{"id":"https://openalex.org/W4408209781","doi":"https://doi.org/10.1007/s44267-025-00073-2","title":"Efficient text-to-video retrieval via multi-modal multi-tagger derived pre-screening","display_name":"Efficient text-to-video retrieval via multi-modal multi-tagger derived pre-screening","publication_year":2025,"publication_date":"2025-03-06","ids":{"openalex":"https://openalex.org/W4408209781","doi":"https://doi.org/10.1007/s44267-025-00073-2"},"language":"en","primary_location":{"id":"doi:10.1007/s44267-025-00073-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44267-025-00073-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44267-025-00073-2.pdf","source":{"id":"https://openalex.org/S4387289164","display_name":"Visual Intelligence","issn_l":"2731-9008","issn":["2731-9008","2097-3330"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Visual Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://link.springer.com/content/pdf/10.1007/s44267-025-00073-2.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113331236","display_name":"Yingjia Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingjia Xu","raw_affiliation_strings":["School of Computer Science & Technology, Soochow University, Suzhou, 215006, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science & Technology, Soochow University, Suzhou, 215006, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101263078","display_name":"Mengxia Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengxia Wu","raw_affiliation_strings":["School of Computer Science & Technology, Soochow University, Suzhou, 215006, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science & Technology, Soochow University, Suzhou, 215006, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100329593","display_name":"Zixin Guo","orcid":"https://orcid.org/0009-0009-4093-6966"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Zixin Guo","raw_affiliation_strings":["Department of Computer Science, Aalto University, Espoo, 02150, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Aalto University, Espoo, 02150, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111346891","display_name":"Min Cao","orcid":"https://orcid.org/0000-0002-6628-0370"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Min Cao","raw_affiliation_strings":["School of Computer Science & Technology, Soochow University, Suzhou, 215006, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science & Technology, Soochow University, Suzhou, 215006, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008999954","display_name":"Mang Ye","orcid":"https://orcid.org/0000-0003-3989-7655"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mang Ye","raw_affiliation_strings":["School of Computer Science, Wuhan University, Wuhan, 430072, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Wuhan University, Wuhan, 430072, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036133390","display_name":"Jorma Laaksonen","orcid":"https://orcid.org/0000-0001-7218-3131"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Jorma Laaksonen","raw_affiliation_strings":["Department of Computer Science, Aalto University, Espoo, 02150, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Aalto University, Espoo, 02150, Finland","institution_ids":["https://openalex.org/I9927081"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5111346891"],"corresponding_institution_ids":["https://openalex.org/I3923682"],"apc_list":null,"apc_paid":null,"fwci":5.3587,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.95713516,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"3","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9998000264167786,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9998000264167786,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"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":0.9994000196456909,"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/computer-science","display_name":"Computer science","score":0.8812093734741211},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6893783211708069},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.6033974289894104},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5524126291275024},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5176703929901123},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.47848767042160034},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42390745878219604},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4148370623588562},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3394291400909424},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3289076089859009},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.16077184677124023}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8812093734741211},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6893783211708069},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.6033974289894104},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5524126291275024},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5176703929901123},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.47848767042160034},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42390745878219604},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4148370623588562},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3394291400909424},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3289076089859009},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.16077184677124023},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/s44267-025-00073-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44267-025-00073-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44267-025-00073-2.pdf","source":{"id":"https://openalex.org/S4387289164","display_name":"Visual Intelligence","issn_l":"2731-9008","issn":["2731-9008","2097-3330"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Visual Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/134799","is_oa":true,"landing_page_url":"http://www.scopus.com/inward/record.url?scp=86000322742&partnerID=8YFLogxK","pdf_url":null,"source":{"id":"https://openalex.org/S4306401663","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:doaj.org/article:7df0e7f4e6924701b623e17654f88029","is_oa":true,"landing_page_url":"https://doaj.org/article/7df0e7f4e6924701b623e17654f88029","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Visual Intelligence, Vol 3, Iss 1, Pp 1-13 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s44267-025-00073-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44267-025-00073-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44267-025-00073-2.pdf","source":{"id":"https://openalex.org/S4387289164","display_name":"Visual Intelligence","issn_l":"2731-9008","issn":["2731-9008","2097-3330"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Visual Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5299999713897705,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G4706251453","display_name":"Understanding speech and scene with ears and eyes","funder_award_id":"345791","funder_id":"https://openalex.org/F4320321108","funder_display_name":"Academy of Finland"},{"id":"https://openalex.org/G6781587187","display_name":null,"funder_award_id":"62476188","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8994705204","display_name":null,"funder_award_id":"345791","funder_id":"https://openalex.org/F4320321108","funder_display_name":"Academy of Finland"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321108","display_name":"Academy of Finland","ror":"https://ror.org/05k73zm37"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4408209781.pdf"},"referenced_works_count":61,"referenced_works":["https://openalex.org/W142212369","https://openalex.org/W1583837637","https://openalex.org/W1858013062","https://openalex.org/W2027179862","https://openalex.org/W2138118304","https://openalex.org/W2138662031","https://openalex.org/W2425121537","https://openalex.org/W2526417872","https://openalex.org/W2544860310","https://openalex.org/W2602856279","https://openalex.org/W2604292070","https://openalex.org/W2745461083","https://openalex.org/W2753311918","https://openalex.org/W2914304175","https://openalex.org/W2925419377","https://openalex.org/W2965458216","https://openalex.org/W2968848930","https://openalex.org/W2981716253","https://openalex.org/W3007938835","https://openalex.org/W3025665229","https://openalex.org/W3035309251","https://openalex.org/W3092470998","https://openalex.org/W3094502228","https://openalex.org/W3100255860","https://openalex.org/W3102887392","https://openalex.org/W3127384563","https://openalex.org/W3135517121","https://openalex.org/W3145807616","https://openalex.org/W3150558292","https://openalex.org/W4221167445","https://openalex.org/W4224875144","https://openalex.org/W4225414521","https://openalex.org/W4225832925","https://openalex.org/W4226182655","https://openalex.org/W4231934124","https://openalex.org/W4236965008","https://openalex.org/W4244061993","https://openalex.org/W4285606530","https://openalex.org/W4289537403","https://openalex.org/W4294691145","https://openalex.org/W4296151206","https://openalex.org/W4301409532","https://openalex.org/W4304014690","https://openalex.org/W4313483475","https://openalex.org/W4321606587","https://openalex.org/W4361229284","https://openalex.org/W4380303571","https://openalex.org/W4385573289","https://openalex.org/W4386907270","https://openalex.org/W4389352609","https://openalex.org/W4389712774","https://openalex.org/W4390529298","https://openalex.org/W4390871725","https://openalex.org/W4392908910","https://openalex.org/W4402670332","https://openalex.org/W6631190155","https://openalex.org/W6670161514","https://openalex.org/W6780924892","https://openalex.org/W6792712899","https://openalex.org/W6808848689","https://openalex.org/W6983682869"],"related_works":["https://openalex.org/W2159024673","https://openalex.org/W2787993192","https://openalex.org/W3001987467","https://openalex.org/W2968165261","https://openalex.org/W2062195135","https://openalex.org/W1603161560","https://openalex.org/W1587382781","https://openalex.org/W2154676777","https://openalex.org/W2158269427","https://openalex.org/W4381280689"],"abstract_inverted_index":{"Abstract":[0],"Text-to-video":[1],"retrieval":[2,31,165],"(TVR)":[3],"has":[4],"made":[5],"significant":[6,49],"progress":[7],"with":[8,94],"advances":[9],"in":[10],"vision":[11],"and":[12,21,28,47,51,92,100,108,137],"language":[13],"representation":[14],"learning.":[15],"Most":[16],"existing":[17],"methods":[18,38],"use":[19],"real-valued":[20],"hash-based":[22],"embeddings":[23],"to":[24,112,127,134],"represent":[25],"the":[26,80,159],"video":[27,91,136],"text,":[29],"allowing":[30],"by":[32],"computing":[33,52],"their":[34],"similarities.":[35],"However,":[36],"these":[37],"are":[39,141],"often":[40],"inefficient":[41],"for":[42,90,106,123],"large":[43],"volumes":[44],"of":[45,70,83],"video,":[46],"require":[48],"storage":[50],"resources.":[53],"In":[54],"this":[55],"work,":[56],"we":[57,130],"present":[58],"a":[59,67,145],"plug-and-play":[60],"multi-modal":[61,97],"multi-tagger-driven":[62],"pre-screening":[63],"framework,":[64],"which":[65,140],"pre-screens":[66],"substantial":[68],"number":[69],"videos":[71,122],"before":[72],"applying":[73],"any":[74],"TVR":[75,160,169],"algorithms,":[76],"thereby":[77],"efficiently":[78],"reducing":[79],"search":[81],"space":[82],"videos.":[84,116],"We":[85],"predict":[86],"discrete":[87],"semantic":[88],"tags":[89],"text":[93,124,138],"our":[95,154],"proposed":[96,155],"multi-tagger":[98],"module,":[99],"then":[101,142],"leverage":[102],"an":[103],"inverted":[104],"index":[105],"space-efficient":[107],"fast":[109],"tag":[110],"matching":[111],"filter":[113],"out":[114,120],"irrelevant":[115],"To":[117],"avoid":[118],"filtering":[119],"relevant":[121],"queries":[125],"due":[126],"inconsistent":[128],"tags,":[129],"utilize":[131],"contrastive":[132],"learning":[133],"align":[135],"embeddings,":[139],"fed":[143],"into":[144],"shared":[146],"multi-tag":[147],"head.":[148],"Extensive":[149],"experimental":[150],"results":[151],"demonstrate":[152],"that":[153],"method":[156],"significantly":[157],"accelerates":[158],"process":[161],"while":[162],"maintaining":[163],"high":[164],"accuracy":[166],"on":[167],"various":[168],"datasets.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":3}],"updated_date":"2026-06-13T06:13:01.061226","created_date":"2025-10-10T00:00:00"}