{"id":"https://openalex.org/W4399418503","doi":"https://doi.org/10.1145/3652583.3657582","title":"Multi-modal Video Summarization","display_name":"Multi-modal Video Summarization","publication_year":2024,"publication_date":"2024-05-30","ids":{"openalex":"https://openalex.org/W4399418503","doi":"https://doi.org/10.1145/3652583.3657582"},"language":"en","primary_location":{"id":"doi:10.1145/3652583.3657582","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3657582","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3657582","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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/10.1145/3652583.3657582","any_repository_has_fulltext":null},"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"],"raw_orcid":"https://orcid.org/0000-0001-7943-2591","affiliations":[{"raw_affiliation_string":"University of Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I4210135670","https://openalex.org/I887064364"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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":0.9523,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.75234375,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1214","last_page":"1218"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","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/T11439","display_name":"Video Analysis and Summarization","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/T11309","display_name":"Music and Audio Processing","score":0.9973999857902527,"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/T12720","display_name":"Multimedia Communication and Technology","score":0.9901999831199646,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.9271112680435181},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8484538793563843},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5442587733268738},{"id":"https://openalex.org/keywords/multi-document-summarization","display_name":"Multi-document summarization","score":0.46662959456443787},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4545421600341797},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.43950629234313965},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.43883147835731506},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4214218258857727},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3264699876308441}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.9271112680435181},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8484538793563843},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5442587733268738},{"id":"https://openalex.org/C134714966","wikidata":"https://www.wikidata.org/wiki/Q6934448","display_name":"Multi-document summarization","level":3,"score":0.46662959456443787},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4545421600341797},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.43950629234313965},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.43883147835731506},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4214218258857727},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3264699876308441},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3652583.3657582","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3657582","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3657582","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3652583.3657582","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3657582","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3657582","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.75}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399418503.pdf"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W2529272619","https://openalex.org/W2766630207","https://openalex.org/W2768010949","https://openalex.org/W2798970487","https://openalex.org/W2963026017","https://openalex.org/W2963919999","https://openalex.org/W2964018078","https://openalex.org/W2964045651","https://openalex.org/W2964167369","https://openalex.org/W2971202647","https://openalex.org/W2999428529","https://openalex.org/W3027431227","https://openalex.org/W3033386097","https://openalex.org/W3194346615","https://openalex.org/W3196479518","https://openalex.org/W3198455660","https://openalex.org/W4234552385","https://openalex.org/W4281482989","https://openalex.org/W4293519400","https://openalex.org/W4312748990","https://openalex.org/W4385815568"],"related_works":["https://openalex.org/W3164984162","https://openalex.org/W2104677027","https://openalex.org/W2902627734","https://openalex.org/W2112885393","https://openalex.org/W2173208124","https://openalex.org/W2568827738","https://openalex.org/W1990695371","https://openalex.org/W2365100044","https://openalex.org/W1943954554","https://openalex.org/W2099859325"],"abstract_inverted_index":{"The":[0],"increasing":[1],"prevalence":[2],"of":[3,42,51,116,181,220],"video":[4,20,78,117,133,158,185,209],"content":[5,29,96,173],"on":[6,84],"platforms":[7],"like":[8,60],"YouTube":[9],"and":[10,32,63,68,75,94,171],"Vimeo":[11],"has":[12,225],"led":[13],"to":[14,26,90,112,130,150,156,197],"a":[15,36,145,152,189,207,227],"growing":[16],"demand":[17],"for":[18,73,165,200],"effective":[19],"summarization":[21,79,159,186,210],"techniques.":[22],"These":[23,161],"methods":[24,80,162],"aim":[25],"extract":[27],"relevant":[28],"from":[30],"videos":[31],"present":[33,97],"it":[34,231],"in":[35,58,98,184,216,241],"condensed":[37],"form,":[38],"addressing":[39],"the":[40,49,52,114,126,142,157,176,179,217],"challenge":[41,180],"information":[43,122],"overload":[44],"faced":[45],"by":[46,187],"users.":[47],"However,":[48],"quality":[50,155],"generated":[53],"summaries":[54,70,134],"is":[55,213],"crucial,":[56],"especially":[57],"fields":[59],"forensics,":[61],"journalism,":[62],"sports":[64],"analysis,":[65],"where":[66],"accurate":[67],"concise":[69],"are":[71],"essential":[72],"decision-making":[74],"analysis.":[76],"Traditional":[77],"often":[81],"rely":[82],"solely":[83],"visual":[85,124],"information,":[86],"limiting":[87],"their":[88,233],"ability":[89],"capture":[91],"textual":[92,121],"cues":[93],"emotional":[95],"videos.":[99],"To":[100],"overcome":[101],"this":[102,104,221],"limitation,":[103],"thesis":[105,143,177],"proposes":[106],"leveraging":[107],"text-based":[108],"queries":[109],"as":[110],"context":[111],"enhance":[113],"effectiveness":[115],"summarization.":[118],"By":[119],"incorporating":[120],"alongside":[123],"data,":[125],"proposed":[127,206],"approach":[128,192],"aims":[129],"generate":[131,198],"query-dependent":[132],"that":[135,193],"better":[136],"align":[137],"with":[138],"users'":[139],"requirements.":[140],"Furthermore,":[141],"leverages":[144,194],"novel":[146],"conditional":[147],"modeling":[148],"perspective":[149],"impart":[151],"more":[153],"human-like":[154],"process.":[160],"hold":[163],"promise":[164],"various":[166],"applications,":[167],"including":[168],"documentary":[169],"filmmaking":[170],"educational":[172],"creation.":[174],"Additionally,":[175],"addresses":[178],"data":[182],"scarcity":[183],"proposing":[188],"self-supervised":[190],"learning":[191],"pretext":[195],"tasks":[196],"pseudo-labels":[199],"model":[201,236],"training.":[202],"In":[203],"2020,":[204],"we":[205],"query-controllable":[208],"technology,":[211],"which":[212],"elaborated":[214],"upon":[215],"second":[218],"chapter":[219],"thesis.":[222],"Notably,":[223],"Google":[224],"adopted":[226],"similar":[228],"feature,":[229],"integrating":[230],"into":[232],"large":[234],"language":[235],"(LLM)":[237],"Gemini":[238],"Pro-1.5":[239],"version,":[240],"2024.":[242]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
