{"id":"https://openalex.org/W4412877108","doi":"https://doi.org/10.1145/3711896.3737203","title":"<i>COEF-VQ:</i> Cost-Efficient Video Quality Understanding through a Cascaded Multimodal LLM Framework","display_name":"<i>COEF-VQ:</i> Cost-Efficient Video Quality Understanding through a Cascaded Multimodal LLM Framework","publication_year":2025,"publication_date":"2025-08-03","ids":{"openalex":"https://openalex.org/W4412877108","doi":"https://doi.org/10.1145/3711896.3737203"},"language":"en","primary_location":{"id":"doi:10.1145/3711896.3737203","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3737203","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3737203","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","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/10.1145/3711896.3737203","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102098401","display_name":"Dong Xin","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Xin Dong","raw_affiliation_strings":["ByteDance Inc., San Jose, CA, USA"],"affiliations":[{"raw_affiliation_string":"ByteDance Inc., San Jose, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035753061","display_name":"Sen Jia","orcid":"https://orcid.org/0000-0001-9742-5037"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sen Jia","raw_affiliation_strings":["ByteDance Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"ByteDance Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044562197","display_name":"M Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ming Rui Wang","raw_affiliation_strings":["ByteDance Inc., Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"ByteDance Inc., Singapore, Singapore","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101759398","display_name":"Yan Li","orcid":"https://orcid.org/0000-0003-1882-3331"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan Li","raw_affiliation_strings":["ByteDance Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"ByteDance Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029181844","display_name":"Zhenheng Yang","orcid":"https://orcid.org/0000-0003-0303-5885"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhenheng Yang","raw_affiliation_strings":["ByteDance Inc., San Jose, CA, USA"],"affiliations":[{"raw_affiliation_string":"ByteDance Inc., San Jose, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119175153","display_name":"Bingfeng Deng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bingfeng Deng","raw_affiliation_strings":["ByteDance Inc., Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"ByteDance Inc., Singapore, Singapore","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013831155","display_name":"Hongyu Xiong","orcid":"https://orcid.org/0000-0001-6699-5192"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongyu Xiong","raw_affiliation_strings":["ByteDance Inc., San Jose, CA, USA"],"affiliations":[{"raw_affiliation_string":"ByteDance Inc., San Jose, CA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5102098401"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18285531,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4387","last_page":"4395"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11165","display_name":"Image and Video Quality Assessment","score":0.9997000098228455,"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":0.9997000098228455,"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/T11019","display_name":"Image Enhancement Techniques","score":0.9994999766349792,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9993000030517578,"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":0.7201288342475891},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.534314751625061},{"id":"https://openalex.org/keywords/video-quality","display_name":"Video quality","score":0.4421892762184143},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.349581778049469},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.32563427090644836},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09971743822097778}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7201288342475891},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.534314751625061},{"id":"https://openalex.org/C103910844","wikidata":"https://www.wikidata.org/wiki/Q2631256","display_name":"Video quality","level":3,"score":0.4421892762184143},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.349581778049469},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32563427090644836},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09971743822097778},{"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},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3711896.3737203","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3737203","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3737203","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3711896.3737203","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3737203","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3737203","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.41999998688697815,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412877108.pdf","grobid_xml":"https://content.openalex.org/works/W4412877108.grobid-xml"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W3129831491","https://openalex.org/W3138516171","https://openalex.org/W3173220247","https://openalex.org/W4390873312","https://openalex.org/W4402727885"],"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":{"Recently,":[0],"with":[1,182],"the":[2,30,63,91,114,125,135,141,170],"emergence":[3],"of":[4,32,118,127,148],"recent":[5],"Multimodal":[6],"Large":[7],"Language":[8],"Model":[9],"(MLLM)":[10],"technology,":[11],"it":[12],"has":[13],"become":[14],"possible":[15],"to":[16,41,57,90,156,165],"exploit":[17],"its":[18,209],"video":[19,59,136,157,190],"understanding":[20,61],"capability":[21],"on":[22,62,151],"different":[23],"classification":[24,116],"tasks.":[25],"In":[26,45],"practice,":[27],"we":[28,39,48,129],"face":[29],"difficulty":[31],"huge":[33],"requirements":[34],"for":[35,96,103],"GPU":[36,110],"resource":[37,184],"if":[38],"need":[40],"deploy":[42,130],"MLLMs":[43],"online.":[44],"this":[46,131],"paper,":[47],"propose":[49],"COEF-VQ,":[50,128],"a":[51,78,119,146,196],"novel":[52],"cascaded":[53],"MLLM":[54,95,121],"framework":[55,107,133],"designed":[56],"enhance":[58],"quality":[60,158],"short-video":[64,142],"platform":[65,138,180],"while":[66,112],"optimizing":[67],"computational":[68],"efficiency.":[69],"Our":[70],"approach":[71],"integrates":[72],"an":[73],"entropy-based":[74],"pre-filtering":[75],"stage,":[76],"where":[77],"lightweight":[79],"model":[80],"assesses":[81],"uncertainty":[82],"and":[83,144,177],"selectively":[84],"filters":[85],"cases":[86],"before":[87],"passing":[88],"them":[89],"more":[92],"computationally":[93],"intensive":[94],"final":[97],"evaluation.":[98],"By":[99],"prioritizing":[100],"high-uncertainty":[101],"samples":[102],"deeper":[104],"analysis,":[105],"our":[106],"significantly":[108,186],"reduces":[109],"usage":[111],"maintaining":[113],"strong":[115],"performance":[117,167],"full":[120],"deployment.":[122],"To":[123],"demonstrate":[124],"effectiveness":[126],"new":[132],"onto":[134],"management":[137],"(VMP)":[139],"at":[140],"platform,":[143],"perform":[145],"series":[147],"detailed":[149],"experiments":[150],"two":[152,175],"in-house":[153],"tasks":[154,176],"related":[155],"understanding.":[159],"We":[160],"show":[161],"that":[162],"COEF-VQ":[163],"leads":[164],"substantial":[166],"gains":[168],"from":[169],"offline":[171],"evaluation":[172],"in":[173,195],"these":[174],"effectively":[178],"enhances":[179],"safety":[181],"limit":[183],"consumption,":[185],"reducing":[187],"inappropriate":[188],"content":[189],"view":[191],"rate":[192],"by":[193],"9.9%":[194],"online":[197],"A/B":[198],"test":[199],"without":[200],"affecting":[201],"engagement.":[202],"Post-launch":[203],"monitoring":[204],"confirmed":[205],"sustained":[206],"improvements,":[207],"validating":[208],"real-world":[210],"impact.":[211]},"counts_by_year":[],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}