{"id":"https://openalex.org/W3164831905","doi":"https://doi.org/10.1145/3582524.3582542","title":"Enhancing Scene Text Recognition with Visual Context Information","display_name":"Enhancing Scene Text Recognition with Visual Context Information","publication_year":2022,"publication_date":"2022-06-01","ids":{"openalex":"https://openalex.org/W3164831905","doi":"https://doi.org/10.1145/3582524.3582542","mag":"3164831905"},"language":"en","primary_location":{"id":"doi:10.1145/3582524.3582542","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3582524.3582542","pdf_url":null,"source":{"id":"https://openalex.org/S6756005","display_name":"ACM SIGIR Forum","issn_l":"0163-5840","issn":["0163-5840","1558-0229"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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 SIGIR Forum","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/10803/670286","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051373692","display_name":"Ahmed Sabir","orcid":null},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Ahmed Sabir","raw_affiliation_strings":["Universitat Polit\u00e8cnica de Catalunya, Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Universitat Polit\u00e8cnica de Catalunya, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5051373692"],"corresponding_institution_ids":["https://openalex.org/I9617848"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00290554,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"56","issue":"1","first_page":"1","last_page":"2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9983999729156494,"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":0.9983000159263611,"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/computer-science","display_name":"Computer science","score":0.873929500579834},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6701691150665283},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6424517631530762},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6374976634979248},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6139944791793823},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.5985883474349976},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5981065630912781},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.5548332333564758},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.5469683408737183},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4795948565006256},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4485008120536804},{"id":"https://openalex.org/keywords/semeval","display_name":"SemEval","score":0.4398070275783539},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4122352600097656},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.282576322555542},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2533813416957855},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.21305450797080994},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12857499718666077}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.873929500579834},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6701691150665283},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6424517631530762},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6374976634979248},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6139944791793823},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.5985883474349976},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5981065630912781},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.5548332333564758},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.5469683408737183},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4795948565006256},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4485008120536804},{"id":"https://openalex.org/C44572571","wikidata":"https://www.wikidata.org/wiki/Q7448970","display_name":"SemEval","level":3,"score":0.4398070275783539},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4122352600097656},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.282576322555542},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2533813416957855},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.21305450797080994},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12857499718666077},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3582524.3582542","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3582524.3582542","pdf_url":null,"source":{"id":"https://openalex.org/S6756005","display_name":"ACM SIGIR Forum","issn_l":"0163-5840","issn":["0163-5840","1558-0229"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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 SIGIR Forum","raw_type":"journal-article"},{"id":"pmh:oai:dnet:tdr_________::3596599cc6ce725208694518556b5695","is_oa":true,"landing_page_url":"http://hdl.handle.net/10803/670286","pdf_url":null,"source":{"id":"https://openalex.org/S4306402641","display_name":"LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Cient\u00edficas)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4383465926","host_organization_name":"LA Referencia","host_organization_lineage":["https://openalex.org/I4383465926"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"TDX (Tesis Doctorals en Xarxa)","raw_type":"info:eu-repo/semantics/doctoralThesis"},{"id":"pmh:oai:digital.csic.es:10261/233568","is_oa":false,"landing_page_url":"http://hdl.handle.net/10261/233568","pdf_url":null,"source":{"id":"https://openalex.org/S4306400616","display_name":"DIGITAL.CSIC (Spanish National Research Council (CSIC))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I134820265","host_organization_name":"Consejo Superior de Investigaciones Cient\u00edficas","host_organization_lineage":["https://openalex.org/I134820265"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"tesis doctoral"},{"id":"pmh:oai:dnet:upcommonspor::1db52d454059872f544aa0a4f5ea2c15","is_oa":true,"landing_page_url":"http://hdl.handle.net/2117/334952","pdf_url":null,"source":{"id":"https://openalex.org/S4306402641","display_name":"LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Cient\u00edficas)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4383465926","host_organization_name":"LA Referencia","host_organization_lineage":["https://openalex.org/I4383465926"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"TDX (Tesis Doctorals en Xarxa)","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:dnet:tdr_________::3596599cc6ce725208694518556b5695","is_oa":true,"landing_page_url":"http://hdl.handle.net/10803/670286","pdf_url":null,"source":{"id":"https://openalex.org/S4306402641","display_name":"LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Cient\u00edficas)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4383465926","host_organization_name":"LA Referencia","host_organization_lineage":["https://openalex.org/I4383465926"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"TDX (Tesis Doctorals en Xarxa)","raw_type":"info:eu-repo/semantics/doctoralThesis"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7400000095367432}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W2758036962","https://openalex.org/W2898692195","https://openalex.org/W2899463612","https://openalex.org/W2970279920","https://openalex.org/W3035597279"],"related_works":["https://openalex.org/W2752041471","https://openalex.org/W78638240","https://openalex.org/W2252122760","https://openalex.org/W2469576572","https://openalex.org/W2159849140","https://openalex.org/W2753242182","https://openalex.org/W2966570129","https://openalex.org/W3099449837","https://openalex.org/W2774861092","https://openalex.org/W2107397692"],"abstract_inverted_index":{"This":[0],"thesis":[1],"addresses":[2],"the":[3,35,43,48,56,59,62,72,78,138,148,166,200,215,219,232,244,247,256,260,264,278,283,293,299,309,329,341,344,350,357],"problem":[4,106],"of":[5,37,58,150,153,202,206,218,311],"improving":[6],"text":[7,16,134,172,248],"spotting":[8,135,249],"systems,":[9,368],"which":[10,69,328],"aim":[11],"to":[12,33,67,122,127,164,213,272,307,352,355,370],"detect":[13],"and":[14,100,116,124,156,186,194,222,251,286,346,362,369,395],"recognize":[15],"in":[17,112,119,327,349,364],"unrestricted":[18],"images":[19],"(e.g.,":[20,182],"a":[21,26,84,92,95,161,320,372],"street":[22],"sign,":[23],"an":[24,81,266,304],"advertisement,":[25],"bus":[27],"destination,":[28],"etc.).":[29],"The":[30,51,241],"goal":[31],"is":[32,53,160,177,270],"improve":[34,132],"performance":[36],"off-the-shelf":[38],"vision":[39],"systems":[40,136],"by":[41,107],"exploiting":[42],"semantic":[44,151,167,175,207,216,358],"information":[45,339],"derived":[46],"from":[47,246,259],"image":[49,60,82,158,274],"itself.":[50],"rationale":[52],"that":[54,80,91,131],"knowing":[55],"content":[57],"or":[61,144,171,228],"visual":[63,257,294,321],"context":[64,159,258,295,322],"can":[65],"help":[66],"decide":[68],"words":[70,155,170,245],"are":[71,189,239],"correct":[73],"candidate":[74,154],"words.":[75],"For":[76,263],"example,":[77],"fact":[79],"shows":[83],"coffee":[85],"shop":[86],"makes":[87],"it":[88],"more":[89,178],"likely":[90],"word":[93,221,235],"on":[94,109,255,292,298,387],"signboard":[96],"reads":[97],"as":[98,280,282,315],"Dunkin":[99],"not":[101,192,290],"unkind.":[102],"We":[103],"address":[104],"this":[105,325],"drawing":[108],"successful":[110],"developments":[111],"natural":[113],"language":[114],"processing":[115],"machine":[117],"learning,":[118],"particular,":[120],"learning":[121],"re-rank":[123,287],"neural":[125,268,316],"networks,":[126,317],"present":[128],"post-process":[129],"frameworks":[130],"state-of-the-art":[133],"without":[137],"need":[139],"for":[140,324,376],"costly":[141],"data-driven":[142,312],"re-training":[143],"tuning":[145],"procedures.":[146],"Discovering":[147],"degree":[149],"relatedness":[152,176,217],"their":[157,365],"task":[162],"related":[163,190],"assessing":[165],"similarity":[168,181],"between":[169,301,360],"fragments.":[173],"However,":[174],"general":[179],"than":[180],"car,":[183],"road":[184],",":[185],"traffic":[187],"light":[188],"but":[191,296],"similar)":[193],"requires":[195],"certain":[196],"adaptations.":[197],"To":[198],"meet":[199,308],"requirements":[201,310],"these":[203],"broader":[204],"perspectives":[205],"similarity,":[208],"we":[209,318],"develop":[210],"two":[211],"approaches":[212,313],"learn":[214],"spotted":[220],"its":[223],"environmental":[224],"context:":[225],"word-to-word":[226,233],"(object)":[227],"word-to-sentence":[229],"(caption).":[230],"In":[231],"approach,":[234],"embedding":[236],"based":[237,254,289],"re-rankers":[238],"developed.":[240],"re-ranker":[242],"takes":[243],"baseline":[250,375],"re-ranks":[252],"them":[253,288],"object":[261],"classifier.":[262],"second,":[265],"end-to-end":[267],"approach":[269],"designed":[271],"drive":[273],"description":[275],"(caption)":[276],"at":[277],"sentence-level":[279],"well":[281],"word-level":[284],"(objects)":[285],"only":[291],"also":[297],"co-occurrence":[300],"them.":[302],"As":[303],"additional":[305],"contribution,":[306],"such":[314,377],"propose":[319],"dataset":[323,333],"task,":[326],"publicly":[330],"available":[331],"COCO-text":[332],"1":[334],"has":[335],"been":[336],"extended":[337],"with":[338],"about":[340],"scene":[342,363],"(including":[343],"objects":[345],"places":[347],"appearing":[348],"image)":[351],"enable":[353],"researchers":[354],"include":[356],"relations":[359],"texts":[361],"Text":[366],"Spotting":[367],"offer":[371],"common":[373],"evaluation":[374],"approaches.":[378],"Awarded":[379],"by:":[380,392],"Universitat":[381],"Polit\u00e8cnica":[382],"de":[383],"Catalunya,":[384],"Barcelona,":[385],"Spain":[386],"10":[388],"September":[389],"2020.":[390],"Supervised":[391],"Llu\u00eds":[393],"Padr\u00f3":[394],"Francesc":[396],"Moreno-Noguer.":[397],"Available":[398],"at:":[399],"https://upcommons.upc.edu/handle/2117/334952.":[400]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}