{"id":"https://openalex.org/W4379806304","doi":"https://doi.org/10.1145/3591106.3592214","title":"Learning and Fusing Multi-Scale Representations for Accurate Arbitrary-Shaped Scene Text Recognition","display_name":"Learning and Fusing Multi-Scale Representations for Accurate Arbitrary-Shaped Scene Text Recognition","publication_year":2023,"publication_date":"2023-06-08","ids":{"openalex":"https://openalex.org/W4379806304","doi":"https://doi.org/10.1145/3591106.3592214"},"language":"en","primary_location":{"id":"doi:10.1145/3591106.3592214","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3591106.3592214","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM International Conference on Multimedia Retrieval","raw_type":"proceedings-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/A5101969639","display_name":"Ming-Jun Li","orcid":"https://orcid.org/0009-0008-8831-1191"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Mingjun Li","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101921675","display_name":"Shuo Xu","orcid":"https://orcid.org/0009-0003-1394-3550"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuo Xu","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006378862","display_name":"Feng Su","orcid":"https://orcid.org/0000-0002-8426-9634"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Su","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101969639"],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05198902,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"353","last_page":"361"},"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9891999959945679,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9866999983787537,"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/computer-science","display_name":"Computer science","score":0.7394264340400696},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6857131123542786},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6445006728172302},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.6004897356033325},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5601814389228821},{"id":"https://openalex.org/keywords/text-recognition","display_name":"Text recognition","score":0.5269861221313477},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5060243010520935},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4811598062515259},{"id":"https://openalex.org/keywords/text-detection","display_name":"Text detection","score":0.4463038146495819},{"id":"https://openalex.org/keywords/noisy-text-analytics","display_name":"Noisy text analytics","score":0.42198002338409424},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4189390540122986},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.40173226594924927},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.32929229736328125},{"id":"https://openalex.org/keywords/text-graph","display_name":"Text graph","score":0.31718912720680237},{"id":"https://openalex.org/keywords/text-mining","display_name":"Text mining","score":0.2617053687572479}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7394264340400696},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6857131123542786},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6445006728172302},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.6004897356033325},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5601814389228821},{"id":"https://openalex.org/C2983812711","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text recognition","level":3,"score":0.5269861221313477},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5060243010520935},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4811598062515259},{"id":"https://openalex.org/C2983589003","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text detection","level":3,"score":0.4463038146495819},{"id":"https://openalex.org/C151375590","wikidata":"https://www.wikidata.org/wiki/Q17147076","display_name":"Noisy text analytics","level":4,"score":0.42198002338409424},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4189390540122986},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.40173226594924927},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32929229736328125},{"id":"https://openalex.org/C66945725","wikidata":"https://www.wikidata.org/wiki/Q18388823","display_name":"Text graph","level":3,"score":0.31718912720680237},{"id":"https://openalex.org/C71472368","wikidata":"https://www.wikidata.org/wiki/Q676880","display_name":"Text mining","level":2,"score":0.2617053687572479},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3591106.3592214","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3591106.3592214","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM International Conference on Multimedia Retrieval","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":23,"referenced_works":["https://openalex.org/W1922126009","https://openalex.org/W1971822075","https://openalex.org/W1981283549","https://openalex.org/W2042243448","https://openalex.org/W2061802763","https://openalex.org/W2122221966","https://openalex.org/W2127141656","https://openalex.org/W2194187530","https://openalex.org/W2341629100","https://openalex.org/W2344822769","https://openalex.org/W2810983211","https://openalex.org/W2963233387","https://openalex.org/W2963526661","https://openalex.org/W2963712589","https://openalex.org/W2965066169","https://openalex.org/W2970910956","https://openalex.org/W2997749585","https://openalex.org/W2998382406","https://openalex.org/W3034414401","https://openalex.org/W3110267192","https://openalex.org/W3204778874","https://openalex.org/W4312298799","https://openalex.org/W6600804061"],"related_works":["https://openalex.org/W4312663241","https://openalex.org/W2152349655","https://openalex.org/W3180286081","https://openalex.org/W4387968327","https://openalex.org/W4297798696","https://openalex.org/W3046446809","https://openalex.org/W2987600763","https://openalex.org/W4312115774","https://openalex.org/W2970910956","https://openalex.org/W3034105996"],"abstract_inverted_index":{"Scene":[0],"text":[1,25,38,49,63,72,88,111,140,145,154,161],"in":[2,50,159],"natural":[3],"images":[4],"carries":[5],"a":[6,27,76,105],"wealth":[7],"of":[8,19,48,62,78,86,133,162],"valuable":[9],"semantic":[10],"information,":[11],"while":[12],"due":[13],"to":[14],"the":[15,20,51,87,116,134,139],"largely":[16],"varied":[17],"appearance":[18,84],"text,":[21,135],"accurately":[22],"recognizing":[23,160],"scene":[24,37,153],"is":[26],"challenging":[28],"task.":[29],"In":[30],"this":[31],"work,":[32],"we":[33,74],"propose":[34],"an":[35,70,130],"arbitrary-shaped":[36],"recognition":[39,141,146],"method":[40,147],"based":[41],"on":[42,151],"learning":[43],"and":[44,121,125],"fusing":[45],"multiple":[46,90],"representations":[47,80,118],"scale":[52,96],"space":[53],"with":[54,93,109,119],"attention":[55,123],"mechanisms.":[56],"Specifically,":[57],"as":[58,104],"distinctive":[59],"visual":[60],"features":[61,103],"often":[64],"appear":[65],"at":[66],"different":[67],"scales,":[68],"given":[69],"input":[71],"image,":[73],"generate":[75],"family":[77],"multi-scale":[79,117],"that":[81],"capture":[82],"complementary":[83],"characteristics":[85],"through":[89],"encoder":[91],"branches":[92],"progressively":[94],"increasing":[95],"parameters.":[97],"We":[98,113],"further":[99],"introduce":[100],"edge":[101],"map":[102],"supplementary":[106],"high-frequency":[107],"representation":[108,132],"useful":[110],"cues.":[112],"then":[114],"refine":[115],"in-scale":[120],"cross-scale":[122],"mechanisms":[124],"adaptively":[126],"aggregate":[127],"them":[128],"into":[129],"enhanced":[131],"which":[136],"effectively":[137],"improves":[138],"accuracy.":[142],"The":[143],"proposed":[144],"achieves":[148],"competitive":[149],"results":[150],"several":[152],"benchmarks,":[155],"demonstrating":[156],"its":[157],"effectiveness":[158],"various":[163],"shapes.":[164]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}