{"id":"https://openalex.org/W4416965997","doi":"https://doi.org/10.1109/tmm.2025.3639890","title":"Exploring Cross-Modal Mutual Prompt Learning for Video Quality Assessment","display_name":"Exploring Cross-Modal Mutual Prompt Learning for Video Quality Assessment","publication_year":2025,"publication_date":"2025-12-03","ids":{"openalex":"https://openalex.org/W4416965997","doi":"https://doi.org/10.1109/tmm.2025.3639890"},"language":null,"primary_location":{"id":"doi:10.1109/tmm.2025.3639890","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3639890","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","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/A5063520709","display_name":"Pengfei Chen","orcid":"https://orcid.org/0000-0002-0509-3782"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Pengfei Chen","raw_affiliation_strings":["School of Artificial Intelligence, Xidian University, Xi&#x2019;an, China","School of Artificial Intelligence, Xidian University, Xi&#x0027;an, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Xidian University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"School of Artificial Intelligence, Xidian University, Xi&#x0027;an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033615240","display_name":"Leida Li","orcid":"https://orcid.org/0000-0001-9069-8796"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Leida Li","raw_affiliation_strings":["School of Artificial Intelligence, Xidian University, Xi&#x2019;an, China","School of Artificial Intelligence, Xidian University, Xi&#x0027;an, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Xidian University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"School of Artificial Intelligence, Xidian University, Xi&#x0027;an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074780876","display_name":"Jinjian Wu","orcid":"https://orcid.org/0000-0001-7501-0009"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinjian Wu","raw_affiliation_strings":["School of Artificial Intelligence, Xidian University, Xi&#x2019;an, China","School of Artificial Intelligence, Xidian University, Xi&#x0027;an, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Xidian University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"School of Artificial Intelligence, Xidian University, Xi&#x0027;an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101781341","display_name":"Jiebin Yan","orcid":"https://orcid.org/0000-0002-0337-6877"},"institutions":[{"id":"https://openalex.org/I59649739","display_name":"Jiangxi University of Finance and Economics","ror":"https://ror.org/03efmyj29","country_code":"CN","type":"education","lineage":["https://openalex.org/I59649739"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiebin Yan","raw_affiliation_strings":["School of Computing and Artificial Intelligence, Jiangxi University of Finance and Economics, Nanchang, China","School of Computing and Artificial Intelligence, Jiangxi University of Finance and Economics, Nanchang, Jiangxi, China"],"affiliations":[{"raw_affiliation_string":"School of Computing and Artificial Intelligence, Jiangxi University of Finance and Economics, Nanchang, China","institution_ids":["https://openalex.org/I59649739"]},{"raw_affiliation_string":"School of Computing and Artificial Intelligence, Jiangxi University of Finance and Economics, Nanchang, Jiangxi, China","institution_ids":["https://openalex.org/I59649739"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019388627","display_name":"Vinit Jakhetiya","orcid":"https://orcid.org/0000-0002-8325-4908"},"institutions":[{"id":"https://openalex.org/I4210127441","display_name":"Indian Institute of Technology Jammu","ror":"https://ror.org/02f0vsw63","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210127441"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Vinit Jakhetiya","raw_affiliation_strings":["Department of Computer Science and Engineering, Indian Institute of Technology Jammu, Jammu, India"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Indian Institute of Technology Jammu, Jammu, India","institution_ids":["https://openalex.org/I4210127441"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031504099","display_name":"Aladine Chetouani","orcid":"https://orcid.org/0000-0002-2066-4707"},"institutions":[{"id":"https://openalex.org/I12449238","display_name":"Universit\u00e9 d'Orl\u00e9ans","ror":"https://ror.org/014zrew76","country_code":"FR","type":"education","lineage":["https://openalex.org/I12449238"]},{"id":"https://openalex.org/I4210096782","display_name":"Laboratoire Pluridisciplinaire de Recherche en Ing\u00e9nierie des Syst\u00e8mes, M\u00e9canique et Energ\u00e9tique","ror":"https://ror.org/00sbth994","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12449238","https://openalex.org/I4210096782","https://openalex.org/I4210143826"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Aladine Chetouani","raw_affiliation_strings":["PRISME Laboratory, University of Orleans, Orleans, France"],"affiliations":[{"raw_affiliation_string":"PRISME Laboratory, University of Orleans, Orleans, France","institution_ids":["https://openalex.org/I12449238","https://openalex.org/I4210096782"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5063520709"],"corresponding_institution_ids":["https://openalex.org/I149594827"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.415434,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"28","issue":null,"first_page":"1253","last_page":"1265"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11165","display_name":"Image and Video Quality Assessment","score":0.9498999714851379,"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":0.9498999714851379,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.016599999740719795,"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":0.004100000020116568,"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/weighting","display_name":"Weighting","score":0.6158000230789185},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.557200014591217},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5256999731063843},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.44600000977516174},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.44179999828338623},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4320000112056732},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.3946000039577484},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.35040000081062317},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.32850000262260437}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.887499988079071},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.6158000230789185},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.557200014591217},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5325000286102295},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5256999731063843},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.44600000977516174},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.44179999828338623},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4332999885082245},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4320000112056732},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4153999984264374},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3946000039577484},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.374099999666214},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.35040000081062317},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3352000117301941},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.32850000262260437},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3264999985694885},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.3027999997138977},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.29760000109672546},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.29429998993873596},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2922999858856201},{"id":"https://openalex.org/C145644426","wikidata":"https://www.wikidata.org/wiki/Q169411","display_name":"Unified Modeling Language","level":3,"score":0.2856999933719635},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.27900001406669617},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C103910844","wikidata":"https://www.wikidata.org/wiki/Q2631256","display_name":"Video quality","level":3,"score":0.2630000114440918},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.26260000467300415},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2583000063896179},{"id":"https://openalex.org/C3020001037","wikidata":"https://www.wikidata.org/wiki/Q836575","display_name":"Quality assessment","level":3,"score":0.2529999911785126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2025.3639890","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3639890","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W1982471090","https://openalex.org/W2048042940","https://openalex.org/W2089875400","https://openalex.org/W2102166818","https://openalex.org/W2105187896","https://openalex.org/W2194363988","https://openalex.org/W2611434713","https://openalex.org/W2791258091","https://openalex.org/W2895868297","https://openalex.org/W2939995367","https://openalex.org/W2949956541","https://openalex.org/W2950154603","https://openalex.org/W2965644659","https://openalex.org/W2984287396","https://openalex.org/W3030701471","https://openalex.org/W3034572008","https://openalex.org/W3034601242","https://openalex.org/W3093244794","https://openalex.org/W3129593183","https://openalex.org/W3135532877","https://openalex.org/W3174437687","https://openalex.org/W3174722860","https://openalex.org/W3187196322","https://openalex.org/W3193919962","https://openalex.org/W3198377975","https://openalex.org/W3203711169","https://openalex.org/W3204829366","https://openalex.org/W4200139856","https://openalex.org/W4205991051","https://openalex.org/W4225292576","https://openalex.org/W4304014328","https://openalex.org/W4312238419","https://openalex.org/W4312558481","https://openalex.org/W4312560592","https://openalex.org/W4312614039","https://openalex.org/W4312651322","https://openalex.org/W4312818079","https://openalex.org/W4312960937","https://openalex.org/W4312978885","https://openalex.org/W4361856613","https://openalex.org/W4382462760","https://openalex.org/W4385901360","https://openalex.org/W4386071547","https://openalex.org/W4386076063","https://openalex.org/W4386076169","https://openalex.org/W4386158873","https://openalex.org/W4386790226","https://openalex.org/W4388145471","https://openalex.org/W4390241502","https://openalex.org/W4390872773","https://openalex.org/W4390874113","https://openalex.org/W4391547560","https://openalex.org/W4392405787","https://openalex.org/W4393033537","https://openalex.org/W4403791619","https://openalex.org/W4405844957","https://openalex.org/W7108228634"],"related_works":[],"abstract_inverted_index":{"Enhancing":[0],"video":[1],"quality":[2,82,148,169],"assessment":[3],"(VQA)":[4],"through":[5,127],"semantic":[6,29],"information":[7],"integration":[8],"is":[9,69,135,201],"a":[10,25,79,101,128],"critical":[11],"research":[12,15],"focus.":[13],"Recent":[14],"has":[16,51],"employed":[17],"the":[18,32,54,62,93,116,166,177],"Contrastive":[19],"Language-Image":[20],"Pre-training":[21],"(CLIP)":[22],"model":[23],"as":[24],"foundation":[26],"to":[27,57,106,119,146,164],"improve":[28],"perception.":[30],"However,":[31],"image-text":[33],"alignment":[34,60],"inherent":[35],"in":[36,44,66,87,190],"these":[37,108],"pre-trained":[38],"Vision-Language":[39],"(VL)":[40],"models":[41],"frequently":[42],"results":[43,175],"suboptimal":[45],"VQA":[46,75,88,185],"performance.":[47],"While":[48],"prompt":[49],"engineering":[50],"recently":[52],"targeted":[53],"language":[55,125,151],"component":[56],"address":[58],"this":[59,97,199],"issue,":[61],"unique":[63],"insights":[64],"resided":[65],"visual":[67,123,155],"analysis":[68],"still":[70],"overlooked":[71],"for":[72,198],"further":[73,158],"advancing":[74],"tasks.":[76],"Additionally,":[77],"seeking":[78],"trade-off":[80],"between":[81,122,168],"separability":[83,170],"and":[84,124,142,171],"domain":[85,172],"invariance":[86],"remains":[89],"largely":[90],"unresolved":[91],"within":[92,115],"VL":[94],"paradigm.":[95],"In":[96],"paper,":[98],"we":[99,111],"introduce":[100],"novel":[102],"cross-modal":[103],"prompt-based":[104],"approach":[105],"tackle":[107],"challenges.":[109],"Specifically,":[110],"propose":[112],"learnable":[113],"prompts":[114],"vision":[117],"branch":[118],"foster":[120],"synergy":[121],"modalities":[126],"language-to-vision":[129],"coupling":[130],"function.":[131],"The":[132,150,195],"multi-view":[133],"backbone":[134],"then":[136],"carefully":[137],"crafted":[138],"with":[139],"content":[140],"enhancement":[141],"distortion-aware":[143],"temporal":[144],"modulation":[145],"ensure":[147],"separability.":[149],"prompts,":[152],"derived":[153],"from":[154],"representations,":[156],"are":[157],"supported":[159],"by":[160],"adaptive":[161],"weighting":[162],"mechanisms":[163],"optimize":[165],"balance":[167],"invariance.":[173],"Experimental":[174],"demonstrate":[176],"effectiveness":[178],"of":[179],"our":[180],"proposed":[181],"method":[182],"over":[183],"leading":[184],"models,":[186],"showing":[187],"significant":[188],"improvements":[189],"generalization":[191],"across":[192],"diverse":[193],"datasets.":[194],"source":[196],"code":[197],"work":[200],"publicly":[202],"available":[203],"at":[204],"<uri":[205],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[206],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/cpf0079/CM2PL</uri>.":[207]},"counts_by_year":[],"updated_date":"2026-03-09T07:00:12.390032","created_date":"2025-12-03T00:00:00"}