623047},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38011854887008667},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.32287365198135376},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11874479055404663},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3524617","doi":"https://doi.org/10.1145/3524617","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3524617","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","ccf-b","cwts-core","dongbi-b","jufo-2","ki-jl-2","norway-2","poland-100","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1484805094","display_name":null,"funder_award_id":"WK3480000011","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G3216672294","display_name":null,"funder_award_id":"Y2021122","funder_id":"https://openalex.org/F4320322847","funder_display_name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences"},{"id":"https://openalex.org/G8293487898","display_name":null,"funder_award_id":"62121002, 62022076, and U1936210","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322847","display_name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","ror":"https://ror.org/031141b54"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W1988461287","https://openalex.org/W2030602513","https://openalex.org/W2124404372","https://openalex.org/W2128854450","https://openalex.org/W2142159465","https://openalex.org/W2144554289","https://openalex.org/W2194775991","https://openalex.org/W2341497066","https://openalex.org/W2343052201","https://openalex.org/W2432481613","https://openalex.org/W2464918637","https://openalex.org/W2519887557","https://openalex.org/W2550687635","https://openalex.org/W2559655401","https://openalex.org/W2593539516","https://openalex.org/W2604186312","https://openalex.org/W2604735854","https://openalex.org/W2605076167","https://openalex.org/W2605982830","https://openalex.org/W2752782242","https://openalex.org/W2766895242","https://openalex.org/W2772800855","https://openalex.org/W2784050770","https://openalex.org/W2798355657","https://openalex.org/W2798450692","https://openalex.org/W2810028092","https://openalex.org/W2875814315","https://openalex.org/W2895065325","https://openalex.org/W2902494497","https://openalex.org/W2947128531","https://openalex.org/W2953894958","https://openalex.org/W2955058313","https://openalex.org/W2962781062","https://openalex.org/W2962810613","https://openalex.org/W2963091558","https://openalex.org/W2963150697","https://openalex.org/W2963161243","https://openalex.org/W2963299736","https://openalex.org/W2963319519","https://openalex.org/W2963353821","https://openalex.org/W2963398399","https://openalex.org/W2963647456","https://openalex.org/W2963977642","https://openalex.org/W2964014680","https://openalex.org/W2964294787","https://openalex.org/W2964685115","https://openalex.org/W2967155990","https://openalex.org/W2967591398","https://openalex.org/W2968226676","https://openalex.org/W2981537222","https://openalex.org/W2981689412","https://openalex.org/W2988098900","https://openalex.org/W2991626090","https://openalex.org/W2996609910","https://openalex.org/W2997351497","https://openalex.org/W3018514853","https://openalex.org/W3027134841","https://openalex.org/W3034345703","https://openalex.org/W3181186176","https://openalex.org/W3202415716","https://openalex.org/W4246999471"],"related_works":["https://openalex.org/W2991626090","https://openalex.org/W4405778871","https://openalex.org/W4212820886","https://openalex.org/W4281250886","https://openalex.org/W3111911450","https://openalex.org/W4322493847","https://openalex.org/W3153178742","https://openalex.org/W4306784162","https://openalex.org/W2953894958","https://openalex.org/W4407736541"],"abstract_inverted_index":{"Arbitrary-shaped":[0],"text":[1,21,36,45,54,97,123,150,187,208,214,247],"detection":[2,46,55],"in":[3,26,67,152,257],"natural":[4],"images":[5],"is":[6,78,89,119],"a":[7,52,63,68,114],"challenging":[8],"task":[9],"due":[10],"to":[11,80,93,121,145,181,205],"the":[12,15,18,74,111,126,131,134,147,153,159,175,183,186,222,225],"complexity":[13],"of":[14,20,31,86,96,133,149,178,224],"background":[16],"and":[17,34,50,62,142,164,227,238,249],"diversity":[19],"properties.":[22],"The":[23,172,194],"difficulty":[24],"lies":[25],"two":[27,156],"aspects:":[28],"accurate":[29,102],"separation":[30],"adjacent":[32],"texts":[33],"sufficient":[35],"feature":[37],"representation.":[38],"To":[39],"handle":[40],"these":[41],"problems,":[42],"we":[43],"consider":[44],"as":[47],"instance":[48,83],"segmentation":[49,61,128],"propose":[51],"novel":[53],"framework,":[56],"which":[57,88,189,211],"jointly":[58],"learns":[59],"semantic":[60,127,176,209],"pixel":[64,75,136],"affinity":[65,76,137],"pyramid":[66,77],"unified":[69],"fully":[70],"convolutional":[71],"network.":[72],"Specifically,":[73],"proposed":[79],"encode":[81],"multi-scale":[82,198],"affiliation":[84],"relationships":[85],"pixels,":[87],"not":[90],"only":[91],"robust":[92],"varying":[94],"shapes":[95],"but":[98,116],"also":[99],"provides":[100],"an":[101,202],"boundary":[103],"description":[104],"for":[105],"separating":[106],"closely":[107],"located":[108],"texts.":[109,260],"In":[110],"inference":[112],"phase,":[113],"simple":[115],"effective":[117],"post-processing":[118],"presented":[120],"reconstruct":[122],"instances":[124],"from":[125,185],"results":[129,230],"under":[130],"guidance":[132],"learned":[135],"pyramid,":[138],"achieving":[139],"good":[140],"accuracy":[141],"efficiency.":[143],"Furthermore,":[144],"enhance":[146,182],"representation":[148],"features":[151,180,184],"neural":[154],"network,":[155],"modules":[157],"\u2014":[158,169],"Region":[160],"Enhancement":[161],"Module":[162,167],"(REM)":[163],"Attentional":[165],"Fusion":[166],"(AFM)":[168],"are":[170,219],"proposed.":[171],"REM":[173,226],"models":[174],"correlations":[177],"regional":[179],"area,":[188],"effectively":[190],"suppresses":[191],"false-positive":[192],"detection.":[193,215],"AFM":[195],"adaptively":[196],"fuses":[197],"textual":[199],"information":[200],"through":[201],"attention":[203],"mechanism":[204],"obtain":[206],"abundant":[207],"features,":[210],"benefits":[212],"multi-sized":[213],"Extensive":[216],"ablation":[217],"experiments":[218],"conducted":[220],"demonstrating":[221],"effectiveness":[223],"AFM.":[228],"Evaluation":[229],"on":[231],"standard":[232],"benchmarks,":[233],"including":[234],"Total-Text,":[235],"ICDAR2015,":[236],"SCUT-CTW1500,":[237],"MSRA-TD500,":[239],"show":[240],"that":[241],"our":[242],"method":[243],"surpasses":[244],"most":[245],"existing":[246],"detectors":[248],"achieves":[250],"state-of-the-art":[251],"performance,":[252],"denoting":[253],"its":[254],"superior":[255],"capability":[256],"detecting":[258],"arbitrary-shaped":[259]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2022-07-05T00:00:00"}