{"id":"https://openalex.org/W4403713306","doi":"https://doi.org/10.1145/3688867.3690176","title":"Text-guided Multi-Task Image Aesthetic Quality Assessment","display_name":"Text-guided Multi-Task Image Aesthetic Quality Assessment","publication_year":2024,"publication_date":"2024-10-23","ids":{"openalex":"https://openalex.org/W4403713306","doi":"https://doi.org/10.1145/3688867.3690176"},"language":"en","primary_location":{"id":"doi:10.1145/3688867.3690176","doi":"https://doi.org/10.1145/3688867.3690176","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3688867.3690176","pdf_url":null,"source":{"id":"https://openalex.org/S7407113424","display_name":"International Workshop on Multimedia Content Generation and Evaluation: New Methods and Practice (McGE)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd International Workshop on Multimedia Content Generation and Evaluation: New Methods and Practice","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5101963202","display_name":"Hongtao Yang","orcid":"https://orcid.org/0000-0002-4029-0255","observed_orcids":["https://orcid.org/0000-0002-4029-0255"]},"institutions":[{"id":"https://openalex.org/I4405281107","display_name":"Beijing Polytechnic College","ror":"https://ror.org/03vzjv161","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405281107"]},{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongtao Yang","raw_affiliation_strings":["Communication University of China & Beijing Polytechnic College, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4029-0255","affiliations":[{"raw_affiliation_string":"Communication University of China & Beijing Polytechnic College, Beijing, China","institution_ids":["https://openalex.org/I4405281107","https://openalex.org/I75689368"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070058501","display_name":"Guolong Wang","orcid":"https://orcid.org/0000-0003-4874-2639","observed_orcids":["https://orcid.org/0000-0003-4874-2639"]},"institutions":[{"id":"https://openalex.org/I146563203","display_name":"University of International Business and Economics","ror":"https://ror.org/05khqpb71","country_code":"CN","type":"education","lineage":["https://openalex.org/I146563203"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guolong Wang","raw_affiliation_strings":["University of International Business and Economics, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4874-2639","affiliations":[{"raw_affiliation_string":"University of International Business and Economics, Beijing, China","institution_ids":["https://openalex.org/I146563203"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yehui Liu","orcid":"https://orcid.org/0009-0001-0393-0751","observed_orcids":["https://orcid.org/0009-0001-0393-0751"]},"institutions":[{"id":"https://openalex.org/I4405281107","display_name":"Beijing Polytechnic College","ror":"https://ror.org/03vzjv161","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405281107"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yehui Liu","raw_affiliation_strings":["Beijing Polytechnic College, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-0393-0751","affiliations":[{"raw_affiliation_string":"Beijing Polytechnic College, Beijing, China","institution_ids":["https://openalex.org/I4405281107"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100553175","display_name":"Shi Ping","orcid":"https://orcid.org/0009-0003-7744-6246","observed_orcids":["https://orcid.org/0009-0003-7744-6246"]},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ping Shi","raw_affiliation_strings":["Communication University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-7744-6246","affiliations":[{"raw_affiliation_string":"Communication University of China, Beijing, China","institution_ids":["https://openalex.org/I75689368"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017875019","display_name":"Xinghui Zhou","orcid":"https://orcid.org/0000-0003-1340-4402","observed_orcids":["https://orcid.org/0000-0003-1340-4402"]},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinghui Zhou","raw_affiliation_strings":["University of Science and Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-1340-4402","affiliations":[{"raw_affiliation_string":"University of Science and Technology, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100641352","display_name":"Xin Jin","orcid":"https://orcid.org/0000-0003-3873-1653","observed_orcids":["https://orcid.org/0000-0003-3873-1653"]},"institutions":[{"id":"https://openalex.org/I202334528","display_name":"Beijing Electronic Science and Technology Institute","ror":"https://ror.org/01xdzh226","country_code":"CN","type":"education","lineage":["https://openalex.org/I202334528"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Jin","raw_affiliation_strings":["Beijing Electronic Science and Technology of Institute, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3873-1653","affiliations":[{"raw_affiliation_string":"Beijing Electronic Science and Technology of Institute, Beijing, China","institution_ids":["https://openalex.org/I202334528"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5606,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.72935277,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"11","last_page":"19"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11165","display_name":"Image and Video Quality Assessment","score":0.9731000065803528,"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":0.9731000065803528,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.01209999993443489,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.004399999976158142,"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/multimodal-learning","display_name":"multimodal learning","score":0.6629999876022339},{"id":"https://openalex.org/keywords/clip","display_name":"CLIP","score":0.8970000147819519},{"id":"https://openalex.org/keywords/contrastive-language-image-pre-training","display_name":"contrastive language-image pretraining","score":0.75},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"multi-task learning","score":0.7730000019073486},{"id":"https://openalex.org/keywords/scene-classification","display_name":"scene classification","score":0.7879999876022339},{"id":"https://openalex.org/keywords/photographic-style","display_name":"photographic style","score":0.8519999980926514},{"id":"https://openalex.org/keywords/aesthetic-characteristics","display_name":"aesthetic characteristics","score":0.8489999771118164},{"id":"https://openalex.org/keywords/transfer-learning","display_name":"transfer learning","score":0.36399999260902405}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7253915071487427},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6195220947265625},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.582095742225647},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.5461699366569519},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.44763100147247314},{"id":"https://openalex.org/C3020001037","wikidata":"https://www.wikidata.org/wiki/Q836575","display_name":"Quality assessment","level":3,"score":0.4154645502567291},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4149162173271179},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4019569158554077},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.369415283203125},{"id":"https://openalex.org/C3018395757","wikidata":"https://www.wikidata.org/wiki/Q1379672","display_name":"Evaluation methods","level":2,"score":0.13415423035621643},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.09865871071815491},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09325549006462097},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.06000930070877075},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3688867.3690176","doi":"https://doi.org/10.1145/3688867.3690176","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3688867.3690176","pdf_url":null,"source":{"id":"https://openalex.org/S7407113424","display_name":"International Workshop on Multimedia Content Generation and Evaluation: New Methods and Practice (McGE)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd International Workshop on Multimedia Content Generation and Evaluation: New Methods and Practice","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W2009678853","https://openalex.org/W2510182739","https://openalex.org/W2514622527","https://openalex.org/W2524036617","https://openalex.org/W2604528050","https://openalex.org/W2735434469","https://openalex.org/W2747102465","https://openalex.org/W2754213847","https://openalex.org/W2904852565","https://openalex.org/W2931027027","https://openalex.org/W2963204629","https://openalex.org/W2963430933","https://openalex.org/W2976886057","https://openalex.org/W3003957020","https://openalex.org/W3016197248","https://openalex.org/W3025478955","https://openalex.org/W3171472210","https://openalex.org/W3201711438","https://openalex.org/W4225452291","https://openalex.org/W4234552385","https://openalex.org/W4285606417","https://openalex.org/W4286611322","https://openalex.org/W4293057409","https://openalex.org/W4293519076","https://openalex.org/W4309933612","https://openalex.org/W4312354469","https://openalex.org/W4322576760","https://openalex.org/W4382462760","https://openalex.org/W4386076169","https://openalex.org/W4386076227","https://openalex.org/W4388543952"],"related_works":["https://openalex.org/W4410186657","https://openalex.org/W4409990928","https://openalex.org/W4403791977","https://openalex.org/W4399400522","https://openalex.org/W4387969352","https://openalex.org/W4410493021","https://openalex.org/W4283800121","https://openalex.org/W7161582898","https://openalex.org/W7165048524","https://openalex.org/W4416183367"],"abstract_inverted_index":{"In":[0],"the":[1,48,60,85,95,98,111,119,159,174,178,182,186],"realm":[2],"of":[3,23,51,62,91,97,113,121,164,177,188],"image":[4,63,122,154,183],"aesthetic":[5,18,24,49,64,115,123,129,155,189],"quality":[6,65,124,130,190],"assessment,":[7,66],"additional":[8],"tagging":[9],"information,":[10],"such":[11],"as":[12],"scene":[13],"classification,":[14],"photographic":[15],"style,":[16],"and":[17,29,88,104,134,144,161],"attributes,":[19],"embodies":[20],"a":[21,41,70,106],"wealth":[22],"connotations.":[25],"The":[26],"textual":[27,86],"descriptions":[28,87],"visual":[30,89],"features":[31,90],"constructed":[32],"from":[33],"this":[34,56,165],"information":[35,57],"often":[36],"exhibit":[37],"significant":[38],"complementarity,":[39],"providing":[40],"more":[42],"comprehensive":[43],"perspective":[44],"for":[45],"delving":[46],"into":[47],"value":[50],"images.":[52],"To":[53],"fully":[54],"harness":[55],"to":[58,82,185],"enhance":[59],"effectiveness":[61],"we":[67],"have":[68],"developed":[69],"Text-guided":[71],"Multitask":[72],"Image":[73],"Aesthetic":[74],"Quality":[75],"Assessment":[76],"model":[77,80,180],"(TM-IAQA).":[78],"This":[79],"aims":[81],"jointly":[83],"learn":[84],"images,":[92],"built":[93],"upon":[94],"foundation":[96],"Contrastive":[99],"Language-Image":[100],"Pre-training":[101],"(CLIP)":[102],"model,":[103,167],"adopts":[105],"multitask":[107,128],"learning":[108],"perspective.":[109],"Through":[110],"transfer":[112,173],"auxiliary":[114],"knowledge,":[116],"it":[117,170],"enhances":[118],"performance":[120],"assessment.":[125,191],"TM-IAQA":[126],"encompasses":[127],"assessments,":[131],"including":[132],"semantic":[133],"stylistic":[135],"task":[136,142,147],"branches":[137],"based":[138],"on":[139,151],"CLIP,":[140],"multi-attribute":[141],"branches,":[143],"multi-theme":[145],"classification":[146],"branches.":[148],"Experimental":[149],"results":[150],"three":[152],"public":[153],"assessment":[156],"datasets":[157],"validate":[158],"efficacy":[160],"generalization":[162],"capability":[163],"multimodal":[166],"demonstrating":[168],"that":[169],"can":[171],"effectively":[172],"prior":[175],"knowledge":[176],"CLIP":[179],"in":[181],"domain":[184],"field":[187]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2024-10-25T00:00:00"}