{"id":"https://openalex.org/W2982121298","doi":"https://doi.org/10.1145/3343031.3351093","title":"You Only Recognize Once","display_name":"You Only Recognize Once","publication_year":2019,"publication_date":"2019-10-15","ids":{"openalex":"https://openalex.org/W2982121298","doi":"https://doi.org/10.1145/3343031.3351093","mag":"2982121298"},"language":"en","primary_location":{"id":"doi:10.1145/3343031.3351093","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3343031.3351093","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM International Conference on Multimedia","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/A5011185036","display_name":"Zhanzhan Cheng","orcid":"https://orcid.org/0000-0002-5732-1513"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhanzhan Cheng","raw_affiliation_strings":["Hikvision Research Institution, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Hikvision Research Institution, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101810007","display_name":"Jing Lu","orcid":"https://orcid.org/0000-0001-7922-9921"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jing Lu","raw_affiliation_strings":["Hikvision Research Institute, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Hikvision Research Institute, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101448949","display_name":"Yi Niu","orcid":"https://orcid.org/0000-0002-7359-276X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi Niu","raw_affiliation_strings":["Hikvision Research Institute, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Hikvision Research Institute, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085955762","display_name":"Shiliang Pu","orcid":"https://orcid.org/0000-0001-5269-7821"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shiliang Pu","raw_affiliation_strings":["Hikvision Research Institute, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Hikvision Research Institute, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004882141","display_name":"Fei Wu","orcid":"https://orcid.org/0000-0003-2139-8807"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Wu","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017862559","display_name":"Shuigeng Zhou","orcid":"https://orcid.org/0000-0002-1949-2768"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuigeng Zhou","raw_affiliation_strings":["Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5011185036"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6196,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.87373213,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"855","last_page":"863"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9955999851226807,"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/T11309","display_name":"Music and Audio Processing","score":0.9922000169754028,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9199895262718201},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8339762091636658},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7139456272125244},{"id":"https://openalex.org/keywords/text-detection","display_name":"Text detection","score":0.6714979410171509},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5823785662651062},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5363733768463135},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5233070850372314},{"id":"https://openalex.org/keywords/text-recognition","display_name":"Text recognition","score":0.4810926616191864},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4797459840774536},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.45643770694732666},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.4305915832519531},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.39553016424179077},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33529770374298096},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.26894426345825195}],"concepts":[{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.9199895262718201},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8339762091636658},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7139456272125244},{"id":"https://openalex.org/C2983589003","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text detection","level":3,"score":0.6714979410171509},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5823785662651062},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5363733768463135},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5233070850372314},{"id":"https://openalex.org/C2983812711","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text recognition","level":3,"score":0.4810926616191864},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4797459840774536},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.45643770694732666},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.4305915832519531},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.39553016424179077},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33529770374298096},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.26894426345825195},{"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3343031.3351093","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3343031.3351093","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8199999928474426,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1821462560","https://openalex.org/W1998384060","https://openalex.org/W2030138018","https://openalex.org/W2127141656","https://openalex.org/W2138621090","https://openalex.org/W2159374016","https://openalex.org/W2163876554","https://openalex.org/W2604735854","https://openalex.org/W2750938222","https://openalex.org/W2798329462","https://openalex.org/W2962986948","https://openalex.org/W2963327605","https://openalex.org/W3106271744","https://openalex.org/W6657827256"],"related_works":["https://openalex.org/W2988098900","https://openalex.org/W4225683503","https://openalex.org/W2949229884","https://openalex.org/W2875814315","https://openalex.org/W4323366758","https://openalex.org/W2982121298","https://openalex.org/W4226291595","https://openalex.org/W3205597380","https://openalex.org/W3005922567","https://openalex.org/W2996956254"],"abstract_inverted_index":{"Video":[0],"text":[1,22,30,33,69,77,87,103,109,111,123,142,150,161,168,174],"spotting":[2,70,151,169],"is":[3],"still":[4],"an":[5,130],"important":[6],"research":[7],"topic":[8],"due":[9],"to":[10],"its":[11],"various":[12],"real-applications.":[13],"Previous":[14],"approaches":[15],"usually":[16],"fall":[17],"into":[18,129],"the":[19,47,54,75,107,116,120,138,148,166,194,203,209],"four-staged":[20],"pipeline:":[21],"detection":[23],"in":[24,89],"individual":[25],"images,":[26],"frame-wisely":[27,81],"recognizing":[28,74,115],"localized":[29,76],"regions,":[31],"tracking":[32],"streams":[34,112],"and":[35,66,113,127,206],"generating":[36],"final":[37],"results":[38],"with":[39,91,202],"complicated":[40],"post-processing":[41],"skills,":[42],"which":[43,134,171],"might":[44],"suffer":[45],"from":[46,110,140,176],"huge":[48],"computational":[49],"cost":[50],"as":[51,53],"well":[52],"interferences":[55,139],"of":[56,80],"low-quality":[57,141],"text.":[58],"In":[59,153],"this":[60],"paper,":[61],"we":[62,84,97,155],"propose":[63],"a":[64,92,101,157],"fast":[65],"robust":[67],"video":[68,149,160,167],"framework":[71],"by":[72,198],"only":[73,114,136],"one-time":[78],"instead":[79],"recognition.":[82],"Specifically,":[83],"first":[85],"obtain":[86],"regions":[88],"videos":[90,175],"well-designed":[93],"spatial-temporal":[94],"detector.":[95],"Then":[96],"concentrate":[98],"on":[99,183],"developing":[100],"novel":[102],"recommender":[104,121],"for":[105,164],"selecting":[106],"highest-quality":[108],"selected":[117],"ones.":[118],"Here,":[119],"assembles":[122],"tracking,":[124],"quality":[125],"scoring":[126],"recognition":[128,195],"end-to-end":[131],"trainable":[132],"module,":[133],"not":[135],"avoids":[137],"but":[143],"also":[144,207],"dramatically":[145],"speeds":[146,192],"up":[147,193],"process.":[152],"addition,":[154],"collect":[156],"larger":[158],"scale":[159],"dataset":[162],"(LSVTD)":[163],"promoting":[165],"community,":[170],"contains":[172],"100":[173],"22":[177],"different":[178],"real-life":[179],"scenarios.":[180],"Extensive":[181],"experiments":[182],"two":[184],"public":[185],"benchmarks":[186],"show":[187],"that":[188],"our":[189],"method":[190],"greatly":[191],"process":[196],"averagely":[197],"71":[199],"times":[200],"compared":[201],"frame-wise":[204],"manner,":[205],"achieves":[208],"remarkable":[210],"state-of-the-art.":[211]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}