{"id":"https://openalex.org/W4408353180","doi":"https://doi.org/10.1109/icassp49660.2025.10890127","title":"Polygon Pixel IoU: Similarity Metric between Polygons with Different Number of Vertices for Arbitrary-Shaped Text Spotting","display_name":"Polygon Pixel IoU: Similarity Metric between Polygons with Different Number of Vertices for Arbitrary-Shaped Text Spotting","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353180","doi":"https://doi.org/10.1109/icassp49660.2025.10890127"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890127","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890127","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5017759252","display_name":"Rei Endo","orcid":"https://orcid.org/0000-0003-4254-7736"},"institutions":[{"id":"https://openalex.org/I15905956","display_name":"NHK Spring (Japan)","ror":"https://ror.org/00vse3055","country_code":"JP","type":"company","lineage":["https://openalex.org/I15905956"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Rei Endo","raw_affiliation_strings":["NHK,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NHK,Tokyo,Japan","institution_ids":["https://openalex.org/I15905956"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101904237","display_name":"Taro Miyazaki","orcid":"https://orcid.org/0009-0008-8137-1984"},"institutions":[{"id":"https://openalex.org/I15905956","display_name":"NHK Spring (Japan)","ror":"https://ror.org/00vse3055","country_code":"JP","type":"company","lineage":["https://openalex.org/I15905956"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Taro Miyazaki","raw_affiliation_strings":["NHK,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NHK,Tokyo,Japan","institution_ids":["https://openalex.org/I15905956"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103275319","display_name":"Takahiro Mochizuki","orcid":"https://orcid.org/0009-0009-9576-4700"},"institutions":[{"id":"https://openalex.org/I15905956","display_name":"NHK Spring (Japan)","ror":"https://ror.org/00vse3055","country_code":"JP","type":"company","lineage":["https://openalex.org/I15905956"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takahiro Mochizuki","raw_affiliation_strings":["NHK,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NHK,Tokyo,Japan","institution_ids":["https://openalex.org/I15905956"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103084561","display_name":"Yoshihiko Kawai","orcid":"https://orcid.org/0000-0002-0811-9095"},"institutions":[{"id":"https://openalex.org/I15905956","display_name":"NHK Spring (Japan)","ror":"https://ror.org/00vse3055","country_code":"JP","type":"company","lineage":["https://openalex.org/I15905956"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshihiko Kawai","raw_affiliation_strings":["NHK,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NHK,Tokyo,Japan","institution_ids":["https://openalex.org/I15905956"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I15905956"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03065159,"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":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9976999759674072,"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":0.9891999959945679,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.8288092017173767},{"id":"https://openalex.org/keywords/polygon","display_name":"Polygon (computer graphics)","score":0.7757658958435059},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6102744936943054},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6007257699966431},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.593043863773346},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.49445009231567383},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.4705539047718048},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3929174542427063},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3244038224220276},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3067514896392822},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1944108009338379},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.05873394012451172}],"concepts":[{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.8288092017173767},{"id":"https://openalex.org/C190694206","wikidata":"https://www.wikidata.org/wiki/Q3276654","display_name":"Polygon (computer graphics)","level":3,"score":0.7757658958435059},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6102744936943054},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6007257699966431},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.593043863773346},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.49445009231567383},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.4705539047718048},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3929174542427063},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3244038224220276},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3067514896392822},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1944108009338379},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.05873394012451172},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890127","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890127","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":30,"referenced_works":["https://openalex.org/W2008806374","https://openalex.org/W2144554289","https://openalex.org/W2194187530","https://openalex.org/W2550687635","https://openalex.org/W2618530766","https://openalex.org/W2784050770","https://openalex.org/W2875814315","https://openalex.org/W2962766617","https://openalex.org/W2964018263","https://openalex.org/W2965463054","https://openalex.org/W3003218881","https://openalex.org/W3003868038","https://openalex.org/W3034792612","https://openalex.org/W3035222584","https://openalex.org/W3097779785","https://openalex.org/W3179897446","https://openalex.org/W3181016597","https://openalex.org/W4214922754","https://openalex.org/W4225683503","https://openalex.org/W4304092561","https://openalex.org/W4312230431","https://openalex.org/W4312351507","https://openalex.org/W4312880451","https://openalex.org/W4312988011","https://openalex.org/W4382464147","https://openalex.org/W4386075667","https://openalex.org/W6638500188","https://openalex.org/W6759192466","https://openalex.org/W6770715449","https://openalex.org/W6839019136"],"related_works":["https://openalex.org/W2034439647","https://openalex.org/W3184921334","https://openalex.org/W4249589822","https://openalex.org/W4386895402","https://openalex.org/W2103063669","https://openalex.org/W4380551034","https://openalex.org/W3202382261","https://openalex.org/W2139675209","https://openalex.org/W4255446307","https://openalex.org/W4362466842"],"abstract_inverted_index":{"Existing":[0],"arbitrary-shaped":[1],"text":[2,145],"(ArT)":[3],"spotting":[4,146],"models":[5],"have":[6,39],"used":[7,67],"coordinate-based":[8],"error":[9,82],"(CBE)":[10],"loss":[11,20,78,96,137],"to":[12,113],"optimize":[13],"polygon":[14,33,62,93],"region":[15],"detection.":[16],"Optimization":[17],"using":[18],"CBE":[19,75],"requires":[21],"a":[22,29,122],"fine-grained":[23],"ground":[24],"truth":[25],"(FineGT),":[26],"which":[27,57],"is":[28,44,86,121],"fixed-length":[30],"list":[31],"of":[32,61,92,100,108,117,143],"vertices.":[34,94],"However,":[35],"not":[36,87],"all":[37],"datasets":[38,102],"FineGT,":[40],"and":[41,64,85],"creating":[42],"FineGT":[43],"costly.":[45],"In":[46],"this":[47],"paper,":[48],"we":[49],"propose":[50],"Polygon":[51],"Pixel":[52],"Intersection":[53],"over":[54],"Union":[55],"(PPIoU),":[56],"shows":[58],"the":[59,80,90,98,115,135,141],"similarity":[60],"regions":[63],"can":[65,138],"be":[66],"for":[68,83],"neural":[69],"network":[70],"training":[71,118,127],"without":[72],"FineGT.":[73],"Unlike":[74],"loss,":[76],"PPIoU":[77,95,136],"represents":[79],"region-based":[81],"polygons":[84,104],"affected":[88],"by":[89],"number":[91],"allows":[97],"use":[99],"multiple":[101],"containing":[103],"with":[105],"different":[106],"numbers":[107],"vertices,":[109],"making":[110],"it":[111],"easy":[112],"increase":[114],"amount":[116],"data.":[119],"This":[120],"useful":[123],"feature":[124],"since":[125],"more":[126],"data":[128],"generally":[129],"improves":[130],"accuracy.":[131],"We":[132],"show":[133],"that":[134],"easily":[139],"improve":[140],"accuracy":[142],"existing":[144],"models.":[147]},"counts_by_year":[],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}