{"id":"https://openalex.org/W4417072978","doi":"https://doi.org/10.1145/3743093.3771031","title":"SELECT: Detecting Label Errors in Real-world Scene Text Data","display_name":"SELECT: Detecting Label Errors in Real-world Scene Text Data","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W4417072978","doi":"https://doi.org/10.1145/3743093.3771031"},"language":null,"primary_location":{"id":"doi:10.1145/3743093.3771031","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3743093.3771031","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2512.14050","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108105976","display_name":"Wenjun Liu","orcid":"https://orcid.org/0000-0001-8364-3391"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjun Liu","raw_affiliation_strings":["Yidun AI Lab, NetEase, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0001-8364-3391","affiliations":[{"raw_affiliation_string":"Yidun AI Lab, NetEase, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109996614","display_name":"Qian Wu","orcid":"https://orcid.org/0009-0006-2491-0035"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qian Wu","raw_affiliation_strings":["Yidun AI Lab, NetEase, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0009-0006-2491-0035","affiliations":[{"raw_affiliation_string":"Yidun AI Lab, NetEase, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110378896","display_name":"Yifeng Hu","orcid":"https://orcid.org/0009-0004-0544-0504"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifeng Hu","raw_affiliation_strings":["Yidun AI Lab, NetEase, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0009-0004-0544-0504","affiliations":[{"raw_affiliation_string":"Yidun AI Lab, NetEase, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028527896","display_name":"Yi-nian LI","orcid":"https://orcid.org/0009-0003-0935-2483"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuke Li","raw_affiliation_strings":["Yidun AI Lab, NetEase, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0009-0003-0935-2483","affiliations":[{"raw_affiliation_string":"Yidun AI Lab, NetEase, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I4210091137"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210091137"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18091994,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.5655999779701233,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.5655999779701233,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.2784000039100647,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.054999999701976776,"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/process","display_name":"Process (computing)","score":0.6086999773979187},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5971999764442444},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.560699999332428},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5273000001907349},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4009999930858612}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7940000295639038},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6403999924659729},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6086999773979187},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5971999764442444},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.560699999332428},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5273000001907349},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4009999930858612},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.373199999332428},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3702000081539154},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.33239999413490295},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3230000138282776},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30070000886917114},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.27079999446868896},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2565999925136566}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3743093.3771031","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3743093.3771031","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2512.14050","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.14050","pdf_url":"https://arxiv.org/pdf/2512.14050","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2512.14050","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.14050","pdf_url":"https://arxiv.org/pdf/2512.14050","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417072978.pdf","grobid_xml":"https://content.openalex.org/works/W4417072978.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W1971822075","https://openalex.org/W1981283549","https://openalex.org/W2146835493","https://openalex.org/W2194775991","https://openalex.org/W2343052201","https://openalex.org/W2978036638","https://openalex.org/W3003921261","https://openalex.org/W3128281178","https://openalex.org/W3156669901","https://openalex.org/W3177684257","https://openalex.org/W3204479434","https://openalex.org/W4312879041","https://openalex.org/W4385767840","https://openalex.org/W4405784827"],"related_works":[],"abstract_inverted_index":{"We":[0],"introduce":[1,57],"SELECT":[2,32,128],"(Scene":[3],"tExt":[4],"Label":[5,60],"Errors":[6],"deteCTion),":[7],"a":[8,29,63,85],"novel":[9],"approach":[10],"that":[11,65],"leverages":[12],"multi-modal":[13],"training":[14,71],"to":[15,73,108],"detect":[16,109],"label":[17,40,110,131],"errors":[18,68,111,132],"in":[19,49,87,112,129],"real-world":[20,75,113,138],"scene":[21,114],"text":[22,115,139],"datasets.":[23],"Utilizing":[24],"an":[25],"image-text":[26],"encoder":[27],"and":[28,43,51,133],"character-level":[30,44],"tokenizer,":[31],"addresses":[33],"the":[34,70,88,96,106,125],"issues":[35],"of":[36,127],"variable-length":[37,120],"sequence":[38,41,89],"labels,":[39],"misalignment,":[42],"errors,":[45],"outperforming":[46],"existing":[47],"methods":[48],"accuracy":[50,136],"practical":[52,143],"utility.":[53,144],"In":[54],"addition,":[55],"we":[56],"Similarity-based":[58],"Sequence":[59],"Corruption":[61],"(SSLC),":[62],"process":[64],"intentionally":[66],"introduces":[67],"into":[69,94],"labels":[72],"mimic":[74],"error":[76],"scenarios":[77],"during":[78,101],"training.":[79],"SSLC":[80],"not":[81],"only":[82],"can":[83],"cause":[84],"change":[86],"length":[90],"but":[91],"also":[92],"takes":[93],"account":[95],"visual":[97],"similarity":[98],"between":[99],"characters":[100],"corruption.":[102],"Our":[103],"method":[104],"is":[105],"first":[107],"datasets":[116],"successfully":[117],"accounting":[118],"for":[119],"labels.":[121],"Experimental":[122],"results":[123],"demonstrate":[124],"effectiveness":[126],"detecting":[130],"improving":[134],"STR":[135],"on":[137],"datasets,":[140],"showcasing":[141],"its":[142]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-12-06T00:00:00"}