{"id":"https://openalex.org/W4392902667","doi":"https://doi.org/10.1109/icassp48485.2024.10448422","title":"ZE-FESG: A Zero-Shot Feature Extraction Method Based on Semantic Guidance for No-Reference Video Quality Assessment","display_name":"ZE-FESG: A Zero-Shot Feature Extraction Method Based on Semantic Guidance for No-Reference Video Quality Assessment","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392902667","doi":"https://doi.org/10.1109/icassp48485.2024.10448422"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448422","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448422","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5110086384","display_name":"Yachun Mi","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yachun Mi","raw_affiliation_strings":["Harbin Institute of Technology,Harbin,China","Harbin Institute of Technology, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Harbin,China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100506935","display_name":"Yu Li","orcid":"https://orcid.org/0009-0004-7819-405X"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Li","raw_affiliation_strings":["Harbin Institute of Technology,Harbin,China","Harbin Institute of Technology, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Harbin,China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035087183","display_name":"Yan Shu","orcid":"https://orcid.org/0000-0002-5544-9425"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Shu","raw_affiliation_strings":["Harbin Institute of Technology,Harbin,China","Harbin Institute of Technology, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Harbin,China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100445780","display_name":"Shaohui Liu","orcid":"https://orcid.org/0000-0002-1810-5412"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaohui Liu","raw_affiliation_strings":["Harbin Institute of Technology,Harbin,China","Harbin Institute of Technology, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Harbin,China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3640","last_page":"3644"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11165","display_name":"Image and Video Quality Assessment","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9983000159263611,"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":0.9980999827384949,"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":0.8442742824554443},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.7325800657272339},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.698316216468811},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6158602237701416},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6018714904785156},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.5708813667297363},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5627993941307068},{"id":"https://openalex.org/keywords/semantic-feature","display_name":"Semantic feature","score":0.5441795587539673},{"id":"https://openalex.org/keywords/subjective-video-quality","display_name":"Subjective video quality","score":0.4934031069278717},{"id":"https://openalex.org/keywords/video-quality","display_name":"Video quality","score":0.4774799346923828},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.46472102403640747},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4490469694137573},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42613595724105835},{"id":"https://openalex.org/keywords/image-quality","display_name":"Image quality","score":0.42021477222442627},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3613387942314148},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2556535005569458}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8442742824554443},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.7325800657272339},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.698316216468811},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6158602237701416},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6018714904785156},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5708813667297363},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5627993941307068},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.5441795587539673},{"id":"https://openalex.org/C114227958","wikidata":"https://www.wikidata.org/wiki/Q7631422","display_name":"Subjective video quality","level":4,"score":0.4934031069278717},{"id":"https://openalex.org/C103910844","wikidata":"https://www.wikidata.org/wiki/Q2631256","display_name":"Video quality","level":3,"score":0.4774799346923828},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.46472102403640747},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4490469694137573},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42613595724105835},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.42021477222442627},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3613387942314148},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2556535005569458},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448422","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448422","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1686810756","https://openalex.org/W2108598243","https://openalex.org/W2157331557","https://openalex.org/W2194775991","https://openalex.org/W2611434713","https://openalex.org/W2791258091","https://openalex.org/W2895868297","https://openalex.org/W2939995367","https://openalex.org/W2963616706","https://openalex.org/W2965644659","https://openalex.org/W3094502228","https://openalex.org/W3099047215","https://openalex.org/W3103745061","https://openalex.org/W3167030277","https://openalex.org/W3169674094","https://openalex.org/W3193919962","https://openalex.org/W4225292576","https://openalex.org/W4312560592","https://openalex.org/W4312818079","https://openalex.org/W4322706707","https://openalex.org/W4382462760","https://openalex.org/W4385245566","https://openalex.org/W4386071544","https://openalex.org/W6637373629","https://openalex.org/W6784333009","https://openalex.org/W6791353385","https://openalex.org/W6793164127"],"related_works":["https://openalex.org/W4388138958","https://openalex.org/W1996919562","https://openalex.org/W2046455617","https://openalex.org/W4390244677","https://openalex.org/W2809031010","https://openalex.org/W2061696964","https://openalex.org/W2546999347","https://openalex.org/W3194854785","https://openalex.org/W3014439586","https://openalex.org/W2022158272"],"abstract_inverted_index":{"Although":[0],"the":[1,16,31,39,45,51,56,73,80,87,100,128,137,142,150,156,165],"current":[2,27,166],"deep":[3],"neural":[4],"network":[5],"based":[6,121,169],"no-reference":[7],"video":[8,40,57,92,143],"quality":[9,68,93],"assessment":[10],"(NR-VQA)":[11],"methods":[12,28,172],"can":[13,69],"effectively":[14],"simulate":[15],"human":[17,60],"visual":[18],"system":[19],"(HVS),":[20],"their":[21],"interpretability":[22,161],"is":[23],"getting":[24],"worse.":[25],"The":[26,175],"only":[29],"extract":[30],"low-level":[32],"features":[33,140],"of":[34,38,47,141,149],"space":[35],"and":[36,41,63,98,134,162],"time":[37],"do":[42],"not":[43],"consider":[44],"impact":[46],"high-level":[48,52],"semantics.":[49],"However,":[50],"semantic":[53,96,123],"information":[54],"in":[55],"related":[58,64,90],"to":[59,65,91,106],"subjective":[61],"perception":[62],"its":[66],"own":[67],"be":[70,178],"perceived":[71],"by":[72,144],"HVS.":[74],"In":[75],"this":[76],"work,":[77],"we":[78,113],"design":[79],"multidimensional":[81,109],"feature":[82,110,118,132,170],"extractor":[83,133],"(MDFE),":[84],"which":[85,126],"takes":[86],"text":[88],"descriptions":[89],"factors":[94],"as":[95,130],"guidance,":[97],"uses":[99],"Contrastive":[101],"Language-Image":[102],"Pre-training":[103],"(CLIP)":[104],"model":[105],"perform":[107],"zero-shot":[108,117],"extraction.":[111],"Then,":[112],"further":[114],"propose":[115],"a":[116,131],"extraction":[119,171],"method":[120],"on":[122,180],"guidance":[124],"(ZE-FESG),":[125],"treats":[127],"MDFE":[129],"acquires":[135],"all":[136],"semantically":[138],"corresponding":[139],"sliding":[145],"over":[146],"each":[147],"frame":[148],"video.":[151],"Extensive":[152],"experiments":[153],"show":[154],"that":[155],"proposed":[157],"ZE-FESG":[158],"has":[159],"better":[160],"performance":[163],"than":[164],"mainstream":[167],"2D-CNN":[168],"for":[173],"NR-VQA.":[174],"code":[176],"will":[177],"released":[179],"https://github.com/xiao-mi-d/ZE-FESG.":[181]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}