{"id":"https://openalex.org/W3198455660","doi":"https://doi.org/10.1145/3460426.3463662","title":"GPT2MVS: Generative Pre-trained Transformer-2 for Multi-modal Video Summarization","display_name":"GPT2MVS: Generative Pre-trained Transformer-2 for Multi-modal Video Summarization","publication_year":2021,"publication_date":"2021-08-24","ids":{"openalex":"https://openalex.org/W3198455660","doi":"https://doi.org/10.1145/3460426.3463662","mag":"3198455660"},"language":"en","primary_location":{"id":"doi:10.1145/3460426.3463662","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3460426.3463662","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Multimedia Retrieval","raw_type":"proceedings-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/A5091066062","display_name":"Jia-Hong Huang","orcid":"https://orcid.org/0000-0001-7943-2591"},"institutions":[{"id":"https://openalex.org/I4210135670","display_name":"Amsterdam University of the Arts","ror":"https://ror.org/04dde1554","country_code":"NL","type":"education","lineage":["https://openalex.org/I4210135670"]},{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Jia-Hong Huang","raw_affiliation_strings":["University of Amsterdam, Amsterdam, Netherlands"],"affiliations":[{"raw_affiliation_string":"University of Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I4210135670","https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025506929","display_name":"Luka Murn","orcid":"https://orcid.org/0000-0001-9041-647X"},"institutions":[{"id":"https://openalex.org/I180825142","display_name":"City, University of London","ror":"https://ror.org/04489at23","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I180825142"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Luka Murn","raw_affiliation_strings":["BBC Research and Development & Dublin City University, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"BBC Research and Development & Dublin City University, London, United Kingdom","institution_ids":["https://openalex.org/I180825142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083550803","display_name":"Marta Mrak","orcid":"https://orcid.org/0000-0002-7777-0252"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marta Mrak","raw_affiliation_strings":["BBC Research and Development, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"BBC Research and Development, London, United Kingdom","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070684680","display_name":"Marcel Worring","orcid":"https://orcid.org/0000-0003-4097-4136"},"institutions":[{"id":"https://openalex.org/I4210135670","display_name":"Amsterdam University of the Arts","ror":"https://ror.org/04dde1554","country_code":"NL","type":"education","lineage":["https://openalex.org/I4210135670"]},{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Marcel Worring","raw_affiliation_strings":["University of Amsterdam, Amsterdam, Netherlands"],"affiliations":[{"raw_affiliation_string":"University of Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I4210135670","https://openalex.org/I887064364"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5091066062"],"corresponding_institution_ids":["https://openalex.org/I4210135670","https://openalex.org/I887064364"],"apc_list":null,"apc_paid":null,"fwci":2.7123,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.91944611,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"580","last_page":"589"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","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/T11439","display_name":"Video Analysis and Summarization","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/T11309","display_name":"Music and Audio Processing","score":0.9922999739646912,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9908000230789185,"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/automatic-summarization","display_name":"Automatic summarization","score":0.9638758897781372},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8640071153640747},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6766282320022583},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5774886012077332},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45012521743774414},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.35181546211242676},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3336811065673828},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3201044201850891},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.0740058422088623}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.9638758897781372},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8640071153640747},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6766282320022583},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5774886012077332},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45012521743774414},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35181546211242676},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3336811065673828},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3201044201850891},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0740058422088623},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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":3,"locations":[{"id":"doi:10.1145/3460426.3463662","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3460426.3463662","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:dare.uva.nl:openaire_cris_publications/473ca26e-7491-4cfe-8af6-1b7d3febd810","is_oa":false,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/gpt2mvs-generative-pretrained-transformer2-for-multimodal-video-summarization(473ca26e-7491-4cfe-8af6-1b7d3febd810).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Huang, J-H, Murn, L, Mrak, M & Worring, M 2021, GPT2MVS: Generative Pre-Trained Transformer-2 for Multi-Modal Video Summarization. in ICMR '21 : proceedings of the 2021 International Conference on Multimedia Retrieval : August 21-24, 2021, Taipei, Taiwan. New York, NY, pp. 580-589, 11th ACM International Conference on Multimedia Retrieval, ICMR 2021, Taipei, Taiwan, Province of China, 16/11/21. https://doi.org/10.1145/3460426.3463662","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:uvapub:oai:dare.uva.nl:publications/473ca26e-7491-4cfe-8af6-1b7d3febd810","is_oa":false,"landing_page_url":"https://dare.uva.nl/personal/pure/en/publications/gpt2mvs-generative-pretrained-transformer2-for-multimodal-video-summarization(473ca26e-7491-4cfe-8af6-1b7d3febd810).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICMR '21: proceedings of the 2021 International Conference on Multimedia Retrieval : August 21-24, 2021, Taipei, Taiwan, 580 - 589","raw_type":"info:eu-repo/semantics/conferencepaper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W79139011","https://openalex.org/W1568869800","https://openalex.org/W1926243429","https://openalex.org/W1933349210","https://openalex.org/W1984087718","https://openalex.org/W1987366351","https://openalex.org/W2032342062","https://openalex.org/W2103605470","https://openalex.org/W2108598243","https://openalex.org/W2115857089","https://openalex.org/W2126718454","https://openalex.org/W2156044652","https://openalex.org/W2194775991","https://openalex.org/W2250189634","https://openalex.org/W2250539671","https://openalex.org/W2334175399","https://openalex.org/W2525693952","https://openalex.org/W2529272619","https://openalex.org/W2625136576","https://openalex.org/W2737677090","https://openalex.org/W2751178015","https://openalex.org/W2766630207","https://openalex.org/W2768010949","https://openalex.org/W2776277180","https://openalex.org/W2781922022","https://openalex.org/W2788303226","https://openalex.org/W2798970487","https://openalex.org/W2883359488","https://openalex.org/W2883872876","https://openalex.org/W2897091983","https://openalex.org/W2903758693","https://openalex.org/W2962677647","https://openalex.org/W2963026017","https://openalex.org/W2963220254","https://openalex.org/W2963919999","https://openalex.org/W2964018078","https://openalex.org/W2964045651","https://openalex.org/W2964167369","https://openalex.org/W2980884691","https://openalex.org/W2982672255","https://openalex.org/W2984001224","https://openalex.org/W2997333136","https://openalex.org/W2999428529","https://openalex.org/W3009353929","https://openalex.org/W3027431227","https://openalex.org/W3033386097","https://openalex.org/W3103014337","https://openalex.org/W3119639728","https://openalex.org/W3194346615","https://openalex.org/W3196479518","https://openalex.org/W4234552385"],"related_works":["https://openalex.org/W2366403280","https://openalex.org/W1495108544","https://openalex.org/W2091301346","https://openalex.org/W3148229873","https://openalex.org/W2150160875","https://openalex.org/W4242223894","https://openalex.org/W1517524280","https://openalex.org/W4389760904","https://openalex.org/W4317547544","https://openalex.org/W4313395829"],"abstract_inverted_index":{"Traditional":[0],"video":[1,6,25,39,45,59,74,83,114,126,137],"summarization":[2,26,40,138],"methods":[3,14,31],"generate":[4],"fixed":[5],"representations":[7,102],"regardless":[8],"of":[9,29,54,58,81,111,133,152,159],"user":[10],"interest.":[11],"Therefore":[12],"such":[13],"limit":[15],"users'":[16],"expectations":[17],"in":[18,154],"content":[19],"search":[20],"and":[21,72,99,124,156],"exploration":[22],"scenarios.":[23],"Multi-modal":[24],"is":[27,41,50,64,76,91,147],"one":[28,53],"the":[30,55,69,73,79,131,134,144,150,163],"utilized":[32],"to":[33,43,103],"address":[34],"this":[35,86,105],"problem.":[36],"When":[37],"multi-modal":[38,82,117,136],"used":[42],"help":[44],"exploration,":[46],"a":[47,88,95,112,125],"text-based":[48,70],"query":[49,71],"considered":[51],"as":[52,62],"main":[56],"drivers":[57],"summary":[60,115,127],"generation,":[61],"it":[63],"user-defined.":[65],"Thus,":[66],"encoding":[67],"both":[68],"effectively":[75],"important":[77],"for":[78],"task":[80],"summarization.":[84],"In":[85],"work,":[87],"new":[89],"method":[90],"proposed":[92,108,145],"that":[93,143],"uses":[94],"specialized":[96],"attention":[97,118,122],"network":[98],"contextualized":[100,113],"word":[101],"tackle":[104],"task.":[106],"The":[107],"model":[109,146],"consists":[110],"controller,":[116],"mechanisms,":[119],"an":[120],"interactive":[121],"network,":[123],"generator.":[128],"Based":[129],"on":[130],"evaluation":[132],"existing":[135],"benchmark,":[139],"experimental":[140],"results":[141],"show":[142],"effective":[148],"with":[149,162],"increase":[151,158],"+5.88%":[153],"accuracy":[155],"+4.06%":[157],"F1-score,":[160],"compared":[161],"state-of-the-art":[164],"method.":[165],"https://github.com/Jhhuangkay/GPT2MVS-Generative-Pre-trained-Transformer-2-for-Multi-modal-Video-Summarization.":[166]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":2}],"updated_date":"2026-03-16T09:10:04.655348","created_date":"2025-10-10T00:00:00"}