{"id":"https://openalex.org/W4409154592","doi":"https://doi.org/10.1109/tmm.2024.3521756","title":"Cps-STS: Bridging the Gap Between Content and Position for Coarse-Point-Supervised Scene Text Spotter","display_name":"Cps-STS: Bridging the Gap Between Content and Position for Coarse-Point-Supervised Scene Text Spotter","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4409154592","doi":"https://doi.org/10.1109/tmm.2024.3521756"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2024.3521756","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3521756","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":"https://openalex.org/A5082389724","display_name":"Weida Chen","orcid":"https://orcid.org/0000-0002-2727-4744"},"institutions":[{"id":"https://openalex.org/I189210763","display_name":"Yunnan University","ror":"https://ror.org/0040axw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I189210763"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Weida Chen","raw_affiliation_strings":["FIST LAB, School of Information Science and Engineering, Yunnan University, Kunming, Yunnan, China"],"affiliations":[{"raw_affiliation_string":"FIST LAB, School of Information Science and Engineering, Yunnan University, Kunming, Yunnan, China","institution_ids":["https://openalex.org/I189210763"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037387576","display_name":"Jie Jiang","orcid":"https://orcid.org/0000-0001-9658-5127"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Jiang","raw_affiliation_strings":["Tencent, Shenzhen, Guangdong, China"],"affiliations":[{"raw_affiliation_string":"Tencent, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102709426","display_name":"Linfei Wang","orcid":"https://orcid.org/0000-0003-1917-9031"},"institutions":[{"id":"https://openalex.org/I189210763","display_name":"Yunnan University","ror":"https://ror.org/0040axw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I189210763"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linfei Wang","raw_affiliation_strings":["FIST LAB, School of Information Science and Engineering, Yunnan University, Kunming, Yunnan, China"],"affiliations":[{"raw_affiliation_string":"FIST LAB, School of Information Science and Engineering, Yunnan University, Kunming, Yunnan, China","institution_ids":["https://openalex.org/I189210763"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080535168","display_name":"Huafeng Li","orcid":"https://orcid.org/0000-0003-2462-6174"},"institutions":[{"id":"https://openalex.org/I10660446","display_name":"Kunming University of Science and Technology","ror":"https://ror.org/00xyeez13","country_code":"CN","type":"education","lineage":["https://openalex.org/I10660446"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huafeng Li","raw_affiliation_strings":["School of Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, Yunnan, China"],"affiliations":[{"raw_affiliation_string":"School of Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, Yunnan, China","institution_ids":["https://openalex.org/I10660446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074672983","display_name":"Yibing Zhan","orcid":"https://orcid.org/0000-0003-3180-0484"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yibing Zhan","raw_affiliation_strings":["JD Explore Academy, Beijing, China"],"affiliations":[{"raw_affiliation_string":"JD Explore Academy, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067600725","display_name":"Dapeng Tao","orcid":"https://orcid.org/0000-0003-0783-5273"},"institutions":[{"id":"https://openalex.org/I189210763","display_name":"Yunnan University","ror":"https://ror.org/0040axw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I189210763"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dapeng Tao","raw_affiliation_strings":["FIST LAB, School of Information Science and Engineering, Yunnan University, Kunming, Yunnan, China"],"affiliations":[{"raw_affiliation_string":"FIST LAB, School of Information Science and Engineering, Yunnan University, Kunming, Yunnan, China","institution_ids":["https://openalex.org/I189210763"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5082389724"],"corresponding_institution_ids":["https://openalex.org/I189210763"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03191173,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"27","issue":null,"first_page":"1652","last_page":"1664"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.993399977684021,"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"}},"topics":[{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.993399977684021,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9908999800682068,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9846000075340271,"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/bridging","display_name":"Bridging (networking)","score":0.8535265922546387},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8140356540679932},{"id":"https://openalex.org/keywords/content","display_name":"Content (measure theory)","score":0.4596620798110962},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.452747642993927},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.4522658884525299},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.4491748511791229},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.38064831495285034},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3655471205711365},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.32144856452941895}],"concepts":[{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.8535265922546387},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8140356540679932},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.4596620798110962},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.452747642993927},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.4522658884525299},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4491748511791229},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.38064831495285034},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3655471205711365},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32144856452941895},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2024.3521756","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3521756","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":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W2008806374","https://openalex.org/W2128409098","https://openalex.org/W2144554289","https://openalex.org/W2875814315","https://openalex.org/W2914492226","https://openalex.org/W2963299604","https://openalex.org/W2997371611","https://openalex.org/W3003921261","https://openalex.org/W3034792612","https://openalex.org/W3096609285","https://openalex.org/W3097932944","https://openalex.org/W3110398855","https://openalex.org/W3111172959","https://openalex.org/W3152831436","https://openalex.org/W3174570731","https://openalex.org/W3179897446","https://openalex.org/W3196702778","https://openalex.org/W3196976036","https://openalex.org/W3217697975","https://openalex.org/W4210692322","https://openalex.org/W4225683503","https://openalex.org/W4285146136","https://openalex.org/W4292471377","https://openalex.org/W4293202879","https://openalex.org/W4293203016","https://openalex.org/W4304080540","https://openalex.org/W4304091583","https://openalex.org/W4304092561","https://openalex.org/W4312230431","https://openalex.org/W4312351507","https://openalex.org/W4312880451","https://openalex.org/W4382464147","https://openalex.org/W4386075667","https://openalex.org/W4386075746","https://openalex.org/W4386076400","https://openalex.org/W4386453743","https://openalex.org/W4386590413","https://openalex.org/W4388283616","https://openalex.org/W6771872505","https://openalex.org/W6801512601","https://openalex.org/W6809485838"],"related_works":["https://openalex.org/W4408719353","https://openalex.org/W4388870064","https://openalex.org/W2210139803","https://openalex.org/W4235186151","https://openalex.org/W2054685365","https://openalex.org/W2056057048","https://openalex.org/W2667588871","https://openalex.org/W2272354214","https://openalex.org/W2388648383","https://openalex.org/W2049371295"],"abstract_inverted_index":{"Recently,":[0],"weakly":[1],"supervised":[2],"methods":[3],"for":[4,113,128],"scene":[5],"text":[6,30,46,99,129,160,170,180,188,202,221],"spotter":[7,31],"are":[8],"increasingly":[9],"popular":[10],"with":[11,42,70,193,246],"researchers":[12],"due":[13],"to":[14,17,48,55,65,131,158,165,213,225,241],"their":[15],"potential":[16],"significantly":[18],"reduce":[19],"dataset":[20],"annotation":[21,51],"efforts.":[22],"The":[23],"latest":[24],"progress":[25],"in":[26,154],"this":[27,39,79,208],"field":[28],"is":[29,238],"based":[32],"on":[33],"single":[34],"or":[35],"multi-point":[36],"annotations.":[37],"However,":[38],"method":[40,84],"struggles":[41],"the":[43,49,57,110,155,183,187,201,211,218,227,260],"sensitivity":[44],"of":[45,62,68,186,230,236,264],"recognition":[47,67,228],"precise":[50],"location":[52,100],"and":[53,60,73,102,115,139,146,168,179,216,223,262],"fails":[54],"capture":[56],"relative":[58],"positions":[59],"shapes":[61],"characters,":[63],"leading":[64],"impaired":[66],"texts":[69],"extensive":[71],"rotations":[72],"flips.":[74],"To":[75],"address":[76],"these":[77],"challenges,":[78],"paper":[80],"develops":[81],"a":[82,94,104,122,152,248,254],"novel":[83],"named":[85],"Coarse-point-supervised":[86],"Scene":[87],"Text":[88],"Spotter":[89],"(Cps-STS).":[90],"Cps-STS":[91,237,265],"first":[92],"utilizes":[93],"few":[95,249],"approximate":[96],"points":[97,252],"as":[98,137,151,197],"labels":[101],"introduces":[103],"learnable":[105],"position":[106,138,224],"modulation":[107],"mechanism,":[108],"easing":[109],"accuracy":[111],"requirements":[112],"annotations":[114],"enhancing":[116],"model":[117,212],"robustness.":[118],"Additionally,":[119],"we":[120,172],"incorporate":[121],"Spatial":[123],"Compatibility":[124],"Attention":[125],"(SCA)":[126],"module":[127,142,157],"decoding":[130],"effectively":[132,214],"utilize":[133,217],"spatial":[134,161,176,194],"data":[135],"such":[136],"shape.":[140],"This":[141],"fuses":[143],"compound":[144],"queries":[145],"global":[147],"feature":[148],"maps,":[149],"serving":[150],"bias":[153,198],"SCA":[156],"express":[159],"morphology.":[162],"In":[163],"order":[164],"accurately":[166],"locate":[167],"decode":[169],"content,":[171],"introduce":[173],"features":[174,185,192],"containing":[175],"morphology":[177,195],"information":[178,196],"content":[181,222],"into":[182,200],"input":[184],"decoder.":[189],"By":[190],"introducing":[191],"terms":[199],"decoder,":[203],"ablation":[204],"experiments":[205,258],"demonstrate":[206],"that":[207],"operation":[209],"enables":[210],"identify":[215],"relationship":[219],"between":[220],"enhance":[226],"performance":[229,245],"our":[231],"model.":[232],"One":[233],"significant":[234],"advantage":[235],"its":[239],"ability":[240],"achieve":[242],"full":[243],"supervision-level":[244],"just":[247],"imprecise":[250],"coarse":[251],"at":[253],"low":[255],"cost.":[256],"Extensive":[257],"validate":[259],"effectiveness":[261],"superiority":[263],"over":[266],"existing":[267],"approaches.":[268]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}