{"id":"https://openalex.org/W4304091583","doi":"https://doi.org/10.1145/3503161.3547942","title":"SPTS: Single-Point Text Spotting","display_name":"SPTS: Single-Point Text Spotting","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304091583","doi":"https://doi.org/10.1145/3503161.3547942"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3547942","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3547942","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","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/A5012042767","display_name":"Dezhi Peng","orcid":"https://orcid.org/0000-0002-3263-3449"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dezhi Peng","raw_affiliation_strings":["South China University of Technology, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100352800","display_name":"Xinyu Wang","orcid":"https://orcid.org/0000-0002-5507-6569"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyu Wang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100389396","display_name":"Yuliang Liu","orcid":"https://orcid.org/0000-0002-3037-173X"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuliang Liu","raw_affiliation_strings":["Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100414877","display_name":"Jiaxin Zhang","orcid":"https://orcid.org/0000-0003-2144-9053"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaxin Zhang","raw_affiliation_strings":["South China University of Technology, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101787743","display_name":"Mingxin Huang","orcid":"https://orcid.org/0009-0002-5736-959X"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingxin Huang","raw_affiliation_strings":["South China University of Technology, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060021391","display_name":"Songxuan Lai","orcid":"https://orcid.org/0000-0002-0009-0566"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Songxuan Lai","raw_affiliation_strings":["Huawei Cloud Computing Technologies, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Cloud Computing Technologies, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100683041","display_name":"Jing Li","orcid":"https://orcid.org/0000-0001-9933-8383"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Li","raw_affiliation_strings":["Huawei Cloud Computing Technologies, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Cloud Computing Technologies, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003746644","display_name":"Shenggao Zhu","orcid":"https://orcid.org/0000-0002-3254-0058"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shenggao Zhu","raw_affiliation_strings":["Huawei Cloud Computing Technologies, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Cloud Computing Technologies, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010087030","display_name":"Dahua Lin","orcid":"https://orcid.org/0000-0002-8865-7896"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Dahua Lin","raw_affiliation_strings":["Chinese University of Hong Kong, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006294869","display_name":"Chunhua Shen","orcid":"https://orcid.org/0000-0002-8648-8718"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunhua Shen","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039363991","display_name":"Xiang Bai","orcid":"https://orcid.org/0000-0002-3449-5940"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Bai","raw_affiliation_strings":["Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080674767","display_name":"Lianwen Jin","orcid":"https://orcid.org/0000-0002-5456-0957"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lianwen Jin","raw_affiliation_strings":["South China University of Technology, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.4551,"has_fulltext":false,"cited_by_count":62,"citation_normalized_percentile":{"value":0.96818754,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"4272","last_page":"4281"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":1.0,"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":1.0,"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":0.9922999739646912,"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.975600004196167,"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/spotting","display_name":"Spotting","score":0.9610916376113892},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8379748463630676},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.7091816067695618},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6779399514198303},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.6315388083457947},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5899486541748047},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5531913042068481},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5288428068161011},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.525144100189209},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.5214985013008118},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4701381325721741},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.46735548973083496},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.43465134501457214},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37421321868896484},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3602932095527649},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09435847401618958}],"concepts":[{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.9610916376113892},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8379748463630676},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.7091816067695618},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6779399514198303},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.6315388083457947},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5899486541748047},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5531913042068481},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5288428068161011},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.525144100189209},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.5214985013008118},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4701381325721741},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.46735548973083496},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.43465134501457214},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37421321868896484},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3602932095527649},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09435847401618958},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3547942","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3547942","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1922126009","https://openalex.org/W2031489346","https://openalex.org/W2343052201","https://openalex.org/W2519818067","https://openalex.org/W2550687635","https://openalex.org/W2604243686","https://openalex.org/W2605982830","https://openalex.org/W2777652944","https://openalex.org/W2785383245","https://openalex.org/W2810028092","https://openalex.org/W2875814315","https://openalex.org/W2914492226","https://openalex.org/W2956161426","https://openalex.org/W2962804639","https://openalex.org/W2962935569","https://openalex.org/W2962986948","https://openalex.org/W2963299604","https://openalex.org/W2964018263","https://openalex.org/W2964296749","https://openalex.org/W2967615747","https://openalex.org/W2972866811","https://openalex.org/W2981969038","https://openalex.org/W2988098900","https://openalex.org/W3034792612","https://openalex.org/W3035452548","https://openalex.org/W3093046205","https://openalex.org/W3110398855","https://openalex.org/W3111172959","https://openalex.org/W3152831436","https://openalex.org/W3159307593","https://openalex.org/W3181016597","https://openalex.org/W3196976036","https://openalex.org/W6681452975"],"related_works":["https://openalex.org/W2918559346","https://openalex.org/W2114097550","https://openalex.org/W4286904253","https://openalex.org/W3119978414","https://openalex.org/W2516975559","https://openalex.org/W3206647229","https://openalex.org/W1969408022","https://openalex.org/W4287728368","https://openalex.org/W3039174484","https://openalex.org/W3163786145"],"abstract_inverted_index":{"Existing":[0],"scene":[1,32,54,60,165],"text":[2,6,33,55,61,166],"spotting":[3,34,56,62,167],"(i.e.,":[4],"end-to-end":[5,53],"detection":[7,77],"and":[8,78,87],"recognition)":[9],"methods":[10],"rely":[11],"on":[12,108],"costly":[13],"bounding":[14,22,147],"box":[15,148],"annotations":[16],"(e.g.,":[17],"text-line,":[18],"word-level,":[19],"or":[20,140],"character-level":[21],"boxes).":[23],"For":[24],"the":[25,75,94,117,124,127,146],"first":[26],"time,":[27],"we":[28,73,114],"demonstrate":[29],"that":[30,58,116,131,149,155],"training":[31],"models":[35],"can":[36,104,133],"be":[37,134,138,142],"achieved":[38],"with":[39],"an":[40,52,69,89],"extremely":[41],"low-cost":[42],"annotation":[43],"of":[44,84,126,169],"a":[45,64,82,157,161,170],"single-point":[46],"for":[47,164],"each":[48],"instance.":[49],"We":[50,153],"propose":[51],"method":[57,98],"tackles":[59],"as":[63,71,81],"sequence":[65,83],"prediction":[66],"task.":[67],"Given":[68],"image":[70],"input,":[72],"formulate":[74],"desired":[76],"recognition":[79],"results":[80,107],"discrete":[85],"tokens":[86],"use":[88],"auto-regressive":[90],"Transformer":[91],"to":[92,123,137],"predict":[93],"sequence.":[95],"The":[96,177],"proposed":[97],"is":[99,119,179],"simple":[100],"yet":[101],"effective,":[102],"which":[103],"achieve":[105],"state-of-the-art":[106],"widely":[109],"used":[110],"benchmarks.":[111],"Most":[112],"significantly,":[113],"show":[115],"performance":[118],"not":[120],"very":[121],"sensitive":[122],"positions":[125],"point":[128],"annotation,":[129],"meaning":[130],"it":[132],"much":[135,171],"easier":[136],"annotated":[139],"even":[141],"automatically":[143],"generated":[144],"than":[145,174],"requires":[150],"precise":[151],"positions.":[152],"believe":[154],"such":[156],"pioneer":[158],"attempt":[159],"indicates":[160],"significant":[162],"opportunity":[163],"applications":[168],"larger":[172],"scale":[173],"previously":[175],"possible.":[176],"code":[178],"available":[180],"at":[181],"https://github.com/shannanyinxiang/SPTS.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":27},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
