{"id":"https://openalex.org/W3160791979","doi":"https://doi.org/10.1109/icassp39728.2021.9414739","title":"Pointer Networks for Arbitrary-Shaped Text Spotting","display_name":"Pointer Networks for Arbitrary-Shaped Text Spotting","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3160791979","doi":"https://doi.org/10.1109/icassp39728.2021.9414739","mag":"3160791979"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414739","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414739","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/A5100388161","display_name":"Yi Zhang","orcid":"https://orcid.org/0000-0002-4217-029X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yi Zhang","raw_affiliation_strings":["University of Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100709268","display_name":"Wei Yang","orcid":"https://orcid.org/0000-0003-0178-7135"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Yang","raw_affiliation_strings":["University of Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021459992","display_name":"Zhenbo Xu","orcid":"https://orcid.org/0000-0002-8948-1589"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenbo Xu","raw_affiliation_strings":["University of Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100425060","display_name":"Yingjie Li","orcid":"https://orcid.org/0000-0001-7526-0120"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingjie Li","raw_affiliation_strings":["University of Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100622018","display_name":"Zhi Chen","orcid":"https://orcid.org/0000-0002-4385-1484"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhi Chen","raw_affiliation_strings":["University of Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019604942","display_name":"Liusheng Huang","orcid":"https://orcid.org/0000-0001-8417-3256"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liusheng Huang","raw_affiliation_strings":["University of Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100388161"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.2882,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.53905229,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2375","last_page":"2379"},"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/T12707","display_name":"Vehicle License Plate Recognition","score":0.9954000115394592,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"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":0.9902999997138977,"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":0.8963718414306641},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8403240442276001},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.5633209347724915},{"id":"https://openalex.org/keywords/offset","display_name":"Offset (computer science)","score":0.5048697590827942},{"id":"https://openalex.org/keywords/pointer","display_name":"Pointer (user interface)","score":0.48441818356513977},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4829823076725006},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.43404683470726013},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36987924575805664},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3374365568161011},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3263727128505707},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1717066466808319}],"concepts":[{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.8963718414306641},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8403240442276001},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.5633209347724915},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.5048697590827942},{"id":"https://openalex.org/C150202949","wikidata":"https://www.wikidata.org/wiki/Q107602","display_name":"Pointer (user interface)","level":2,"score":0.48441818356513977},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4829823076725006},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.43404683470726013},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36987924575805664},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3374365568161011},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3263727128505707},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1717066466808319},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414739","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414739","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7300000190734863,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1922126009","https://openalex.org/W2144554289","https://openalex.org/W2194775991","https://openalex.org/W2343052201","https://openalex.org/W2550687635","https://openalex.org/W2565639579","https://openalex.org/W2605076167","https://openalex.org/W2777652944","https://openalex.org/W2875814315","https://openalex.org/W2962773189","https://openalex.org/W2962810613","https://openalex.org/W2963150697","https://openalex.org/W2963299604","https://openalex.org/W2964018263","https://openalex.org/W2964296749","https://openalex.org/W2970971581","https://openalex.org/W2981969038","https://openalex.org/W2982770724","https://openalex.org/W2983626510","https://openalex.org/W2996956254","https://openalex.org/W3034792612","https://openalex.org/W4295312788","https://openalex.org/W6729791593","https://openalex.org/W6760947256","https://openalex.org/W6766978945","https://openalex.org/W6774238520"],"related_works":["https://openalex.org/W2034439647","https://openalex.org/W4249589822","https://openalex.org/W2103063669","https://openalex.org/W3184921334","https://openalex.org/W4255446307","https://openalex.org/W2033009170","https://openalex.org/W2988098900","https://openalex.org/W4386895402","https://openalex.org/W3202382261","https://openalex.org/W2387857478"],"abstract_inverted_index":{"Current":[0],"text":[1,5,8,26,55,65],"spotting":[2],"methods":[3,123],"perform":[4],"detection":[6,27,33,66],"and":[7,37,67,117],"recognition":[9],"separately.":[10],"However,":[11],"in":[12],"complex":[13],"scenes":[14],"where":[15],"bounding":[16],"boxes":[17],"of":[18,98,105],"texts":[19],"with":[20,128],"various":[21],"shapes":[22],"are":[23],"often":[24],"overlapped,":[25],"becomes":[28],"error-prone.":[29],"By":[30],"contrast,":[31],"character":[32,101],"is":[34,118],"more":[35,119],"non-ambiguous":[36],"easier":[38],"to":[39,75,78,102],"learn.":[40],"In":[41,73],"this":[42],"paper,":[43],"we":[44,80],"present":[45],"a":[46,69,82],"highly":[47,85],"efficient":[48,120],"one-stage":[49],"method":[50],"named":[51,88],"PointerNet":[52,60,113],"for":[53],"arbitrary-shaped":[54],"spotting.":[56],"Unlike":[57],"previous":[58],"methods,":[59],"does":[61],"not":[62],"rely":[63],"on":[64],"opens":[68],"novel":[70],"spotting-by-character-detection":[71],"paradigm.":[72],"particular,":[74],"connect":[76],"characters":[77],"texts,":[79],"propose":[81],"simple":[83],"yet":[84],"effective":[86],"strategy":[87],"pointer":[89],"that":[90,111],"learns":[91],"the":[92,96,99,103,106],"2D":[93],"offset":[94],"from":[95],"center":[97,104],"current":[100,122],"subsequent":[107],"character.":[108],"Evaluations":[109],"demonstrate":[110],"our":[112],"achieves":[114],"state-of-the-art":[115],"performance":[116],"than":[121],"(75ms":[124],"vs.":[125],"133ms":[126],"compared":[127],"FOTS).":[129],"Our":[130],"code":[131],"will":[132],"be":[133],"publicly":[134],"available.":[135]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}