{"id":"https://openalex.org/W4405778935","doi":"https://doi.org/10.1109/tmm.2024.3521824","title":"Spotlight Text Detector: Spotlight on Candidate Regions Like a Camera","display_name":"Spotlight Text Detector: Spotlight on Candidate Regions Like a Camera","publication_year":2024,"publication_date":"2024-12-25","ids":{"openalex":"https://openalex.org/W4405778935","doi":"https://doi.org/10.1109/tmm.2024.3521824"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2024.3521824","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3521824","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-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":null,"display_name":"Xu Han","orcid":"https://orcid.org/0009-0005-6489-719X"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xu Han","raw_affiliation_strings":["School of Computer Science and the School of Artificial Intelligence, Optics and Electronics (iOPEN), Northwestern Polytechnical University, Xi&#x0027;an, China","School of Artificial Intelligence, Optics and Electronics (iOPEN), Northwestern Polytechnical University, Xi&#x0027;an, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and the School of Artificial Intelligence, Optics and Electronics (iOPEN), Northwestern Polytechnical University, Xi&#x0027;an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Artificial Intelligence, Optics and Electronics (iOPEN), Northwestern Polytechnical University, Xi&#x0027;an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001848378","display_name":"Junyu Gao","orcid":"https://orcid.org/0000-0001-6000-8168"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junyu Gao","raw_affiliation_strings":["School of Artificial Intelligence, Optics and Electronics (iOPEN), Northwestern Polytechnical University, Xi&#x0027;an, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Optics and Electronics (iOPEN), Northwestern Polytechnical University, Xi&#x0027;an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077254624","display_name":"Chuang Yang","orcid":"https://orcid.org/0000-0002-4086-8387"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuang Yang","raw_affiliation_strings":["School of Computer Science and the School of Artificial Intelligence, Optics and Electronics (iOPEN), Northwestern Polytechnical University, Xi&#x0027;an, China","School of Artificial Intelligence, Optics and Electronics (iOPEN), Northwestern Polytechnical University, Xi&#x0027;an, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and the School of Artificial Intelligence, Optics and Electronics (iOPEN), Northwestern Polytechnical University, Xi&#x0027;an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Artificial Intelligence, Optics and Electronics (iOPEN), Northwestern Polytechnical University, Xi&#x0027;an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100334801","display_name":"Yuan Yuan","orcid":"https://orcid.org/0000-0003-3352-0662"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Yuan","raw_affiliation_strings":["School of Artificial Intelligence, Optics and Electronics (iOPEN), Northwestern Polytechnical University, Xi&#x0027;an, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Optics and Electronics (iOPEN), Northwestern Polytechnical University, Xi&#x0027;an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100341321","display_name":"Qi Wang","orcid":"https://orcid.org/0000-0002-7028-4956"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Wang","raw_affiliation_strings":["School of Artificial Intelligence, Optics and Electronics (iOPEN), Northwestern Polytechnical University, Xi&#x0027;an, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Optics and Electronics (iOPEN), Northwestern Polytechnical University, Xi&#x0027;an, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":9.8715,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.97976573,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"27","issue":null,"first_page":"1937","last_page":"1949"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13718","display_name":"Media Influence and Politics","score":0.22630000114440918,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13718","display_name":"Media Influence and Politics","score":0.22630000114440918,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7986534833908081},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.6434925198554993},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.4447340965270996},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.43071362376213074},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4169744551181793},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.15286126732826233}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7986534833908081},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.6434925198554993},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.4447340965270996},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.43071362376213074},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4169744551181793},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.15286126732826233}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2024.3521824","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3521824","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1058697321","display_name":null,"funder_award_id":"62306241","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1964179093","display_name":null,"funder_award_id":"U21B2041","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5992145127","display_name":null,"funder_award_id":"62471394","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1972065312","https://openalex.org/W1988461287","https://openalex.org/W2074849287","https://openalex.org/W2144554289","https://openalex.org/W2194775991","https://openalex.org/W2343052201","https://openalex.org/W2519818067","https://openalex.org/W2550687635","https://openalex.org/W2560023338","https://openalex.org/W2565639579","https://openalex.org/W2593539516","https://openalex.org/W2605076167","https://openalex.org/W2605982830","https://openalex.org/W2784050770","https://openalex.org/W2785383245","https://openalex.org/W2810028092","https://openalex.org/W2902494497","https://openalex.org/W2962810613","https://openalex.org/W2963299604","https://openalex.org/W2963647456","https://openalex.org/W2964294787","https://openalex.org/W2966926453","https://openalex.org/W2967615747","https://openalex.org/W2970910956","https://openalex.org/W2991626090","https://openalex.org/W2997371611","https://openalex.org/W2998621280","https://openalex.org/W3003868038","https://openalex.org/W3034514377","https://openalex.org/W3034792612","https://openalex.org/W3035679705","https://openalex.org/W3088488048","https://openalex.org/W3093046205","https://openalex.org/W3138649552","https://openalex.org/W3154631726","https://openalex.org/W3159307593","https://openalex.org/W3171030392","https://openalex.org/W3172799005","https://openalex.org/W3181016597","https://openalex.org/W3184364189","https://openalex.org/W3203431461","https://openalex.org/W4210692322","https://openalex.org/W4212820886","https://openalex.org/W4214922754","https://openalex.org/W4221097663","https://openalex.org/W4283692648","https://openalex.org/W4283802017","https://openalex.org/W4285065310","https://openalex.org/W4285263829","https://openalex.org/W4289792721","https://openalex.org/W4293202879","https://openalex.org/W4293203016","https://openalex.org/W4293679656","https://openalex.org/W4296872795","https://openalex.org/W4312593844","https://openalex.org/W4312714895","https://openalex.org/W4321021053","https://openalex.org/W4376456529","https://openalex.org/W4380839071","https://openalex.org/W4382464147","https://openalex.org/W4383113591","https://openalex.org/W4393148643","https://openalex.org/W4402774414","https://openalex.org/W6746206475","https://openalex.org/W6802541184"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"The":[0,130,163],"irregular":[1],"contour":[2],"representation":[3],"is":[4,58,209],"one":[5],"of":[6,24,30,89,117,197],"the":[7,22,28,55,78,81,104,135,143,185,195,198],"tough":[8],"challenges":[9],"in":[10],"scene":[11,90,175],"text":[12,46,56,112],"detection.":[13,73],"Although":[14],"segmentation-based":[15],"methods":[16,44,214],"have":[17],"achieved":[18],"significant":[19],"progress":[20],"with":[21,62],"help":[23],"flexible":[25],"pixel":[26],"prediction,":[27],"overlap":[29],"geographically":[31],"close":[32],"texts":[33,91],"hinders":[34],"detecting":[35],"them":[36,50,100,155],"separately.":[37],"To":[38,102],"alleviate":[39],"this":[40],"problem,":[41],"some":[42,159],"shrink-based":[43],"predict":[45],"kernels":[47],"and":[48,87,123,153,201,222],"expand":[49],"to":[51,69,98,157,169,183,188,211],"restructure":[52],"texts.":[53,176],"However,":[54],"kernel":[57,190],"an":[59,109],"artificial":[60],"object":[61],"incomplete":[63],"semantic":[64],"features":[65,83,148,173],"that":[66,206],"are":[67],"prone":[68],"incorrect":[70],"or":[71],"missing":[72],"In":[74],"addition,":[75],"different":[76,166],"from":[77],"general":[79],"objects,":[80],"geometry":[82],"(aspect":[84],"ratio,":[85],"scale,":[86],"shape)":[88],"vary":[92],"significantly,":[93],"which":[94,115],"makes":[95],"it":[96],"difficult":[97],"detect":[99],"accurately.":[101],"consider":[103],"above":[105],"problems,":[106],"we":[107],"propose":[108],"effective":[110],"spotlight":[111,119],"detector":[113],"(STD),":[114],"consists":[116],"a":[118,124,139,150],"calibration":[120],"module":[121,128],"(SCM)":[122],"multivariate":[125],"information":[126],"extraction":[127],"(MIEM).":[129],"former":[131],"concentrates":[132],"efforts":[133],"on":[134,142,215],"candidate":[136,147],"kernel,":[137],"like":[138],"camera":[140],"focus":[141],"target.":[144],"It":[145,177],"obtains":[146],"through":[149],"mapping":[151],"filter":[152],"calibrates":[154],"precisely":[156],"eliminate":[158],"false":[160],"positive":[161],"samples.":[162],"latter":[164],"designs":[165],"shape":[167],"schemes":[168],"explore":[170],"multiple":[171],"geometric":[172],"for":[174],"helps":[178],"extract":[179],"various":[180,216],"spatial":[181],"relationships":[182],"improve":[184],"model's":[186],"ability":[187],"recognize":[189],"regions.":[191],"Ablation":[192],"studies":[193],"prove":[194],"effectiveness":[196],"designed":[199],"SCM":[200],"MIEM.":[202],"Extensive":[203],"experiments":[204],"verify":[205],"our":[207],"STD":[208],"superior":[210],"existing":[212],"state-of-the-art":[213],"datasets,":[217],"including":[218],"ICDAR2015,":[219],"CTW1500,":[220],"MSRA-TD500,":[221],"Total-Text.":[223]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}
