{"id":"https://openalex.org/W4410536545","doi":"https://doi.org/10.1109/tcsvt.2025.3571788","title":"LMM-VQA: Advancing Video Quality Assessment With Large Multimodal Models","display_name":"LMM-VQA: Advancing Video Quality Assessment With Large Multimodal Models","publication_year":2025,"publication_date":"2025-05-20","ids":{"openalex":"https://openalex.org/W4410536545","doi":"https://doi.org/10.1109/tcsvt.2025.3571788"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2025.3571788","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3571788","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-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/A5107454196","display_name":"Qihang Ge","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qihang Ge","raw_affiliation_strings":["Institute of Image Communication and Information Processing, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0003-2981-7460","affiliations":[{"raw_affiliation_string":"Institute of Image Communication and Information Processing, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044700284","display_name":"Wei Sun","orcid":"https://orcid.org/0000-0001-8162-1949"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Sun","raw_affiliation_strings":["School of Communication and Electronic Engineering, East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-8162-1949","affiliations":[{"raw_affiliation_string":"School of Communication and Electronic Engineering, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100433773","display_name":"Yu Zhang","orcid":"https://orcid.org/0009-0005-4213-8045"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Zhang","raw_affiliation_strings":["MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","AI Institute, MoE Key Laboratory of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"AI Institute, MoE Key Laboratory of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100778543","display_name":"Yunhao Li","orcid":"https://orcid.org/0000-0002-7337-1748"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunhao Li","raw_affiliation_strings":["Institute of Image Communication and Information Processing, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-7337-1748","affiliations":[{"raw_affiliation_string":"Institute of Image Communication and Information Processing, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060080802","display_name":"Zhongpeng Ji","orcid":"https://orcid.org/0000-0002-9532-7035"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongpeng Ji","raw_affiliation_strings":["Huawei Technologies, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-9532-7035","affiliations":[{"raw_affiliation_string":"Huawei Technologies, Shanghai, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085976829","display_name":"Fengyu Sun","orcid":"https://orcid.org/0009-0007-8258-8109"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fengyu Sun","raw_affiliation_strings":["Huawei Technologies, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies, Shanghai, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012650575","display_name":"Shangling Jui","orcid":"https://orcid.org/0000-0002-1047-4264"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shangling Jui","raw_affiliation_strings":["Huawei Technologies, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-1047-4264","affiliations":[{"raw_affiliation_string":"Huawei Technologies, Shanghai, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043405654","display_name":"Xiongkuo Min","orcid":"https://orcid.org/0000-0001-5693-0416"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiongkuo Min","raw_affiliation_strings":["Institute of Image Communication and Information Processing, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-5693-0416","affiliations":[{"raw_affiliation_string":"Institute of Image Communication and Information Processing, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064168853","display_name":"Guangtao Zhai","orcid":"https://orcid.org/0000-0001-8165-9322"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangtao Zhai","raw_affiliation_strings":["Institute of Image Communication and Information Processing, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-8165-9322","affiliations":[{"raw_affiliation_string":"Institute of Image Communication and Information Processing, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":11.4829,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.98809908,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"35","issue":"11","first_page":"11083","last_page":"11096"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11165","display_name":"Image and Video Quality Assessment","score":0.9979000091552734,"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":0.9979000091552734,"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/T11659","display_name":"Advanced Image Fusion Techniques","score":0.9847000241279602,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9753000140190125,"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":0.7146276235580444},{"id":"https://openalex.org/keywords/video-quality","display_name":"Video quality","score":0.5521456599235535},{"id":"https://openalex.org/keywords/quality-assessment","display_name":"Quality assessment","score":0.5396945476531982},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.497974157333374},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4090225398540497},{"id":"https://openalex.org/keywords/evaluation-methods","display_name":"Evaluation methods","score":0.14488548040390015},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.14105108380317688},{"id":"https://openalex.org/keywords/operations-management","display_name":"Operations management","score":0.0857267677783966},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08544892072677612}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7146276235580444},{"id":"https://openalex.org/C103910844","wikidata":"https://www.wikidata.org/wiki/Q2631256","display_name":"Video quality","level":3,"score":0.5521456599235535},{"id":"https://openalex.org/C3020001037","wikidata":"https://www.wikidata.org/wiki/Q836575","display_name":"Quality assessment","level":3,"score":0.5396945476531982},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.497974157333374},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4090225398540497},{"id":"https://openalex.org/C3018395757","wikidata":"https://www.wikidata.org/wiki/Q1379672","display_name":"Evaluation methods","level":2,"score":0.14488548040390015},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.14105108380317688},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0857267677783966},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08544892072677612},{"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/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:10.1109/tcsvt.2025.3571788","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3571788","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46000000834465027,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G1583650166","display_name":null,"funder_award_id":"62132006","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3386619338","display_name":null,"funder_award_id":"62301316","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5909587017","display_name":null,"funder_award_id":"SL2020ZD102","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6337704764","display_name":null,"funder_award_id":"22DZ2229005","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8668751174","display_name":null,"funder_award_id":"62225112","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8830604195","display_name":null,"funder_award_id":"62271312","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W1971014006","https://openalex.org/W1979451680","https://openalex.org/W1982471090","https://openalex.org/W2044338482","https://openalex.org/W2048042940","https://openalex.org/W2059823394","https://openalex.org/W2080511792","https://openalex.org/W2096621047","https://openalex.org/W2102166818","https://openalex.org/W2148848374","https://openalex.org/W2157331557","https://openalex.org/W2158100927","https://openalex.org/W2162692770","https://openalex.org/W2194363988","https://openalex.org/W2194775991","https://openalex.org/W2250384498","https://openalex.org/W2314091824","https://openalex.org/W2611434713","https://openalex.org/W2617811665","https://openalex.org/W2791258091","https://openalex.org/W2803532311","https://openalex.org/W2886641317","https://openalex.org/W2895868297","https://openalex.org/W2939995367","https://openalex.org/W2950154603","https://openalex.org/W2963398015","https://openalex.org/W2965644659","https://openalex.org/W2990503944","https://openalex.org/W3002992380","https://openalex.org/W3017136408","https://openalex.org/W3030380536","https://openalex.org/W3030701471","https://openalex.org/W3035595647","https://openalex.org/W3035712445","https://openalex.org/W3169674094","https://openalex.org/W3174089122","https://openalex.org/W3174437687","https://openalex.org/W3174722860","https://openalex.org/W3193919962","https://openalex.org/W3195201937","https://openalex.org/W4213342923","https://openalex.org/W4225292576","https://openalex.org/W4296558729","https://openalex.org/W4312560592","https://openalex.org/W4312818079","https://openalex.org/W4322706707","https://openalex.org/W4385572634","https://openalex.org/W4386071544","https://openalex.org/W4387967918","https://openalex.org/W4389519587","https://openalex.org/W4390874113","https://openalex.org/W4394841775","https://openalex.org/W4401070165","https://openalex.org/W4401343632","https://openalex.org/W4401726215","https://openalex.org/W4402660133","https://openalex.org/W4402671548","https://openalex.org/W4402727669","https://openalex.org/W4402727764","https://openalex.org/W4402727885","https://openalex.org/W4402769976","https://openalex.org/W4402916139","https://openalex.org/W4403002096","https://openalex.org/W4403601500","https://openalex.org/W4403722527"],"related_works":["https://openalex.org/W1972391593","https://openalex.org/W2062936665","https://openalex.org/W2054084867","https://openalex.org/W4234477160","https://openalex.org/W3201904914","https://openalex.org/W2140624161","https://openalex.org/W2007326877","https://openalex.org/W4243824339","https://openalex.org/W1513749200","https://openalex.org/W4379929470"],"abstract_inverted_index":{"The":[0],"explosive":[1],"growth":[2],"of":[3,28,86,167,233,247],"videos":[4],"on":[5,258],"streaming":[6,29],"media":[7],"platforms":[8],"has":[9],"underscored":[10],"the":[11,26,40,45,81,90,130,164,174,178,185,190,199,206,212,244,248],"urgent":[12],"need":[13],"for":[14,72,123,145,181,198],"effective":[15],"video":[16,42,260],"quality":[17,27,131,165,207,213],"assessment":[18],"(VQA)":[19],"algorithms":[20],"to":[21,39,56,79,88,156,162,204,243],"monitor":[22],"and":[23,44,48,137,141,159,189,251],"perceptually":[24],"optimize":[25],"videos.":[30],"However,":[31],"VQA":[32,91,146,227],"remains":[33],"an":[34,96,230],"extremely":[35],"challenging":[36],"task":[37,140],"due":[38,242],"diverse":[41],"content":[43],"complex":[46],"spatial":[47,158],"temporal":[49,160],"distortions,":[50],"thus":[51],"necessitating":[52],"more":[53],"advanced":[54,245],"methods":[55],"address":[57],"these":[58],"issues.":[59],"Nowadays,":[60],"large":[61,200],"multimodal":[62,83],"models":[63],"(LMMs),":[64],"such":[65],"as":[66,196,209,211],"GPT-4V,":[67],"have":[68],"exhibited":[69],"strong":[70],"capabilities":[71],"various":[73],"visual":[74,120,187],"understanding":[75,261],"tasks,":[76,262],"motivating":[77],"us":[78],"leverage":[80],"powerful":[82],"representation":[84],"ability":[85,237],"LMMs":[87],"solve":[89],"task.":[92],"Therefore,":[93],"we":[94,128,150],"propose":[95],"<italic":[97,100,106,109,219],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[98,101,103,107,110,220],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">L</i>arge":[99],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">M</i>ulti-<italic":[102],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">M</i>odal":[104],"based":[105],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">V</i>ideo":[108],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Q</i>uality":[111],"Assessment":[112],"(LMM-VQA)":[113],"model,":[114],"which":[115,169],"introduces":[116],"a":[117,135,152],"novel":[118],"spatiotemporal":[119,153,179,249],"modeling":[121],"strategy":[122],"quality-aware":[124],"feature":[125],"extraction.":[126],"Specifically,":[127],"reformulate":[129],"regression":[132],"problem":[133],"into":[134,173],"question":[136],"answering":[138],"(Q&A)":[139],"construct":[142],"Q&A":[143],"prompts":[144],"instruction":[147],"tuning.":[148],"Then,":[149],"design":[151,246],"vision":[154],"encoder":[155,250],"extract":[157],"features":[161],"represent":[163],"characteristics":[166],"videos,":[168],"are":[170,194],"subsequently":[171],"mapped":[172],"language":[175,201],"space":[176],"by":[177],"projector":[180],"modality":[182],"alignment.":[183],"Finally,":[184],"aligned":[186],"tokens":[188,193],"quality-inquired":[191],"text":[192],"aggregated":[195],"inputs":[197],"model":[202],"(LLM)":[203],"generate":[205],"score":[208],"well":[210,257],"level.":[214],"Extensive":[215],"experiments":[216],"demonstrate":[217],"that":[218],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">LMM-VQA</i>":[221],"achieves":[222],"state-of-the-art":[223],"performance":[224],"across":[225],"five":[226],"benchmarks,":[228],"exhibiting":[229],"average":[231],"improvement":[232],"5%":[234],"in":[235],"generalization":[236],"over":[238],"existing":[239],"methods.":[240],"Furthermore,":[241],"projector,":[252],"LMM-VQA":[253],"also":[254],"performs":[255],"exceptionally":[256],"general":[259],"further":[263],"validating":[264],"its":[265],"effectiveness.":[266],"Our":[267],"code":[268],"will":[269],"be":[270],"released":[271],"at":[272],"https://github.com/Sueqk/LMM-VQA.":[273]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":9}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
