{"id":"https://openalex.org/W4298118989","doi":"https://doi.org/10.1587/transinf.2022edl8018","title":"An Efficient Multimodal Aggregation Network for Video-Text Retrieval","display_name":"An Efficient Multimodal Aggregation Network for Video-Text Retrieval","publication_year":2022,"publication_date":"2022-09-30","ids":{"openalex":"https://openalex.org/W4298118989","doi":"https://doi.org/10.1587/transinf.2022edl8018"},"language":"en","primary_location":{"id":"doi:10.1587/transinf.2022edl8018","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2022edl8018","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E105.D/10/E105.D_2022EDL8018/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.jstage.jst.go.jp/article/transinf/E105.D/10/E105.D_2022EDL8018/_pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101856541","display_name":"Zhi Liu","orcid":"https://orcid.org/0000-0002-8464-3235"},"institutions":[{"id":"https://openalex.org/I1456306","display_name":"North China University of Technology","ror":"https://ror.org/01nky7652","country_code":"CN","type":"education","lineage":["https://openalex.org/I1456306"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhi LIU","raw_affiliation_strings":["North China University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"North China University of Technology","institution_ids":["https://openalex.org/I1456306"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107497869","display_name":"Fangyuan Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I1456306","display_name":"North China University of Technology","ror":"https://ror.org/01nky7652","country_code":"CN","type":"education","lineage":["https://openalex.org/I1456306"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangyuan ZHAO","raw_affiliation_strings":["North China University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"North China University of Technology","institution_ids":["https://openalex.org/I1456306"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020279911","display_name":"Mengmeng ZHANG","orcid":null},"institutions":[{"id":"https://openalex.org/I1456306","display_name":"North China University of Technology","ror":"https://ror.org/01nky7652","country_code":"CN","type":"education","lineage":["https://openalex.org/I1456306"]},{"id":"https://openalex.org/I4210152042","display_name":"Beijing Polytechnic","ror":"https://ror.org/03xgzn792","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengmeng ZHANG","raw_affiliation_strings":["Beijing Polytechnic College","North China University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Polytechnic College","institution_ids":["https://openalex.org/I4210152042"]},{"raw_affiliation_string":"North China University of Technology","institution_ids":["https://openalex.org/I1456306"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0979,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.36998537,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"E105.D","issue":"10","first_page":"1825","last_page":"1828"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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/T11714","display_name":"Multimodal Machine Learning Applications","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/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/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":0.9141022562980652},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.7035400867462158},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6418107151985168},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6184642910957336},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5454864501953125},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4797709882259369},{"id":"https://openalex.org/keywords/video-retrieval","display_name":"Video retrieval","score":0.46651947498321533},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.41826292872428894},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4034915566444397},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2559291124343872}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9141022562980652},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.7035400867462158},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6418107151985168},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6184642910957336},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5454864501953125},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4797709882259369},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.46651947498321533},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.41826292872428894},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4034915566444397},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2559291124343872},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1587/transinf.2022edl8018","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2022edl8018","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E105.D/10/E105.D_2022EDL8018/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1587/transinf.2022edl8018","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2022edl8018","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E105.D/10/E105.D_2022EDL8018/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322724","display_name":"Ministry of Education, India","ror":"https://ror.org/048xjjh50"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4298118989.pdf","grobid_xml":"https://content.openalex.org/works/W4298118989.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W2425121537","https://openalex.org/W2796207103","https://openalex.org/W2885775891","https://openalex.org/W2896457183","https://openalex.org/W2897439619","https://openalex.org/W2951019013","https://openalex.org/W2963916161","https://openalex.org/W2965458216","https://openalex.org/W3027758526","https://openalex.org/W3043840704","https://openalex.org/W3135367836","https://openalex.org/W3145807616","https://openalex.org/W3175593095","https://openalex.org/W3180463990"],"related_works":["https://openalex.org/W2989932438","https://openalex.org/W3099765033","https://openalex.org/W4210794429","https://openalex.org/W4283732135","https://openalex.org/W1996541855","https://openalex.org/W2940336242","https://openalex.org/W4313159793","https://openalex.org/W4287598411","https://openalex.org/W3098382480","https://openalex.org/W4362014186"],"abstract_inverted_index":{"In":[0,35,79],"video-text":[1,44],"retrieval":[2,45],"task,":[3,25],"mainstream":[4],"framework":[5],"consists":[6],"of":[7,31,84,119],"three":[8],"parts:":[9],"video":[10,57],"encoder,":[11],"text":[12,103],"encoder":[13,104],"and":[14,71],"similarity":[15],"calculation.":[16],"MMT":[17,54],"(Multi-modal":[18],"Transformer)":[19],"achieves":[20,135],"remarkable":[21],"performance":[22],"for":[23,43,74],"this":[24,36],"however,":[26],"it":[27,99],"faces":[28],"the":[29,50,59,64,82,106,120,132,140],"problem":[30],"insufficient":[32],"training":[33,75,125],"dataset.":[34],"paper,":[37],"an":[38],"efficient":[39],"multimodal":[40],"aggregation":[41],"network":[42,108],"is":[46,61,72,100,127],"proposed.":[47],"Different":[48],"from":[49,96],"prior":[51],"work":[52],"using":[53],"to":[55,109,115],"fuse":[56],"features,":[58],"NetVLAD":[60],"introduced":[62,101],"in":[63,105,113],"proposed":[65,107,133],"network.":[66],"It":[67],"has":[68],"fewer":[69],"parameters":[70],"feasible":[73],"with":[76,139],"small":[77],"datasets.":[78],"addition,":[80],"since":[81],"function":[83],"CLIP":[85],"(Contrastive":[86],"Language-Image":[87],"Pre-training)":[88],"can":[89],"be":[90],"considered":[91],"as":[92,102],"learning":[93],"language":[94],"models":[95],"visual":[97],"supervision,":[98],"avoid":[110],"overfitting.":[111],"Meanwhile,":[112],"order":[114],"make":[116],"full":[117],"use":[118],"pre-training":[121],"model,":[122],"a":[123],"two-step":[124],"scheme":[126],"designed.":[128],"Experiments":[129],"show":[130],"that":[131],"model":[134],"competitive":[136],"results":[137],"compared":[138],"latest":[141],"work.":[142]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}