{"id":"https://openalex.org/W4400112881","doi":"https://doi.org/10.1109/tmm.2024.3416669","title":"Efficient Cross-Modal Video Retrieval With Meta-Optimized Frames","display_name":"Efficient Cross-Modal Video Retrieval With Meta-Optimized Frames","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4400112881","doi":"https://doi.org/10.1109/tmm.2024.3416669"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2024.3416669","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3416669","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","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/A5057073729","display_name":"Ning Han","orcid":"https://orcid.org/0000-0002-0654-6026"},"institutions":[{"id":"https://openalex.org/I4610292","display_name":"Xiangtan University","ror":"https://ror.org/00xsfaz62","country_code":"CN","type":"education","lineage":["https://openalex.org/I4610292"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ning Han","raw_affiliation_strings":["School of Computer Science, Xiangtan University, Xiangtan, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Xiangtan University, Xiangtan, China","institution_ids":["https://openalex.org/I4610292"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034737032","display_name":"Xun Yang","orcid":"https://orcid.org/0000-0003-0201-1638"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xun Yang","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039617569","display_name":"Ee\u2010Peng Lim","orcid":"https://orcid.org/0000-0003-0065-8665"},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ee-Peng Lim","raw_affiliation_strings":["School of Computing and Information Systems, Singapore Management University, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computing and Information Systems, Singapore Management University, Singapore","institution_ids":["https://openalex.org/I79891267"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100353471","display_name":"Hao Chen","orcid":"https://orcid.org/0000-0001-5902-1824"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Chen","raw_affiliation_strings":["Department of Information Science and Engineering, Hunan University, Changsha, China"],"affiliations":[{"raw_affiliation_string":"Department of Information Science and Engineering, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101633158","display_name":"Qianru Sun","orcid":"https://orcid.org/0000-0003-2689-317X"},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Qianru Sun","raw_affiliation_strings":["School of Computing and Information Systems, Singapore Management University, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computing and Information Systems, Singapore Management University, Singapore","institution_ids":["https://openalex.org/I79891267"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5057073729"],"corresponding_institution_ids":["https://openalex.org/I4610292"],"apc_list":null,"apc_paid":null,"fwci":1.9943,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.87512843,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"26","issue":null,"first_page":"10924","last_page":"10936"},"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":0.9995999932289124,"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"}},"topics":[{"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":0.9991000294685364,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9952999949455261,"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":0.8540151119232178},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.568547248840332},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41467222571372986},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.39474380016326904},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.38487714529037476}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8540151119232178},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.568547248840332},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41467222571372986},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.39474380016326904},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.38487714529037476},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2024.3416669","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3416669","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G405190135","display_name":null,"funder_award_id":"U22A2094","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7026977538","display_name":null,"funder_award_id":"2024JJ6435","funder_id":"https://openalex.org/F4320322843","funder_display_name":"Natural Science Foundation of\u00a0Hunan Province"}],"funders":[{"id":"https://openalex.org/F4320320696","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322843","display_name":"Natural Science Foundation of\u00a0Hunan Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":71,"referenced_works":["https://openalex.org/W2139501017","https://openalex.org/W2425121537","https://openalex.org/W2462996230","https://openalex.org/W2614367549","https://openalex.org/W2808399042","https://openalex.org/W2885775891","https://openalex.org/W2886641317","https://openalex.org/W2896457183","https://openalex.org/W2897439619","https://openalex.org/W2948037078","https://openalex.org/W2951019013","https://openalex.org/W2955273087","https://openalex.org/W2963017553","https://openalex.org/W2963877232","https://openalex.org/W2975813532","https://openalex.org/W2990503944","https://openalex.org/W3035265375","https://openalex.org/W3035309251","https://openalex.org/W3035356601","https://openalex.org/W3035635319","https://openalex.org/W3043840704","https://openalex.org/W3043990051","https://openalex.org/W3081484346","https://openalex.org/W3082570681","https://openalex.org/W3107973541","https://openalex.org/W3113055207","https://openalex.org/W3126721948","https://openalex.org/W3128401049","https://openalex.org/W3130796238","https://openalex.org/W3144281354","https://openalex.org/W3152619510","https://openalex.org/W3157181916","https://openalex.org/W3163842339","https://openalex.org/W3168640669","https://openalex.org/W3173223111","https://openalex.org/W3197828817","https://openalex.org/W3204588463","https://openalex.org/W3204670646","https://openalex.org/W3204891544","https://openalex.org/W3205497712","https://openalex.org/W3206597437","https://openalex.org/W3210758160","https://openalex.org/W3217102353","https://openalex.org/W4205817612","https://openalex.org/W4210900713","https://openalex.org/W4225414521","https://openalex.org/W4225547367","https://openalex.org/W4226407477","https://openalex.org/W4285606530","https://openalex.org/W4304014690","https://openalex.org/W4304080188","https://openalex.org/W4312299780","https://openalex.org/W4312372711","https://openalex.org/W4312560592","https://openalex.org/W4387614569","https://openalex.org/W6684090549","https://openalex.org/W6755365793","https://openalex.org/W6756054015","https://openalex.org/W6757297395","https://openalex.org/W6765987901","https://openalex.org/W6766582784","https://openalex.org/W6766776083","https://openalex.org/W6768851824","https://openalex.org/W6770070843","https://openalex.org/W6775564893","https://openalex.org/W6784184991","https://openalex.org/W6784333009","https://openalex.org/W6791353385","https://openalex.org/W6797148833","https://openalex.org/W6801013943","https://openalex.org/W6810042059"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Cross-modal":[0],"video":[1,32,82,136,164,192,220,265],"retrieval":[2,165,193,221,266],"aims":[3],"to":[4,30,67,225],"retrieve":[5],"semantically":[6],"relevant":[7],"videos":[8,231],"when":[9,57],"given":[10],"a":[11,70,97,123,141,162,237,282,295],"textual":[12],"query,":[13],"and":[14,63,152,274,284,292],"is":[15,66,181,223,251,281],"one":[16],"of":[17,54,77,84,94,103,147,190,229,240,249],"the":[18,50,80,86,101,170,187,191,197,208,211,219,227],"fundamental":[19],"multimedia":[20],"tasks.":[21],"Most":[22],"top-performing":[23],"methods":[24],"primarily":[25],"leverage":[26],"Vision":[27],"Transformer":[28],"(ViT)":[29],"extract":[31],"features":[33],"(Lei":[34],"et":[35,39,43],"al.,":[36,40,44],"2021},":[37],"(Bain":[38],"2021),":[41],"(Wang":[42],"2022).":[45],"However,":[46],"they":[47],"suffer":[48],"from":[49,79,128],"high":[51],"computational":[52,119],"complexity":[53],"ViT,":[55,104],"especially":[56],"encoding":[58],"long":[59],"videos.":[60],"A":[61],"common":[62],"simple":[64],"solution":[65],"uniformly":[68],"sample":[69],"small":[71,238],"number":[72,93,239],"(e.g.,":[73],"4":[74,114],"or":[75],"8)":[76],"frames":[78,95,108,115,242],"target":[81],"(instead":[83],"using":[85,106,113,186],"whole":[87,198,230],"video)":[88],"as":[89,207],"ViT":[90],"inputs.":[91],"The":[92,157,247],"has":[96],"strong":[98],"influence":[99],"on":[100,140,196,268],"performance":[102,111],"e.g.,":[105],"8":[107],"yields":[109],"better":[110],"than":[112],"but":[116],"requires":[117],"more":[118],"resources,":[120],"resulting":[121],"in":[122,243],"trade-off.":[124],"To":[125],"get":[126],"free":[127],"this":[129,131,202],"trade-off,":[130],"paper":[132],"introduces":[133],"an":[134],"automatic":[135],"compression":[137],"method":[138,204,286],"based":[139],"bilevel":[142],"optimization":[143,159,180],"program":[144],"(BOP)":[145],"consisting":[146],"both":[148],"model-level":[149,158],"(i.e.,":[150,154],"base-level)":[151],"frame-level":[153,175,179],"meta-level)":[155],"optimizations.":[156],"process":[160],"learns":[161],"cross-modal":[163,264],"model":[166,194,222],"whose":[167],"input":[168,241],"includes":[169],"\u201ccompressed":[171,209],"frames\u201d":[172],"learned":[173],"by":[174,253],"optimization.":[176],"In":[177],"turn,":[178],"achieved":[182],"through":[183],"gradient":[184,255],"descent":[185,256],"meta":[188,254],"loss":[189],"computed":[195],"video.":[199],"We":[200],"call":[201],"BOP":[203],"(as":[205],"well":[206],"frames\u201d)":[210],"Meta-Optimized":[212],"Frames":[213],"(MOF)":[214],"approach.":[215],"By":[216],"incorporating":[217],"MOF,":[218],"able":[224],"utilize":[226],"information":[228],"(for":[232],"training)":[233],"while":[234],"taking":[235],"only":[236],"its":[244],"actual":[245],"implementation.":[246],"convergence":[248],"MOF":[250,280],"guaranteed":[252],"algorithms.":[257],"For":[258],"evaluation":[259],"purposes,":[260],"we":[261],"conduct":[262],"extensive":[263],"experiments":[267],"three":[269],"large-scale":[270],"benchmarks:":[271],"MSR-VTT,":[272],"MSVD,":[273],"DiDeMo.":[275],"Our":[276],"results":[277],"show":[278],"that":[279,287],"generic":[283],"efficient":[285],"boost":[288],"multiple":[289],"baseline":[290],"methods,":[291],"can":[293],"achieve":[294],"new":[296],"state-of-the-art":[297],"performance.":[298]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}