{"id":"https://openalex.org/W4399418426","doi":"https://doi.org/10.1145/3652583.3660001","title":"MVRMLM 2024: Multimodal Video Retrieval and Multimodal Language Modelling","display_name":"MVRMLM 2024: Multimodal Video Retrieval and Multimodal Language Modelling","publication_year":2024,"publication_date":"2024-05-30","ids":{"openalex":"https://openalex.org/W4399418426","doi":"https://doi.org/10.1145/3652583.3660001"},"language":"en","primary_location":{"id":"doi:10.1145/3652583.3660001","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3660001","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3660001","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3660001","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100460917","display_name":"Hui Wang","orcid":"https://orcid.org/0000-0003-2633-6015"},"institutions":[{"id":"https://openalex.org/I126231945","display_name":"Queen's University Belfast","ror":"https://ror.org/00hswnk62","country_code":"GB","type":"education","lineage":["https://openalex.org/I126231945"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Hui Wang","raw_affiliation_strings":["Queens University Belfast, Belfast, UK"],"raw_orcid":"https://orcid.org/0000-0003-2633-6015","affiliations":[{"raw_affiliation_string":"Queens University Belfast, Belfast, UK","institution_ids":["https://openalex.org/I126231945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028209738","display_name":"Josef Kittler","orcid":"https://orcid.org/0000-0002-8110-9205"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Josef Kittler","raw_affiliation_strings":["University of Surrey, Surrey, UK"],"raw_orcid":"https://orcid.org/0000-0002-8110-9205","affiliations":[{"raw_affiliation_string":"University of Surrey, Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050766679","display_name":"Mark Gales","orcid":"https://orcid.org/0000-0002-5311-8219"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mark Gales","raw_affiliation_strings":["University of Cambridge, Cambridge, UK"],"raw_orcid":"https://orcid.org/0000-0002-5311-8219","affiliations":[{"raw_affiliation_string":"University of Cambridge, Cambridge, UK","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087931267","display_name":"Rob Cooper","orcid":"https://orcid.org/0009-0006-7576-0217"},"institutions":[{"id":"https://openalex.org/I2801884250","display_name":"British Broadcasting Corporation (United Kingdom)","ror":"https://ror.org/01qepzr42","country_code":"GB","type":"government","lineage":["https://openalex.org/I2801884250"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Rob Cooper","raw_affiliation_strings":["BBC, London, United Kingdom"],"raw_orcid":"https://orcid.org/0009-0006-7576-0217","affiliations":[{"raw_affiliation_string":"BBC, London, United Kingdom","institution_ids":["https://openalex.org/I2801884250"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038610271","display_name":"Maurice Mulvenna","orcid":"https://orcid.org/0000-0002-1554-0785"},"institutions":[{"id":"https://openalex.org/I138801177","display_name":"University of Ulster","ror":"https://ror.org/01yp9g959","country_code":"GB","type":"education","lineage":["https://openalex.org/I138801177"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Maurice Mulvenna","raw_affiliation_strings":["Ulster University, Belfast, UK"],"raw_orcid":"https://orcid.org/0000-0002-1554-0785","affiliations":[{"raw_affiliation_string":"Ulster University, Belfast, UK","institution_ids":["https://openalex.org/I138801177"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105759393","display_name":"Wing W. Y. Ng","orcid":"https://orcid.org/0000-0003-0783-3585"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wing Ng","raw_affiliation_strings":["South China University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-0783-3585","affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016123060","display_name":"Hua Yang","orcid":"https://orcid.org/0000-0001-5536-503X"},"institutions":[{"id":"https://openalex.org/I126231945","display_name":"Queen's University Belfast","ror":"https://ror.org/00hswnk62","country_code":"GB","type":"education","lineage":["https://openalex.org/I126231945"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yang Hua","raw_affiliation_strings":["Queens University Belfast, Belfast, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0001-5536-503X","affiliations":[{"raw_affiliation_string":"Queens University Belfast, Belfast, United Kingdom","institution_ids":["https://openalex.org/I126231945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034054812","display_name":"Richard Gault","orcid":"https://orcid.org/0000-0001-6097-8981"},"institutions":[{"id":"https://openalex.org/I126231945","display_name":"Queen's University Belfast","ror":"https://ror.org/00hswnk62","country_code":"GB","type":"education","lineage":["https://openalex.org/I126231945"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Richard Gault","raw_affiliation_strings":["Queens University Belfast, Belfast, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0001-6097-8981","affiliations":[{"raw_affiliation_string":"Queens University Belfast, Belfast, United Kingdom","institution_ids":["https://openalex.org/I126231945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037285328","display_name":"Abbas Haider","orcid":"https://orcid.org/0000-0003-1802-3086"},"institutions":[{"id":"https://openalex.org/I126231945","display_name":"Queen's University Belfast","ror":"https://ror.org/00hswnk62","country_code":"GB","type":"education","lineage":["https://openalex.org/I126231945"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Abbas Haider","raw_affiliation_strings":["Queens University Belfast, Belfast, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0003-1802-3086","affiliations":[{"raw_affiliation_string":"Queens University Belfast, Belfast, United Kingdom","institution_ids":["https://openalex.org/I126231945"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048656618","display_name":"Guanfeng Wu","orcid":"https://orcid.org/0000-0001-8449-974X"},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanfeng Wu","raw_affiliation_strings":["Southwest Jiatong University, China, China"],"raw_orcid":"https://orcid.org/0000-0001-8449-974X","affiliations":[{"raw_affiliation_string":"Southwest Jiatong University, China, China","institution_ids":["https://openalex.org/I4800084"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5100460917"],"corresponding_institution_ids":["https://openalex.org/I126231945"],"apc_list":null,"apc_paid":null,"fwci":0.2381,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.47894287,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1345","last_page":"1346"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9973000288009644,"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":0.9973000288009644,"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":0.9800999760627747,"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":0.9765999913215637,"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":0.8503050804138184},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.7852561473846436},{"id":"https://openalex.org/keywords/interactivity","display_name":"Interactivity","score":0.6656383275985718},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.5684244632720947},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5312597155570984},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5088265538215637},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.50543212890625},{"id":"https://openalex.org/keywords/multimodal-interaction","display_name":"Multimodal interaction","score":0.4804101288318634},{"id":"https://openalex.org/keywords/interactive-video","display_name":"Interactive video","score":0.4480670392513275},{"id":"https://openalex.org/keywords/multimodality","display_name":"Multimodality","score":0.4447404742240906},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.43314769864082336},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.424355149269104},{"id":"https://openalex.org/keywords/multimodal-learning","display_name":"Multimodal learning","score":0.41425931453704834},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4121074974536896},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3564372658729553},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24500951170921326}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8503050804138184},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.7852561473846436},{"id":"https://openalex.org/C144430266","wikidata":"https://www.wikidata.org/wiki/Q839721","display_name":"Interactivity","level":2,"score":0.6656383275985718},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.5684244632720947},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5312597155570984},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5088265538215637},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.50543212890625},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.4804101288318634},{"id":"https://openalex.org/C2776566319","wikidata":"https://www.wikidata.org/wiki/Q3495514","display_name":"Interactive video","level":2,"score":0.4480670392513275},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.4447404742240906},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.43314769864082336},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.424355149269104},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.41425931453704834},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4121074974536896},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3564372658729553},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24500951170921326},{"id":"https://openalex.org/C129307140","wikidata":"https://www.wikidata.org/wiki/Q6795880","display_name":"Maximum bubble pressure method","level":3,"score":0.0},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"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/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C157915830","wikidata":"https://www.wikidata.org/wiki/Q2928001","display_name":"Bubble","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3652583.3660001","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3660001","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3660001","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.qub.ac.uk/portal:publications/35b79d06-5aad-4d59-89af-3f97010f5370","is_oa":true,"landing_page_url":"https://pure.qub.ac.uk/en/publications/35b79d06-5aad-4d59-89af-3f97010f5370","pdf_url":null,"source":{"id":"https://openalex.org/S4306402319","display_name":"Research Portal (Queen's University Belfast)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I126231945","host_organization_name":"Queen's University Belfast","host_organization_lineage":["https://openalex.org/I126231945"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Wang , H , Kittler , J , Gales , M , Cooper , R , Mulvenna , M , Ng , W , Hua , Y , Gault , R , Haider , A &amp; Wu , G 2024 , MVRMLM 2024: multimodal video retrieval and multimodal language modelling . in ICMR '24: Proceedings of the 14th Annual ACM International Conference on Multimedia Retrieval . Association for Computing Machinery , pp. 1345-1346 , 14th Annual ACM International Conference on Multimedia Retrieval 2024 , Phuket , Thailand , 10/06/2024 . https://doi.org/10.1145/3652583.3660001","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"doi:10.1145/3652583.3660001","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3660001","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3660001","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4598575966","display_name":null,"funder_award_id":"EP/V006223/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G7111890331","display_name":null,"funder_award_id":"EP/V002856/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G8836132066","display_name":null,"funder_award_id":"EP/V002740/2","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399418426.pdf","grobid_xml":"https://content.openalex.org/works/W4399418426.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2123601988","https://openalex.org/W3093803775","https://openalex.org/W2068964259","https://openalex.org/W2013013717","https://openalex.org/W66256988","https://openalex.org/W4302857920","https://openalex.org/W1987340722","https://openalex.org/W199123384","https://openalex.org/W1595044459","https://openalex.org/W2739856905"],"abstract_inverted_index":{"As":[0],"the":[1,31,112,119,156],"proliferation":[2],"of":[3,33,36,114,140,158,162],"video":[4,9,15,53,67],"content":[5,60],"continues,":[6],"and":[7,49,82,90,99,108,126,167],"many":[8],"archives":[10],"lack":[11],"suitable":[12],"metadata,":[13],"therefore,":[14],"retrieval,":[16],"particularly":[17],"through":[18],"example-based":[19],"search,":[20,165],"has":[21,128],"become":[22],"increasingly":[23],"crucial.":[24],"Existing":[25],"metadata":[26],"often":[27],"fails":[28],"to":[29,147,154],"meet":[30],"needs":[32],"specific":[34],"types":[35],"searches,":[37],"especially":[38],"when":[39],"videos":[40],"contain":[41],"elements":[42],"from":[43,151],"different":[44],"modalities,":[45],"such":[46],"as":[47],"visual":[48],"audio.":[50],"Consequently,":[51],"developing":[52,159],"retrieval":[54,68],"methods":[55],"that":[56],"can":[57],"handle":[58],"multi-modal":[59],"is":[61],"essential.":[62],"In":[63],"designing":[64],"our":[65],"novel":[66,160],"framework":[69],"named":[70],"Multi-modal":[71],"Video":[72],"Search":[73],"by":[74],"Examples":[75],"(MVSE)1,":[76],"we":[77],"focused":[78],"on":[79],"accuracy":[80],"(precision":[81],"recall),":[83],"efficiency":[84],"(retrieval":[85],"time":[86],"in":[87],"seconds),":[88],"interactivity,":[89],"extensibility,":[91],"with":[92,131],"key":[93],"components":[94],"including":[95,124],"advanced":[96],"data":[97,164],"processing":[98],"a":[100,132,137],"user-friendly":[101],"interface":[102],"aimed":[103],"at":[104],"enhancing":[105],"search":[106],"effectiveness":[107],"user":[109],"experience.":[110],"With":[111],"advent":[113],"Large":[115],"Language":[116],"Models":[117],"(LLMs),":[118],"interaction":[120],"between":[121],"multimodal":[122,163],"data,":[123],"image":[125],"audio":[127],"been":[129],"transformed":[130],"significant":[133],"leap":[134],"forward":[135],"towards":[136],"bigger":[138],"goal":[139],"artificial":[141],"general":[142],"intelligence.":[143],"This":[144],"workshop":[145],"aims":[146],"bring":[148],"together":[149],"experts":[150],"diverse":[152],"domains":[153],"explore":[155],"possibilities":[157],"ways":[161],"understanding":[166],"interaction.":[168]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
