{"id":"https://openalex.org/W4296437558","doi":"https://doi.org/10.1109/tcsvt.2022.3207910","title":"Temporal Multimodal Graph Transformer With Global-Local Alignment for Video-Text Retrieval","display_name":"Temporal Multimodal Graph Transformer With Global-Local Alignment for Video-Text Retrieval","publication_year":2022,"publication_date":"2022-09-19","ids":{"openalex":"https://openalex.org/W4296437558","doi":"https://doi.org/10.1109/tcsvt.2022.3207910"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2022.3207910","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2022.3207910","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","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/A5019172074","display_name":"Zerun Feng","orcid":"https://orcid.org/0000-0003-3987-0591"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zerun Feng","raw_affiliation_strings":["Beijing Key Laboratory of Network System Architecture and Convergence, School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Network System Architecture and Convergence, School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101906657","display_name":"Zhimin Zeng","orcid":"https://orcid.org/0009-0008-5717-9167"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhimin Zeng","raw_affiliation_strings":["Beijing Key Laboratory of Network System Architecture and Convergence, School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Network System Architecture and Convergence, School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058648594","display_name":"Caili Guo","orcid":"https://orcid.org/0000-0001-8892-4520"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Caili Guo","raw_affiliation_strings":["Beijing Laboratory of Advanced Information Networks, School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Laboratory of Advanced Information Networks, School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100415053","display_name":"Zheng Li","orcid":"https://orcid.org/0000-0003-2535-2523"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Li","raw_affiliation_strings":["Beijing Key Laboratory of Network System Architecture and Convergence, School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Network System Architecture and Convergence, School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5019172074"],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":2.7564,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.91807471,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"33","issue":"3","first_page":"1438","last_page":"1453"},"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":0.9995999932289124,"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":0.9987999796867371,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7971032857894897},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5556848049163818},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5418409109115601},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4860961437225342},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4845961332321167},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.47043463587760925},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4699314534664154},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.41608282923698425},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3739582300186157},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.36903902888298035},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.22165226936340332}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7971032857894897},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5556848049163818},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5418409109115601},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4860961437225342},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4845961332321167},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47043463587760925},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4699314534664154},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.41608282923698425},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3739582300186157},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36903902888298035},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.22165226936340332},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2022.3207910","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2022.3207910","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5199999809265137}],"awards":[{"id":"https://openalex.org/G2914057848","display_name":null,"funder_award_id":"2021XD-A01-1","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G5181277069","display_name":null,"funder_award_id":"4202049","funder_id":"https://openalex.org/F4320322919","funder_display_name":"Natural Science Foundation of Beijing Municipality"}],"funders":[{"id":"https://openalex.org/F4320322919","display_name":"Natural Science Foundation of Beijing Municipality","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":72,"referenced_works":["https://openalex.org/W1491389626","https://openalex.org/W1522301498","https://openalex.org/W1614298861","https://openalex.org/W1771999989","https://openalex.org/W1995137594","https://openalex.org/W1995875735","https://openalex.org/W2012592962","https://openalex.org/W2021899621","https://openalex.org/W2078238240","https://openalex.org/W2106568252","https://openalex.org/W2112912048","https://openalex.org/W2127944900","https://openalex.org/W2147238549","https://openalex.org/W2194775991","https://openalex.org/W2425121537","https://openalex.org/W2526050071","https://openalex.org/W2552579943","https://openalex.org/W2608988379","https://openalex.org/W2619947201","https://openalex.org/W2732026016","https://openalex.org/W2752782242","https://openalex.org/W2796207103","https://openalex.org/W2883429621","https://openalex.org/W2885775891","https://openalex.org/W2894730515","https://openalex.org/W2896457183","https://openalex.org/W2951019013","https://openalex.org/W2956018683","https://openalex.org/W2962810613","https://openalex.org/W2963446712","https://openalex.org/W2963507712","https://openalex.org/W2963839617","https://openalex.org/W2963916161","https://openalex.org/W2964051877","https://openalex.org/W2969377765","https://openalex.org/W2975813532","https://openalex.org/W2981165461","https://openalex.org/W2981851019","https://openalex.org/W3011305844","https://openalex.org/W3034773362","https://openalex.org/W3034882096","https://openalex.org/W3035356601","https://openalex.org/W3043840704","https://openalex.org/W3044256341","https://openalex.org/W3048093647","https://openalex.org/W3087642760","https://openalex.org/W3097336090","https://openalex.org/W3119243803","https://openalex.org/W3145807616","https://openalex.org/W3173223111","https://openalex.org/W3174873881","https://openalex.org/W3188030217","https://openalex.org/W3195284414","https://openalex.org/W4205510032","https://openalex.org/W4206430846","https://openalex.org/W4211053420","https://openalex.org/W4285345750","https://openalex.org/W4288373939","https://openalex.org/W6620707391","https://openalex.org/W6629590909","https://openalex.org/W6631190155","https://openalex.org/W6636510571","https://openalex.org/W6676647902","https://openalex.org/W6684191040","https://openalex.org/W6739901393","https://openalex.org/W6750041603","https://openalex.org/W6755207826","https://openalex.org/W6760837195","https://openalex.org/W6766582784","https://openalex.org/W6779068807","https://openalex.org/W6784184991","https://openalex.org/W6955071965"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W4312814274","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703"],"abstract_inverted_index":{"Video-text":[0],"retrieval":[1,59],"is":[2,117,216],"a":[3,9,100,124,143,190,211,242],"crucial":[4],"task":[5],"that":[6],"has":[7],"been":[8],"powerful":[10],"application":[11],"for":[12,114,134,218],"multi-media":[13],"data":[14],"analysis":[15],"and":[16,30,39,93,158,174,184,196,232,245],"attracted":[17],"tremendous":[18],"interest":[19],"in":[20,50,86],"the":[21,34,110,139,151,165,181,197,202,209,220,229],"research":[22],"area.":[23],"The":[24,72,90,105],"core":[25],"steps":[26],"are":[27,79,96,162,187,205,225],"feature":[28,87],"representations":[29],"alignment":[31,56,116],"to":[32,57,108,149,169,189],"overcome":[33],"heterogeneous":[35],"gap":[36],"between":[37,75,154,199],"videos":[38,51],"texts.":[40],"Existing":[41],"methods":[42,65],"not":[43,80],"only":[44],"take":[45],"advantage":[46],"of":[47,145,192],"multi-modal":[48,155],"information":[49,153],"but":[52],"also":[53],"explore":[54],"local":[55,115,179],"enhance":[58],"accuracy.":[60],"Although":[61],"performing":[62],"well,":[63],"these":[64],"seem":[66],"deficient":[67],"at":[68],"three":[69],"perspectives:":[70],"a)":[71],"semantic":[73,111,146,166,194],"correlations":[74],"different":[76],"modal":[77],"features":[78,186],"considered,":[81],"which":[82],"introduces":[83],"irrelevant":[84],"noise":[85],"representations.":[88],"b)":[89],"cross-modal":[91,172],"relations":[92,173],"temporal":[94,159,175],"associations":[95,176],"ambiguously":[97],"learned":[98],"by":[99,241],"single":[101],"self-attention":[102,160],"manipulation.":[103],"c)":[104],"training":[106,219],"signal":[107],"optimize":[109,208],"topic":[112],"assignment":[113],"missing.":[118],"In":[119],"this":[120],"paper,":[121],"we":[122],"proposed":[123,217],"novel":[125],"Temporal":[126],"Multi-modal":[127],"Graph":[128,157],"Transformer":[129],"with":[130],"Global-Local":[131],"Alignment":[132],"(TMMGT-GLA)":[133],"video-text":[135],"retrieval.":[136],"We":[137],"model":[138],"input":[140],"video":[141,183],"as":[142],"sequence":[144],"correlation":[147,167],"graphs":[148,168],"exploit":[150],"structural":[152],"features.":[156],"layers":[161],"leveraged":[163],"on":[164,228],"effectively":[170],"learn":[171],"respectively.":[177],"For":[178],"alignment,":[180],"encoded":[182],"text":[185],"assigned":[188],"set":[191],"shared":[193],"topics,":[195],"distances":[198],"residuals":[200],"from":[201],"same":[203],"ones":[204],"minimized.":[206],"To":[207],"assignments,":[210],"minimum":[212],"entropy-based":[213],"regularization":[214],"term":[215],"overall":[221],"framework.":[222],"Experimental":[223],"results":[224],"carried":[226],"out":[227],"MSR-VTT,":[230],"LSMDC,":[231],"ActivityNet":[233],"Captions":[234],"datasets.":[235],"Our":[236],"method":[237],"outperforms":[238],"previous":[239],"approaches":[240],"large":[243],"margin":[244],"achieves":[246],"state-of-the-art":[247],"performance.":[248]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}