{"id":"https://openalex.org/W4416250717","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228836","title":"Towards Emotional Insights in Art: A Knowledge-Driven Framework Integrating Artistic Emotion Knowledge into Vision Language Models","display_name":"Towards Emotional Insights in Art: A Knowledge-Driven Framework Integrating Artistic Emotion Knowledge into Vision Language Models","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416250717","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228836"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11228836","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228836","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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/A5108943356","display_name":"Haoyang Chen","orcid":"https://orcid.org/0009-0002-4221-5811"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haoyang Chen","raw_affiliation_strings":["Nanjing University,State Key Laboratory for Novel Software Technology,Nanjing,China"],"affiliations":[{"raw_affiliation_string":"Nanjing University,State Key Laboratory for Novel Software Technology,Nanjing,China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014537056","display_name":"Hengyang Lu","orcid":"https://orcid.org/0000-0001-5321-705X"},"institutions":[{"id":"https://openalex.org/I111599522","display_name":"Jiangnan University","ror":"https://ror.org/04mkzax54","country_code":"CN","type":"education","lineage":["https://openalex.org/I111599522"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hengyang Lu","raw_affiliation_strings":["Jiangnan University,School of Artificial Intelligence and Computer Science,Wuxi,China"],"affiliations":[{"raw_affiliation_string":"Jiangnan University,School of Artificial Intelligence and Computer Science,Wuxi,China","institution_ids":["https://openalex.org/I111599522"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006921976","display_name":"Yi Xin","orcid":"https://orcid.org/0000-0001-8546-0580"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Xin","raw_affiliation_strings":["Nanjing University,State Key Laboratory for Novel Software Technology,Nanjing,China"],"affiliations":[{"raw_affiliation_string":"Nanjing University,State Key Laboratory for Novel Software Technology,Nanjing,China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085047273","display_name":"Desheng Kong","orcid":"https://orcid.org/0000-0001-9312-0623"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dian Kong","raw_affiliation_strings":["Nanjing University,State Key Laboratory for Novel Software Technology,Nanjing,China"],"affiliations":[{"raw_affiliation_string":"Nanjing University,State Key Laboratory for Novel Software Technology,Nanjing,China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044733681","display_name":"Chongjun Wang","orcid":"https://orcid.org/0000-0002-2628-7033"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chongjun Wang","raw_affiliation_strings":["Nanjing University,State Key Laboratory for Novel Software Technology,Nanjing,China"],"affiliations":[{"raw_affiliation_string":"Nanjing University,State Key Laboratory for Novel Software Technology,Nanjing,China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5108943356"],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33780741,"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":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12650","display_name":"Aesthetic Perception and Analysis","score":0.8008000254631042,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T12650","display_name":"Aesthetic Perception and Analysis","score":0.8008000254631042,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.042899999767541885,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0364999994635582,"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/task","display_name":"Task (project management)","score":0.47609999775886536},{"id":"https://openalex.org/keywords/painting","display_name":"Painting","score":0.4702000021934509},{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.41769999265670776},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.41119998693466187},{"id":"https://openalex.org/keywords/grasp","display_name":"GRASP","score":0.40209999680519104},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.3716999888420105},{"id":"https://openalex.org/keywords/metaphor","display_name":"Metaphor","score":0.3625999987125397},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.33709999918937683}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49889999628067017},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.47609999775886536},{"id":"https://openalex.org/C205783811","wikidata":"https://www.wikidata.org/wiki/Q11629","display_name":"Painting","level":2,"score":0.4702000021934509},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.4388999938964844},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.41769999265670776},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.41119998693466187},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4097999930381775},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.4056999981403351},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.4027000069618225},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.40209999680519104},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3716999888420105},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3684999942779541},{"id":"https://openalex.org/C2778311575","wikidata":"https://www.wikidata.org/wiki/Q18534","display_name":"Metaphor","level":2,"score":0.3625999987125397},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.33709999918937683},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.32670000195503235},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.3131999969482422},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3102000057697296},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.303600013256073},{"id":"https://openalex.org/C2776289891","wikidata":"https://www.wikidata.org/wiki/Q1931511","display_name":"Neglect","level":2,"score":0.2985999882221222},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.287200003862381},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2797999978065491},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.2766000032424927},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.25920000672340393},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.25189998745918274}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11228836","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228836","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1979369422","https://openalex.org/W2003856922","https://openalex.org/W2074356411","https://openalex.org/W2075456404","https://openalex.org/W2090374580","https://openalex.org/W2163352848","https://openalex.org/W2964051877","https://openalex.org/W3034655362","https://openalex.org/W3138516171","https://openalex.org/W3173683732","https://openalex.org/W3174770825","https://openalex.org/W4312443924","https://openalex.org/W4312537386","https://openalex.org/W4312651322","https://openalex.org/W4313046229","https://openalex.org/W4385571664","https://openalex.org/W4393160572","https://openalex.org/W4402660140","https://openalex.org/W4402669747","https://openalex.org/W4402713111","https://openalex.org/W4402754294","https://openalex.org/W4404166661","https://openalex.org/W4404783482"],"related_works":[],"abstract_inverted_index":{"Understanding":[0],"emotions":[1,9,74,202],"in":[2,37,75,123,196],"art":[3,53,110,118,146],"paintings":[4,161],"and":[5,20,85,115,165,180],"generating":[6],"comments":[7],"about":[8],"is":[10,135],"a":[11,49,61],"highly":[12],"challenging":[13],"task":[14,198],"due":[15],"to":[16,28,145,149],"their":[17],"rich":[18],"semantics":[19],"complex":[21],"expressions.":[22],"However,":[23],"existing":[24,207],"related":[25,148],"methods":[26],"tend":[27],"neglect":[29],"the":[30,40,81,86,91,124,129,142,192,197],"critical":[31],"role":[32],"of":[33,52,132,194,199],"artistic":[34,66,201],"emotion":[35,67,97,113,121,138],"features":[36,101,111,119,147],"artworks":[38],"at":[39],"visual":[41,83,93,100,133,169],"level,":[42],"while":[43],"general":[44],"vision":[45],"language":[46],"models(VLMs)":[47],"lack":[48],"comprehensive":[50],"grasp":[51],"domain":[54],"knowledge.":[55],"To":[56],"address":[57],"this,":[58],"we":[59],"propose":[60],"knowledge-driven":[62],"framework":[63,78,189],"based":[64],"on":[65,177,203],"knowledge,":[68],"which":[69,140],"helps":[70],"VLMs":[71,195],"better":[72],"comprehend":[73],"artworks.":[76],"The":[77,151,184],"primarily":[79],"comprises":[80],"artistic-emotion":[82,92],"tower":[84,94,134,170],"ANP":[87,152],"cross-attention":[88,153,167],"module.":[89],"Specifically,":[90],"introduces":[95],"additional":[96],"tokens":[98,114,122],"before":[99],"are":[102],"fed":[103],"into":[104,112,120],"transformer":[105,126],"layers.":[106],"It":[107],"integrate":[108],"low-level":[109],"infuses":[116],"high-level":[117],"penultimate":[125],"layer.":[127],"Moreover,":[128],"attention":[130],"mechanism":[131],"optimized":[136],"by":[137],"bias,":[139],"enhances":[141],"model\u2019s":[143],"sensitivity":[144],"emotions.":[150],"module":[154],"will":[155],"extract":[156],"affective":[157],"entities":[158],"directly":[159],"from":[160],"as":[162],"adjective-noun":[163],"pairs":[164],"apply":[166],"with":[168],"outputs.":[171],"We":[172],"have":[173],"conducted":[174],"extensive":[175],"experiments":[176],"Artemis":[178,181],"1.0":[179],"2.0":[182],"datasets.":[183],"results":[185],"demonstrate":[186],"that":[187],"our":[188],"effectively":[190],"improves":[191],"performance":[193],"understanding":[200],"eight":[204],"metrics,":[205],"outperforming":[206],"methods.":[208]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-14T00:00:00"}