{"id":"https://openalex.org/W4403792358","doi":"https://doi.org/10.1145/3664647.3680981","title":"DNTextSpotter: Arbitrary-Shaped Scene Text Spotting via Improved Denoising Training","display_name":"DNTextSpotter: Arbitrary-Shaped Scene Text Spotting via Improved Denoising Training","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403792358","doi":"https://doi.org/10.1145/3664647.3680981"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3680981","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680981","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd 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/A5018143356","display_name":"Qian Qiao","orcid":"https://orcid.org/0009-0005-6154-1411"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qian Qiao","raw_affiliation_strings":["School of Computer Science and Technology, Soochow University & bilibili Inc., Suzhou, Jiangsu, China"],"raw_orcid":"https://orcid.org/0009-0005-6154-1411","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Soochow University & bilibili Inc., Suzhou, Jiangsu, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100992291","display_name":"Yu Xie","orcid":"https://orcid.org/0009-0007-1695-9370"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Xie","raw_affiliation_strings":["School of Computer Science and Technology, Soochow University & bilibili Inc., Suzhou, Jiangsu, China"],"raw_orcid":"https://orcid.org/0009-0007-1695-9370","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Soochow University & bilibili Inc., Suzhou, Jiangsu, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112146859","display_name":"Jun Gao","orcid":"https://orcid.org/0009-0004-1287-7472"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jun Gao","raw_affiliation_strings":["The Hong Kong Polytechnic University, Hongkong, China"],"raw_orcid":"https://orcid.org/0009-0004-1287-7472","affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University, Hongkong, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tianxiang Wu","orcid":"https://orcid.org/0009-0009-4712-1241"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianxiang Wu","raw_affiliation_strings":["School of Computer Science and Technology, Soochow University, Suzhou, Jiangsu, China"],"raw_orcid":"https://orcid.org/0009-0009-4712-1241","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Soochow University, Suzhou, Jiangsu, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109788089","display_name":"Shaoyao Huang","orcid":"https://orcid.org/0009-0004-7676-8830"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaoyao Huang","raw_affiliation_strings":["School of Computer Science and Technology, Soochow University, Suzhou, Jiangsu, China"],"raw_orcid":"https://orcid.org/0009-0004-7676-8830","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Soochow University, Suzhou, Jiangsu, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102866341","display_name":"Jiaqing Fan","orcid":"https://orcid.org/0000-0001-5659-7457"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaqing Fan","raw_affiliation_strings":["School of Computer Science and Technology, Soochow University, Suzhou, Jiangsu, China"],"raw_orcid":"https://orcid.org/0000-0001-5659-7457","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Soochow University, Suzhou, Jiangsu, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102007730","display_name":"Ziqiang Cao","orcid":"https://orcid.org/0000-0002-1077-9033"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziqiang Cao","raw_affiliation_strings":["School of Computer Science and Technology, Soochow University, Suzhou, Jiangsu, China"],"raw_orcid":"https://orcid.org/0000-0002-1077-9033","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Soochow University, Suzhou, Jiangsu, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zili Wang","orcid":"https://orcid.org/0009-0008-5266-8367"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zili Wang","raw_affiliation_strings":["Inf Tech, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0008-5266-8367","affiliations":[{"raw_affiliation_string":"Inf Tech, Shanghai, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5104184190","display_name":"Yue Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Zhang","raw_affiliation_strings":["School of Computer Science and Technology, Soochow University, Suzhou, Jiangsu, China"],"raw_orcid":"https://orcid.org/0009-0003-5936-6410","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Soochow University, Suzhou, Jiangsu, China","institution_ids":["https://openalex.org/I3923682"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10134","last_page":"10143"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9975000023841858,"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":0.9522877931594849},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.7297728061676025},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7172341346740723},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6639758348464966},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6602996587753296},{"id":"https://openalex.org/keywords/image-denoising","display_name":"Image denoising","score":0.560834527015686},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5593817234039307},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4554142951965332},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.431810200214386},{"id":"https://openalex.org/keywords/video-denoising","display_name":"Video denoising","score":0.43134206533432007},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06887879967689514},{"id":"https://openalex.org/keywords/video-processing","display_name":"Video processing","score":0.0443284809589386}],"concepts":[{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.9522877931594849},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.7297728061676025},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7172341346740723},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6639758348464966},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6602996587753296},{"id":"https://openalex.org/C2983327147","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Image denoising","level":3,"score":0.560834527015686},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5593817234039307},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4554142951965332},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.431810200214386},{"id":"https://openalex.org/C30814859","wikidata":"https://www.wikidata.org/wiki/Q4119603","display_name":"Video denoising","level":5,"score":0.43134206533432007},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06887879967689514},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.0443284809589386},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.0},{"id":"https://openalex.org/C23431618","wikidata":"https://www.wikidata.org/wiki/Q1404672","display_name":"Multiview Video Coding","level":4,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3680981","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680981","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1536680647","https://openalex.org/W2127141656","https://openalex.org/W2128409098","https://openalex.org/W2135231474","https://openalex.org/W2875814315","https://openalex.org/W2914492226","https://openalex.org/W2964018263","https://openalex.org/W2964296749","https://openalex.org/W2965463054","https://openalex.org/W2970910956","https://openalex.org/W2983626510","https://openalex.org/W2988098900","https://openalex.org/W2996956254","https://openalex.org/W2997371611","https://openalex.org/W3034792612","https://openalex.org/W3035106683","https://openalex.org/W3082397598","https://openalex.org/W3096609285","https://openalex.org/W3134064484","https://openalex.org/W3138516171","https://openalex.org/W3157738407","https://openalex.org/W3159307593","https://openalex.org/W3161679556","https://openalex.org/W3196976036","https://openalex.org/W4214614183","https://openalex.org/W4214627427","https://openalex.org/W4225683503","https://openalex.org/W4226041419","https://openalex.org/W4304084026","https://openalex.org/W4304091583","https://openalex.org/W4312230431","https://openalex.org/W4312312588","https://openalex.org/W4312351507","https://openalex.org/W4312769131","https://openalex.org/W4312880451","https://openalex.org/W4315705623","https://openalex.org/W4384519125","https://openalex.org/W4386075667","https://openalex.org/W4386075746","https://openalex.org/W4390874051"],"related_works":["https://openalex.org/W4287081060","https://openalex.org/W2791234060","https://openalex.org/W1538114257","https://openalex.org/W2541197080","https://openalex.org/W1974034585","https://openalex.org/W2810018092","https://openalex.org/W2098237619","https://openalex.org/W2035842925","https://openalex.org/W2912242094","https://openalex.org/W2360732716"],"abstract_inverted_index":{"More":[0],"and":[1,31,96,132,199,235],"more":[2,97],"end-to-end":[3],"text":[4,83,99,118,165,197],"spotting":[5,84],"methods":[6,16,229],"based":[7],"on":[8,230,246],"Transformer":[9],"architecture":[10],"have":[11],"demonstrated":[12],"superior":[13],"performance.":[14],"These":[15],"utilize":[17,212],"a":[18,110,167,181],"bipartite":[19,38,65],"graph":[20,39,66],"matching":[21,27,40,67],"algorithm":[22],"to":[23,43,60,82,90,148,174,186,202],"perform":[24,91],"one-to-one":[25],"optimal":[26],"between":[28],"predicted":[29],"objects":[30],"actual":[32],"objects.":[33],"However,":[34],"the":[35,49,53,62,123,126,138,144,150,155,161,164,194,204,208,222,243],"instability":[36,68],"of":[37,52,64,125,143,163,196,207],"can":[41],"lead":[42],"inconsistent":[44],"optimization":[45],"targets,":[46],"thereby":[47,191],"affecting":[48],"training":[50,59,76,113,224],"performance":[51],"model.":[54],"Existing":[55],"literature":[56],"applies":[57],"denoising":[58,75,112,127,223],"solve":[61],"problem":[63],"in":[69,166,193,221],"object":[70],"detection":[71,94],"tasks.":[72],"Unfortunately,":[73],"this":[74,106],"method":[77,114,185],"cannot":[78],"be":[79],"directly":[80],"applied":[81],"tasks,":[85],"as":[86],"these":[87],"tasks":[88,95,101],"need":[89],"irregular":[92],"shape":[93],"complex":[98],"recognition":[100],"than":[102],"classification.":[103],"To":[104],"address":[105],"issue,":[107],"we":[108,121,179,210],"propose":[109],"novel":[111],"(DNTextSpotter)":[115],"for":[116,217],"arbitrary-shaped":[117],"spotting.":[119],"Specifically,":[120],"decompose":[122],"queries":[124],"part":[128],"into":[129],"noised":[130,133,151,156,188],"positional":[131,152,169],"content":[134,157,189,198],"queries.":[135,153],"We":[136],"use":[137],"four":[139,231],"Bezier":[140,145],"control":[141],"points":[142],"center":[146],"curve":[147],"generate":[149],"For":[154],"queries,":[158,190],"considering":[159],"that":[160],"output":[162],"fixed":[168],"order":[170],"is":[171],"not":[172],"conducive":[173],"aligning":[175],"position":[176],"with":[177],"content,":[178],"employ":[180],"masked":[182],"character":[183],"sliding":[184],"initialize":[187],"assisting":[192],"alignment":[195],"position.":[200],"Additionally,":[201],"improve":[203],"model's":[205],"perception":[206],"background,":[209],"further":[211],"an":[213,239],"additional":[214],"loss":[215],"function":[216],"background":[218],"characters":[219],"classification":[220],"part.":[225],"DNTextSpotter":[226],"outperforms":[227],"state-of-the-art":[228],"benchmarks-Total-Text,":[232],"SCUT-CTW1500,":[233],"ICDAR15,":[234],"Inverse-Text-most":[236],"notably":[237],"achieving":[238],"11.3%":[240],"improvement":[241],"over":[242],"best":[244],"approach":[245],"Inverse-Text.":[247]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}