{"id":"https://openalex.org/W4309764765","doi":"https://doi.org/10.1145/3572844","title":"Semantic Completion and Filtration for Image\u2013Text Retrieval","display_name":"Semantic Completion and Filtration for Image\u2013Text Retrieval","publication_year":2022,"publication_date":"2022-11-23","ids":{"openalex":"https://openalex.org/W4309764765","doi":"https://doi.org/10.1145/3572844"},"language":"en","primary_location":{"id":"doi:10.1145/3572844","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3572844","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-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/A5101972555","display_name":"Song Soo Yang","orcid":"https://orcid.org/0000-0002-8238-8226"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Song Yang","raw_affiliation_strings":["Tianjin University; China and also with the Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, China"],"raw_orcid":"https://orcid.org/0000-0002-8238-8226","affiliations":[{"raw_affiliation_string":"Tianjin University; China and also with the Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100429894","display_name":"Qiang Li","orcid":"https://orcid.org/0000-0001-7129-1456"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Li","raw_affiliation_strings":["Tianjin University, China"],"raw_orcid":"https://orcid.org/0000-0001-7129-1456","affiliations":[{"raw_affiliation_string":"Tianjin University, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100339851","display_name":"Wenhui Li","orcid":"https://orcid.org/0000-0001-9609-6120"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenhui Li","raw_affiliation_strings":["Tianjin University, China"],"raw_orcid":"https://orcid.org/0000-0001-9609-6120","affiliations":[{"raw_affiliation_string":"Tianjin University, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024121467","display_name":"Xuanya Li","orcid":"https://orcid.org/0000-0002-2227-207X"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuan-Ya Li","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2227-207X","affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102986285","display_name":"Ran Jin","orcid":"https://orcid.org/0000-0001-7113-7838"},"institutions":[{"id":"https://openalex.org/I1315279114","display_name":"Zhejiang Wanli University","ror":"https://ror.org/00rjdhd62","country_code":"CN","type":"education","lineage":["https://openalex.org/I1315279114"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ran Jin","raw_affiliation_strings":["Zhejiang Wanli University, Ningbo, China"],"raw_orcid":"https://orcid.org/0000-0001-7113-7838","affiliations":[{"raw_affiliation_string":"Zhejiang Wanli University, Ningbo, China","institution_ids":["https://openalex.org/I1315279114"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020575658","display_name":"Bo Lv","orcid":"https://orcid.org/0000-0002-2499-0948"},"institutions":[{"id":"https://openalex.org/I2800372957","display_name":"China Electronics Technology Group Corporation","ror":"https://ror.org/0098hst83","country_code":"CN","type":"company","lineage":["https://openalex.org/I2800372957"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Lv","raw_affiliation_strings":["The 30th Research Institute of China Electronics Technology Group Corporation, ChengDu, China"],"raw_orcid":"https://orcid.org/0000-0002-2499-0948","affiliations":[{"raw_affiliation_string":"The 30th Research Institute of China Electronics Technology Group Corporation, ChengDu, China","institution_ids":["https://openalex.org/I2800372957"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100431137","display_name":"Rui Wang","orcid":"https://orcid.org/0000-0001-7274-4525"},"institutions":[{"id":"https://openalex.org/I2800372957","display_name":"China Electronics Technology Group Corporation","ror":"https://ror.org/0098hst83","country_code":"CN","type":"company","lineage":["https://openalex.org/I2800372957"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Wang","raw_affiliation_strings":["The 30th Research Institute of China Electronics Technology Group Corporation, China"],"raw_orcid":"https://orcid.org/0000-0001-7274-4525","affiliations":[{"raw_affiliation_string":"The 30th Research Institute of China Electronics Technology Group Corporation, China","institution_ids":["https://openalex.org/I2800372957"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081485810","display_name":"An-An Liu","orcid":"https://orcid.org/0000-0001-5755-9145"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Anan Liu","raw_affiliation_strings":["Tianjin University; China and also with the Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, China","Tianjin University"],"raw_orcid":"https://orcid.org/0000-0001-5755-9145","affiliations":[{"raw_affiliation_string":"Tianjin University; China and also with the Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"Tianjin University","institution_ids":["https://openalex.org/I162868743"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.972,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.74704762,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"19","issue":"4","first_page":"1","last_page":"20"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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/T11714","display_name":"Multimodal Machine Learning Applications","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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9987999796867371,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.8136624097824097},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6916500926017761},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.639009952545166},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.6346410512924194},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.622724175453186},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6149429082870483},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5719573497772217},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.56903475522995},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.506564736366272},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5034915804862976},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.500096321105957},{"id":"https://openalex.org/keywords/semantic-matching","display_name":"Semantic matching","score":0.44972822070121765},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.4129483103752136},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.1333596408367157},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09338542819023132},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07358580827713013}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8136624097824097},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6916500926017761},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.639009952545166},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.6346410512924194},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.622724175453186},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6149429082870483},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5719573497772217},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.56903475522995},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.506564736366272},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5034915804862976},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.500096321105957},{"id":"https://openalex.org/C2778493491","wikidata":"https://www.wikidata.org/wiki/Q7449072","display_name":"Semantic matching","level":3,"score":0.44972822070121765},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.4129483103752136},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.1333596408367157},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09338542819023132},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07358580827713013},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3572844","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3572844","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7200000286102295}],"awards":[{"id":"https://openalex.org/G1611867576","display_name":null,"funder_award_id":"2022M712369","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G6481249813","display_name":null,"funder_award_id":"U21B2024, 62202327","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1527575280","https://openalex.org/W1916445035","https://openalex.org/W1924770834","https://openalex.org/W1933349210","https://openalex.org/W2186222003","https://openalex.org/W2194775991","https://openalex.org/W2481240925","https://openalex.org/W2568262903","https://openalex.org/W2594785588","https://openalex.org/W2596164567","https://openalex.org/W2606473278","https://openalex.org/W2795389793","https://openalex.org/W2900953995","https://openalex.org/W2948037078","https://openalex.org/W2953369829","https://openalex.org/W2962845008","https://openalex.org/W2963191264","https://openalex.org/W2963467339","https://openalex.org/W2963536419","https://openalex.org/W2964120214","https://openalex.org/W2978826229","https://openalex.org/W2987607708","https://openalex.org/W3006962461","https://openalex.org/W3014367186","https://openalex.org/W3015686016","https://openalex.org/W3072820880","https://openalex.org/W3099614098","https://openalex.org/W3106925514","https://openalex.org/W3115695930","https://openalex.org/W3176763654","https://openalex.org/W4220790454","https://openalex.org/W4242177601","https://openalex.org/W4301409532","https://openalex.org/W4304091481"],"related_works":["https://openalex.org/W2085384747","https://openalex.org/W2106071040","https://openalex.org/W2088166309","https://openalex.org/W4312133475","https://openalex.org/W4238976562","https://openalex.org/W2276587472","https://openalex.org/W4248323080","https://openalex.org/W1986106996","https://openalex.org/W4285012873","https://openalex.org/W2122517733"],"abstract_inverted_index":{"Image\u2013text":[0],"retrieval":[1],"is":[2,105,139],"a":[3,86,109],"vital":[4],"task":[5],"in":[6,51],"computer":[7],"vision":[8],"and":[9,29,36,90,180],"has":[10],"received":[11],"growing":[12],"attention,":[13],"since":[14],"it":[15],"connects":[16],"cross-modality":[17],"data.":[18],"It":[19],"comes":[20],"with":[21,58,78],"the":[22,31,40,59,72,96,100,121,125,133,148,157,163,175,185],"critical":[23],"challenges":[24],"of":[25,61,65,113,127,151,165,187],"learning":[26,162],"unified":[27],"representations":[28],"eliminating":[30],"large":[32],"gap":[33],"between":[34,74],"visual":[35],"textual":[37],"domains.":[38],"Over":[39],"past":[41],"few":[42],"decades,":[43],"although":[44],"many":[45],"works":[46],"have":[47],"made":[48],"significant":[49],"progress":[50],"image\u2013text":[52],"retrieval,":[53],"they":[54],"are":[55],"still":[56],"confronted":[57],"challenge":[60],"incomplete":[62],"text":[63,101,118],"descriptions":[64],"images,":[66],"i.e.,":[67],"how":[68],"to":[69,94,107,123,141,159],"fully":[70],"learn":[71],"correlations":[73,126],"relevant":[75,128],"region\u2013word":[76,129,144,153],"pairs":[77,130,145],"semantic":[79,88,102,111,136],"diversity.":[80],"In":[81],"this":[82],"article,":[83],"we":[84],"propose":[85],"novel":[87],"completion":[89,103],"filtration":[91],"(SCAF)":[92],"method":[93],"alleviate":[95],"above":[97],"issue.":[98],"Specifically,":[99],"module":[104,138],"presented":[106,140],"generate":[108],"complete":[110],"description":[112],"an":[114],"image":[115],"using":[116],"multi-view":[117],"descriptions,":[119],"guiding":[120],"model":[122,158],"explore":[124],"fully.":[131],"Meanwhile,":[132],"adaptive":[134],"structural":[135],"matching":[137,166],"filter":[142],"irrelevant":[143],"by":[146],"considering":[147],"relevance":[149,164],"score":[150],"each":[152],"pair,":[154],"which":[155,183],"facilitates":[156],"focus":[160],"on":[161,178],"pairs.":[167],"Extensive":[168],"experiments":[169],"show":[170],"that":[171],"our":[172,188],"SCAF":[173],"outperforms":[174],"existing":[176],"methods":[177],"Flickr30K":[179],"MSCOCO":[181],"datasets,":[182],"demonstrates":[184],"superiority":[186],"proposed":[189],"method.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}