{"id":"https://openalex.org/W7123349412","doi":"https://doi.org/10.1109/mmul.2026.3652839","title":"Toward Improving Arbitrary-Shaped Text Detection With Boundary Adaptation in Noisy Scene Images","display_name":"Toward Improving Arbitrary-Shaped Text Detection With Boundary Adaptation in Noisy Scene Images","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7123349412","doi":"https://doi.org/10.1109/mmul.2026.3652839"},"language":null,"primary_location":{"id":"doi:10.1109/mmul.2026.3652839","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmul.2026.3652839","pdf_url":null,"source":{"id":"https://openalex.org/S72873717","display_name":"IEEE Multimedia","issn_l":"1070-986X","issn":["1070-986X","1941-0166"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 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":"Aishwarya Soni","orcid":"https://orcid.org/0009-0004-5667-9419"},"institutions":[{"id":"https://openalex.org/I56404289","display_name":"Indian Institute of Technology BHU","ror":"https://ror.org/01kh5gc44","country_code":"IN","type":"education","lineage":["https://openalex.org/I56404289","https://openalex.org/I91357014"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Aishwarya Soni","raw_affiliation_strings":["Indian Institute of Technology, Varanasi, India"],"raw_orcid":"https://orcid.org/0009-0004-5667-9419","affiliations":[{"raw_affiliation_string":"Indian Institute of Technology, Varanasi, India","institution_ids":["https://openalex.org/I56404289"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088215863","display_name":"Tanima Dutta","orcid":"https://orcid.org/0000-0002-2801-0687"},"institutions":[{"id":"https://openalex.org/I56404289","display_name":"Indian Institute of Technology BHU","ror":"https://ror.org/01kh5gc44","country_code":"IN","type":"education","lineage":["https://openalex.org/I56404289","https://openalex.org/I91357014"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Tanima Dutta","raw_affiliation_strings":["Indian Institute of Technology, Varanasi, India"],"raw_orcid":"https://orcid.org/0000-0002-2801-0687","affiliations":[{"raw_affiliation_string":"Indian Institute of Technology, Varanasi, India","institution_ids":["https://openalex.org/I56404289"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":16.7524,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.96656441,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"33","issue":"1","first_page":"7","last_page":"20"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.904699981212616,"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":0.904699981212616,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.014399999752640724,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.010099999606609344,"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/robustness","display_name":"Robustness (evolution)","score":0.8361999988555908},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.7202000021934509},{"id":"https://openalex.org/keywords/boundary","display_name":"Boundary (topology)","score":0.5115000009536743},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48190000653266907},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4690999984741211},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.43849998712539673},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.361299991607666},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.34299999475479126}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8374000191688538},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.8361999988555908},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7396000027656555},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.7202000021934509},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7041000127792358},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.5115000009536743},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48190000653266907},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4690999984741211},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.43849998712539673},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.361299991607666},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.34299999475479126},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.30469998717308044},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.299699991941452},{"id":"https://openalex.org/C40069579","wikidata":"https://www.wikidata.org/wiki/Q62494","display_name":"Polar coordinate system","level":2,"score":0.29679998755455017},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.29420000314712524},{"id":"https://openalex.org/C112353826","wikidata":"https://www.wikidata.org/wiki/Q127313","display_name":"Active contour model","level":4,"score":0.2831999957561493},{"id":"https://openalex.org/C193536780","wikidata":"https://www.wikidata.org/wiki/Q1513153","display_name":"Edge detection","level":4,"score":0.2660999894142151},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2581000030040741},{"id":"https://openalex.org/C150140777","wikidata":"https://www.wikidata.org/wiki/Q960648","display_name":"Point of interest","level":2,"score":0.2578999996185303}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mmul.2026.3652839","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmul.2026.3652839","pdf_url":null,"source":{"id":"https://openalex.org/S72873717","display_name":"IEEE Multimedia","issn_l":"1070-986X","issn":["1070-986X","1941-0166"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Accurate":[0],"detection":[1],"of":[2,37,140,152],"arbitrary-shaped":[3],"text":[4,89],"in":[5,56,81],"natural":[6],"scenes":[7],"remains":[8],"a":[9,50,61,82,95,109],"challenging":[10],"problem,":[11],"particularly":[12],"under":[13],"real-world":[14],"noise":[15],"conditions":[16],"such":[17],"as":[18],"blur,":[19],"occlusion,":[20],"uneven":[21],"lighting,":[22],"and":[23,31,70,133,150],"cluttered":[24],"backgrounds.":[25],"These":[26,91],"factors":[27],"degrade":[28],"local":[29,88],"features":[30,69],"boundary":[32,54,117],"precision,":[33],"hindering":[34],"the":[35,148],"performance":[36],"existing":[38],"contour-based":[39],"methods.":[40],"To":[41],"address":[42],"this,":[43],"we":[44,107],"propose":[45],"Ray":[46],"Contour":[47,73],"Net":[48],"(RC-Net),":[49],"robust":[51],"framework":[52],"for":[53],"adaptation":[55],"noisy":[57],"environments.":[58],"RC-Net":[59],"incorporates":[60],"Noise-":[62],"Aware":[63],"Attention":[64],"Module":[65,76,97],"to":[66,101,114,142],"obtain":[67],"noise-robust":[68],"an":[71],"Active":[72],"Point":[74],"Initialization":[75],"that":[77],"emits":[78],"contour":[79],"points":[80],"polar":[83],"coordinate":[84],"system":[85],"anchored":[86],"at":[87],"centers.":[90],"are":[92],"refined":[93],"by":[94],"Deformation":[96],"using":[98],"lightweight":[99],"transformers":[100],"ensure":[102],"shape-aware,":[103],"noise-tolerant":[104],"adaptation.":[105],"Additionally,":[106],"introduce":[108],"Tightness":[110],"Evaluation":[111],"Loss":[112],"(TEL)":[113],"enforce":[115],"precise":[116],"predictions.":[118],"Extensive":[119],"experiments":[120],"on":[121],"six":[122],"benchmark":[123],"datasets":[124],"including":[125],"Total-Text,":[126],"CTW-1500,":[127],"MSRATD500,":[128],"ICDAR":[129],"2015,":[130],"ICDAR2019":[131,134],"ArT,":[132],"MLT":[135],"demonstrate":[136],"consistent":[137],"F-measure":[138],"improvements":[139],"2%":[141],"3%":[143],"over":[144],"strong":[145],"baselines,":[146],"validating":[147],"effectiveness":[149],"robustness":[151],"our":[153],"method.":[154]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-16T09:24:06.705377","created_date":"2026-01-14T00:00:00"}