{"id":"https://openalex.org/W4408354287","doi":"https://doi.org/10.1109/icassp49660.2025.10888524","title":"An Ensemble Approach to Short-form Video Quality Assessment Using Multimodal LLM","display_name":"An Ensemble Approach to Short-form Video Quality Assessment Using Multimodal LLM","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354287","doi":"https://doi.org/10.1109/icassp49660.2025.10888524"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888524","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888524","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5062836696","display_name":"Wen Wen","orcid":"https://orcid.org/0000-0002-6457-9176"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Wen Wen","raw_affiliation_strings":["City University of Hong Kong,Hong Kong SAR"],"affiliations":[{"raw_affiliation_string":"City University of Hong Kong,Hong Kong SAR","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100449864","display_name":"Yilin Wang","orcid":"https://orcid.org/0000-0003-4031-8753"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yilin Wang","raw_affiliation_strings":["Google Inc.,Mountain View,CA,USA"],"affiliations":[{"raw_affiliation_string":"Google Inc.,Mountain View,CA,USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090695020","display_name":"Neil Birkbeck","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Neil Birkbeck","raw_affiliation_strings":["Google Inc.,Mountain View,CA,USA"],"affiliations":[{"raw_affiliation_string":"Google Inc.,Mountain View,CA,USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060507975","display_name":"Balu Adsumilli","orcid":"https://orcid.org/0000-0002-5187-6331"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Balu Adsumilli","raw_affiliation_strings":["Google Inc.,Mountain View,CA,USA"],"affiliations":[{"raw_affiliation_string":"Google Inc.,Mountain View,CA,USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5062836696"],"corresponding_institution_ids":["https://openalex.org/I168719708"],"apc_list":null,"apc_paid":null,"fwci":1.319,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.77984961,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11165","display_name":"Image and Video Quality Assessment","score":0.9951000213623047,"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/T11165","display_name":"Image and Video Quality Assessment","score":0.9951000213623047,"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":0.9771999716758728,"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/T13731","display_name":"Advanced Computing and Algorithms","score":0.9077000021934509,"subfield":{"id":"https://openalex.org/subfields/3322","display_name":"Urban Studies"},"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/computer-science","display_name":"Computer science","score":0.7618979811668396},{"id":"https://openalex.org/keywords/video-quality","display_name":"Video quality","score":0.5670751929283142},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5476764440536499},{"id":"https://openalex.org/keywords/quality-assessment","display_name":"Quality assessment","score":0.5144691467285156},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45882439613342285},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3582730293273926},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.15260529518127441},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09054774045944214},{"id":"https://openalex.org/keywords/evaluation-methods","display_name":"Evaluation methods","score":0.08914104104042053}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7618979811668396},{"id":"https://openalex.org/C103910844","wikidata":"https://www.wikidata.org/wiki/Q2631256","display_name":"Video quality","level":3,"score":0.5670751929283142},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5476764440536499},{"id":"https://openalex.org/C3020001037","wikidata":"https://www.wikidata.org/wiki/Q836575","display_name":"Quality assessment","level":3,"score":0.5144691467285156},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45882439613342285},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3582730293273926},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.15260529518127441},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09054774045944214},{"id":"https://openalex.org/C3018395757","wikidata":"https://www.wikidata.org/wiki/Q1379672","display_name":"Evaluation methods","level":2,"score":0.08914104104042053},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888524","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888524","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.46000000834465027,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W2048042940","https://openalex.org/W2194363988","https://openalex.org/W2890391014","https://openalex.org/W2939995367","https://openalex.org/W2950154603","https://openalex.org/W2965644659","https://openalex.org/W2968618681","https://openalex.org/W3030701471","https://openalex.org/W3169674094","https://openalex.org/W3174437687","https://openalex.org/W3193919962","https://openalex.org/W4225292576","https://openalex.org/W4312818079","https://openalex.org/W4386071544","https://openalex.org/W4387068132","https://openalex.org/W4390874113","https://openalex.org/W4392822465","https://openalex.org/W4394841775","https://openalex.org/W4402704606","https://openalex.org/W4402727669","https://openalex.org/W4402727764","https://openalex.org/W4402753893","https://openalex.org/W4402772655","https://openalex.org/W4402915565","https://openalex.org/W4403844348","https://openalex.org/W4404536559","https://openalex.org/W4404613040","https://openalex.org/W4410536545","https://openalex.org/W6790830454","https://openalex.org/W6810334672","https://openalex.org/W6849177959","https://openalex.org/W6851592950","https://openalex.org/W6851950068","https://openalex.org/W6856810635","https://openalex.org/W6857055646","https://openalex.org/W6858147810","https://openalex.org/W6859870462","https://openalex.org/W6861503643","https://openalex.org/W6870687016"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","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":{"The":[0],"rise":[1],"of":[2,56,116],"short-form":[3,49],"videos,":[4],"characterized":[5],"by":[6,129],"diverse":[7],"content,":[8],"editing":[9],"styles,":[10],"and":[11,58,61,76,98],"artifacts,":[12],"poses":[13],"substantial":[14],"challenges":[15],"for":[16,30,48],"learning-based":[17,88],"blind":[18],"video":[19,50,123],"quality":[20,51],"assessment":[21],"(BVQA)":[22],"models.":[23,69,101],"Multimodal":[24],"large":[25],"language":[26],"models":[27,139],"(MLLMs),":[28],"renowned":[29],"their":[31],"superior":[32,105],"generalization":[33,106],"capabilities,":[34],"present":[35],"a":[36,45,86],"promising":[37],"solution.":[38],"This":[39],"paper":[40],"focuses":[41],"on":[42,63],"effectively":[43],"leveraging":[44],"pretrained":[46],"MLLM":[47,66,97],"assessment,":[52],"regarding":[53],"the":[54,65,80,96,109,114],"impacts":[55],"pre-processing":[57,75],"response":[59],"variability,":[60],"insights":[62],"combining":[64],"with":[67,108],"BVQA":[68,100,131,138],"We":[70],"first":[71],"investigated":[72],"how":[73],"frame":[74],"sampling":[77],"techniques":[78],"influence":[79],"MLLM\u2019s":[81],"performance.":[82],"Then,":[83],"we":[84],"introduced":[85],"lightweight":[87],"ensemble":[89,111,118],"method":[90],"that":[91,121],"adaptively":[92],"integrates":[93],"predictions":[94],"from":[95],"state-of-the-art":[99],"Our":[102],"results":[103],"demonstrated":[104],"performance":[107],"proposed":[110],"approach.":[112],"Furthermore,":[113],"analysis":[115],"content-aware":[117],"weights":[119],"highlighted":[120],"some":[122],"characteristics":[124],"are":[125],"not":[126],"fully":[127],"represented":[128],"existing":[130],"models,":[132],"revealing":[133],"potential":[134],"directions":[135],"to":[136],"improve":[137],"further.":[140]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}