{"id":"https://openalex.org/W3015415468","doi":"https://doi.org/10.1109/icassp40776.2020.9054135","title":"A New Perspective for Flexible Feature Gathering in Scene Text Recognition Via Character Anchor Pooling","display_name":"A New Perspective for Flexible Feature Gathering in Scene Text Recognition Via Character Anchor Pooling","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015415468","doi":"https://doi.org/10.1109/icassp40776.2020.9054135","mag":"3015415468"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054135","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054135","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5024174755","display_name":"Shangbang Long","orcid":"https://orcid.org/0000-0002-4089-5369"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shangbang Long","raw_affiliation_strings":["Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065487736","display_name":"Yushuo Guan","orcid":"https://orcid.org/0000-0001-5258-2397"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yushuo Guan","raw_affiliation_strings":["Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064314482","display_name":"Kaigui Bian","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaigui Bian","raw_affiliation_strings":["Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100669593","display_name":"Cong Yao","orcid":"https://orcid.org/0000-0001-6564-4796"},"institutions":[{"id":"https://openalex.org/I4210109870","display_name":"Vi Technology (United States)","ror":"https://ror.org/016mnbp44","country_code":"US","type":"company","lineage":["https://openalex.org/I4210109870"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cong Yao","raw_affiliation_strings":["Megvii (Face++) Technology Inc"],"affiliations":[{"raw_affiliation_string":"Megvii (Face++) Technology Inc","institution_ids":["https://openalex.org/I4210109870"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5024174755"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":1.1724,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.80755529,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":97},"biblio":{"volume":"31","issue":null,"first_page":"2458","last_page":"2462"},"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":0.9933000206947327,"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":0.9902999997138977,"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/pooling","display_name":"Pooling","score":0.7669677734375},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7098127603530884},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.6982026100158691},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.6571981906890869},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6187468767166138},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5919612050056458},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5410650372505188},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.4951874315738678},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.4795893728733063},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.47516578435897827},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.47070810198783875},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44109034538269043},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.42917540669441223},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.41476643085479736},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11113831400871277}],"concepts":[{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.7669677734375},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7098127603530884},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.6982026100158691},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.6571981906890869},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6187468767166138},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5919612050056458},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5410650372505188},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.4951874315738678},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.4795893728733063},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47516578435897827},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.47070810198783875},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44109034538269043},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.42917540669441223},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.41476643085479736},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11113831400871277},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054135","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054135","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W603908379","https://openalex.org/W1491389626","https://openalex.org/W1521064364","https://openalex.org/W1971822075","https://openalex.org/W1981283549","https://openalex.org/W2008806374","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2140132917","https://openalex.org/W2146835493","https://openalex.org/W2194775991","https://openalex.org/W2343052201","https://openalex.org/W2565639579","https://openalex.org/W2740767790","https://openalex.org/W2751748110","https://openalex.org/W2766895242","https://openalex.org/W2768779776","https://openalex.org/W2810028092","https://openalex.org/W2810983211","https://openalex.org/W2899996070","https://openalex.org/W2963233387","https://openalex.org/W2963299604","https://openalex.org/W2963517393","https://openalex.org/W2964308564","https://openalex.org/W2965066169","https://openalex.org/W2997462482","https://openalex.org/W3005436539","https://openalex.org/W3082397598","https://openalex.org/W6600284362","https://openalex.org/W6618372016","https://openalex.org/W6629590909","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6744179516","https://openalex.org/W6746242831","https://openalex.org/W6752486419","https://openalex.org/W6755730432","https://openalex.org/W6772653370"],"related_works":["https://openalex.org/W4237171675","https://openalex.org/W3036286480","https://openalex.org/W3192357901","https://openalex.org/W2387360586","https://openalex.org/W4287027631","https://openalex.org/W2952736415","https://openalex.org/W3209723314","https://openalex.org/W3205398323","https://openalex.org/W2883297582","https://openalex.org/W4390524233"],"abstract_inverted_index":{"Irregular":[0],"scene":[1],"text":[2,20,79,133,147],"recognition":[3,123],"has":[4],"attracted":[5],"much":[6],"attention":[7],"from":[8,67],"the":[9,15,78,98,119],"research":[10],"community,":[11],"mainly":[12],"due":[13],"to":[14,63,70],"complexity":[16],"of":[17,19,49,112],"shapes":[18],"in":[21,80],"natural":[22],"scene.":[23],"However,":[24],"recent":[25],"methods":[26],"either":[27],"rely":[28],"on":[29,129,145],"shape-sensitive":[30],"modules":[31,107],"such":[32],"as":[33,53],"bounding":[34],"box":[35],"regression,":[36],"or":[37],"discard":[38],"sequence":[39,103,116],"learning.":[40,104,117],"To":[41],"tackle":[42],"these":[43],"issues,":[44],"we":[45],"propose":[46],"a":[47,81,109],"pair":[48],"coupling":[50],"modules,":[51,121],"termed":[52],"Character":[54],"Anchoring":[55],"Module":[56,61],"(CAM)":[57],"and":[58,93,115,131,139],"Anchor":[59],"Pooling":[60],"(APM),":[62],"extract":[64],"high-level":[65],"semantics":[66],"two-dimensional":[68],"space":[69],"form":[71],"feature":[72],"sequences.":[73],"The":[74,105],"proposed":[75,120],"CAM":[76],"localizes":[77],"shape-insensitive":[82],"way":[83],"by":[84,86],"design":[85],"anchoring":[87],"characters":[88],"individually.":[89],"APM":[90],"then":[91],"interpolates":[92],"gathers":[94],"features":[95],"flexibly":[96],"along":[97],"character":[99],"anchors":[100],"which":[101],"enables":[102],"complementary":[106],"realize":[108],"harmonic":[110],"unification":[111],"spatial":[113],"information":[114],"With":[118],"our":[122],"system":[124],"surpasses":[125],"previous":[126],"state-of-the-art":[127,143],"scores":[128],"irregular":[130],"perspective":[132],"datasets,":[134],"including,":[135],"ICDAR":[136],"2015,":[137],"CUTE,":[138],"Total-Text,":[140],"while":[141],"paralleling":[142],"performance":[144],"regular":[146],"datasets.":[148]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}