{"id":"https://openalex.org/W4415708702","doi":"https://doi.org/10.1109/icme59968.2025.11210013","title":"MACA-VQA: Quality Assessment of UGC Videos via Multi-level Distortion Adaptation and Spatiotemporal Cross-Attention Fusion","display_name":"MACA-VQA: Quality Assessment of UGC Videos via Multi-level Distortion Adaptation and Spatiotemporal Cross-Attention Fusion","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708702","doi":"https://doi.org/10.1109/icme59968.2025.11210013"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11210013","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11210013","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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/A5100748112","display_name":"Bo Hu","orcid":"https://orcid.org/0000-0001-5874-3315"},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bo Hu","raw_affiliation_strings":["Chongqing University of Posts and Telecommunications,Key Laboratory of Image Cognition,Chongqing,China"],"affiliations":[{"raw_affiliation_string":"Chongqing University of Posts and Telecommunications,Key Laboratory of Image Cognition,Chongqing,China","institution_ids":["https://openalex.org/I10535382"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064352017","display_name":"Yimeng Zhao","orcid":"https://orcid.org/0000-0002-4217-7061"},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yimeng Zhao","raw_affiliation_strings":["Chongqing University of Posts and Telecommunications,Key Laboratory of Image Cognition,Chongqing,China"],"affiliations":[{"raw_affiliation_string":"Chongqing University of Posts and Telecommunications,Key Laboratory of Image Cognition,Chongqing,China","institution_ids":["https://openalex.org/I10535382"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113876094","display_name":"Leida Li","orcid":null},"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":["Xidian University,School of Artificial Intelligence,Xi’an,China"],"affiliations":[{"raw_affiliation_string":"Xidian University,School of Artificial Intelligence,Xi’an,China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108586995","display_name":"Lihuo He","orcid":null},"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":"Lihuo He","raw_affiliation_strings":["Xidian University,School of Electronic Engineering,Xi’an,China"],"affiliations":[{"raw_affiliation_string":"Xidian University,School of Electronic Engineering,Xi’an,China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059540876","display_name":"Wen Lu","orcid":"https://orcid.org/0000-0002-8193-6016"},"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":"Wen Lu","raw_affiliation_strings":["Xidian University,School of Electronic Engineering,Xi’an,China"],"affiliations":[{"raw_affiliation_string":"Xidian University,School of Electronic Engineering,Xi’an,China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101313930","display_name":"Xinbo Gao","orcid":"https://orcid.org/0000-0002-7985-0037"},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinbo Gao","raw_affiliation_strings":["Chongqing University of Posts and Telecommunications,Key Laboratory of Image Cognition,Chongqing,China"],"affiliations":[{"raw_affiliation_string":"Chongqing University of Posts and Telecommunications,Key Laboratory of Image Cognition,Chongqing,China","institution_ids":["https://openalex.org/I10535382"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100748112"],"corresponding_institution_ids":["https://openalex.org/I10535382"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31161577,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11165","display_name":"Image and Video Quality Assessment","score":0.942300021648407,"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":0.942300021648407,"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":0.009800000116229057,"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":0.008999999612569809,"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/robustness","display_name":"Robustness (evolution)","score":0.6682000160217285},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.5281000137329102},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.47029998898506165},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4512999951839447},{"id":"https://openalex.org/keywords/merge","display_name":"Merge (version control)","score":0.44940000772476196},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.43970000743865967},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.38589999079704285},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.34209999442100525}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7699000239372253},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6682000160217285},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5579000115394592},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.5281000137329102},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.47029998898506165},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4512999951839447},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.44940000772476196},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4462999999523163},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.43970000743865967},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.38589999079704285},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.34209999442100525},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33709999918937683},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.3287000060081482},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.31040000915527344},{"id":"https://openalex.org/C3020001037","wikidata":"https://www.wikidata.org/wiki/Q836575","display_name":"Quality assessment","level":3,"score":0.30869999527931213},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.30640000104904175},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3027999997138977},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.28369998931884766},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C64185310","wikidata":"https://www.wikidata.org/wiki/Q843483","display_name":"Rate\u2013distortion theory","level":3,"score":0.26750001311302185},{"id":"https://openalex.org/C2982962833","wikidata":"https://www.wikidata.org/wiki/Q17092450","display_name":"Information fusion","level":2,"score":0.25369998812675476},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.25290000438690186}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11210013","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11210013","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320323172","display_name":"Natural Science Foundation of Chongqing","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324805","display_name":"Chongqing Municipal Education Commission","ror":"https://ror.org/031nm5713"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2063658831","https://openalex.org/W2611434713","https://openalex.org/W2791258091","https://openalex.org/W2939995367","https://openalex.org/W2950154603","https://openalex.org/W2965644659","https://openalex.org/W2970901058","https://openalex.org/W3030701471","https://openalex.org/W3093431261","https://openalex.org/W3169674094","https://openalex.org/W3174722860","https://openalex.org/W3193919962","https://openalex.org/W4225292576","https://openalex.org/W4308237917","https://openalex.org/W4312560592","https://openalex.org/W4312818079","https://openalex.org/W4386057769","https://openalex.org/W4386071544","https://openalex.org/W4386071753","https://openalex.org/W4387068132","https://openalex.org/W4390204417","https://openalex.org/W4390874113","https://openalex.org/W4402753893","https://openalex.org/W4402754178","https://openalex.org/W4402769976","https://openalex.org/W4402772655"],"related_works":[],"abstract_inverted_index":{"User-generated":[0],"content":[1],"(UGC)":[2],"videos":[3],"often":[4],"exhibit":[5],"complex":[6],"distortions":[7],"and":[8,26,32,63,95,128,133],"diverse":[9],"content,":[10],"posing":[11],"significant":[12],"challenges":[13],"for":[14,68],"traditional":[15],"video":[16],"quality":[17],"assessment":[18],"(VQA)":[19],"methods.":[20],"Approaches":[21],"that":[22,116],"directly":[23],"merge":[24],"distortion":[25,80,96],"semantic":[27,94],"information":[28,81],"risk":[29],"feature":[30],"conflicts":[31],"the":[33,87],"loss":[34],"of":[35,41,86,93],"details.":[36],"In":[37],"addition,":[38],"simple":[39],"concatenation":[40],"spatiotemporal":[42,107],"features":[43],"fails":[44],"to":[45],"capture":[46],"vital":[47],"interactions,":[48],"limiting":[49],"predictive":[50],"accuracy.":[51],"Motivated":[52],"by":[53],"these":[54],"challenges,":[55],"this":[56],"paper":[57],"proposes":[58],"a":[59,73,99],"Multi-level":[60],"Distortion":[61],"Adaptation":[62],"Spatiotemporal":[64],"Cross-Attention":[65],"Fusion":[66],"framework":[67],"VQA,":[69],"named":[70],"MACA-VQA.":[71],"Specifically,":[72],"novel":[74],"multi-level":[75],"adaptive":[76],"strategy":[77],"progressively":[78],"incorporates":[79],"into":[82],"each":[83],"Transformer":[84],"layer":[85],"CLIP":[88],"model,":[89],"enabling":[90],"layer-wise":[91],"fusion":[92,103],"features.":[97],"Furthermore,":[98],"newly":[100],"introduced":[101],"cross-attention":[102],"mechanism":[104],"dynamically":[105],"integrates":[106],"features,":[108],"capturing":[109],"complex,":[110],"multidimensional":[111],"interactions.":[112],"Extensive":[113],"experiments":[114],"demonstrate":[115],"MACA-VQA":[117],"achieves":[118],"state-of-the-art":[119],"performance":[120],"on":[121],"multiple":[122],"public":[123],"datasets,":[124],"validating":[125],"its":[126],"effectiveness":[127],"robustness":[129],"in":[130],"both":[131],"intra-dataset":[132],"inter-dataset":[134],"scenarios.":[135],"The":[136],"source":[137],"code":[138],"is":[139],"available":[140],"at":[141],"https://github.com/BoHu90/MACA-VQA":[142]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-30T00:00:00"}