{"id":"https://openalex.org/W4414758352","doi":"https://doi.org/10.48550/arxiv.2509.04378","title":"Aesthetic Image Captioning with Saliency Enhanced MLLMs","display_name":"Aesthetic Image Captioning with Saliency Enhanced MLLMs","publication_year":2025,"publication_date":"2025-09-04","ids":{"openalex":"https://openalex.org/W4414758352","doi":"https://doi.org/10.48550/arxiv.2509.04378"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2509.04378","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.04378","pdf_url":"https://arxiv.org/pdf/2509.04378","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2509.04378","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011794783","display_name":"Yilin Tao","orcid":"https://orcid.org/0009-0001-9982-1495","observed_orcids":["https://orcid.org/0009-0001-9982-1495"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tao, Yilin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035089949","display_name":"Jiashui Huang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Jiashui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033135480","display_name":"Huaze Xu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Huaze","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Shao, Ling","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shao, Ling","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9937000274658203,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9937000274658203,"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":0.0035000001080334187,"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":0.00139999995008111,"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-large-language-models","display_name":"multimodal large language models","score":0.8709999918937683},{"id":"https://openalex.org/keywords/computational-aesthetics","display_name":"computational aesthetics","score":0.7279999852180481},{"id":"https://openalex.org/keywords/cross-attention-fusion","display_name":"cross-attention fusion","score":0.7319999933242798}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7833999991416931},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6962000131607056},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6912000179290771},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6504999995231628},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6281999945640564},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.49160000681877136},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.45680001378059387},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4537999927997589},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4336000084877014},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4174000024795532},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.3188000023365021},{"id":"https://openalex.org/C2777617010","wikidata":"https://www.wikidata.org/wiki/Q18957","display_name":"Mainstream","level":2,"score":0.31850001215934753},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.31209999322891235},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.25609999895095825}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2509.04378","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.04378","pdf_url":"https://arxiv.org/pdf/2509.04378","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2509.04378","doi":"https://doi.org/10.48550/arxiv.2509.04378","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2509.04378","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2509.04378","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.04378","pdf_url":"https://arxiv.org/pdf/2509.04378","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Aesthetic":[0,98,123],"Image":[1,122],"Captioning":[2],"(AIC)":[3],"aims":[4],"to":[5,36,85,172],"generate":[6],"textual":[7,49],"descriptions":[8],"of":[9,20,164],"image":[10,41,56,143,155,174],"aesthetics,":[11],"becoming":[12],"a":[13,37,158],"key":[14],"research":[15,43],"direction":[16],"in":[17,40,69],"the":[18,97,121,142,162,169],"field":[19],"computational":[21],"aesthetics.":[22],"In":[23],"recent":[24],"years,":[25],"pretrained":[26],"Multimodal":[27,101],"Large":[28,102],"Language":[29,103],"Models":[30],"(MLLMs)":[31],"have":[32,65],"advanced":[33],"rapidly,":[34],"leading":[35],"significant":[38],"increase":[39],"aesthetics":[42,57],"that":[44,109,186],"integrates":[45],"both":[46],"visual":[47],"and":[48,64,129,193],"modalities.":[50],"However,":[51],"most":[52],"existing":[53],"studies":[54],"on":[55,60,78,87,196],"primarily":[58],"focus":[59,86],"predicting":[61],"aesthetic":[62,89,112,132,150,175],"ratings":[63],"shown":[66],"limited":[67],"application":[68],"AIC.":[70],"Existing":[71],"AIC":[72,181,199],"works":[73],"leveraging":[74],"MLLMs":[75,84,178,195],"predominantly":[76],"rely":[77],"fine-tuning":[79],"methods":[80,192],"without":[81],"specifically":[82,179],"adapting":[83],"target":[88],"content.":[90],"To":[91,161],"address":[92],"this":[93,117,147],"limitation,":[94],"we":[95,119,138],"propose":[96],"Saliency":[99,124],"Enhanced":[100],"Model":[104],"(ASE-MLLM),":[105],"an":[106],"end-to-end":[107],"framework":[108,171],"explicitly":[110],"incorporates":[111],"saliency":[113,133,151,176],"into":[114,177],"MLLMs.":[115],"Within":[116],"framework,":[118],"introduce":[120],"Module":[125],"(IASM),":[126],"which":[127],"efficiently":[128],"effectively":[130],"extracts":[131],"features":[134,152,156],"from":[135],"images.":[136],"Additionally,":[137],"design":[139],"IAS-ViT":[140],"as":[141],"encoder":[144],"for":[145,180],"MLLMs,":[146],"module":[148],"fuses":[149],"with":[153],"original":[154],"via":[157],"cross-attention":[159],"mechanism.":[160],"best":[163],"our":[165,187],"knowledge,":[166],"ASE-MLLM":[167],"is":[168],"first":[170],"integrate":[173],"tasks.":[182],"Extensive":[183],"experiments":[184],"demonstrated":[185],"approach":[188],"significantly":[189],"outperformed":[190],"traditional":[191],"generic":[194],"current":[197],"mainstream":[198],"benchmarks,":[200],"achieving":[201],"state-of-the-art":[202],"(SOTA)":[203],"performance.":[204]},"counts_by_year":[],"updated_date":"2026-09-29T14:09:16.559479","created_date":"2025-10-10T00:00:00"}