{"id":"https://openalex.org/W3090050016","doi":"https://doi.org/10.1109/ijcnn48605.2020.9206953","title":"Towards Personalized Aesthetic Image Caption","display_name":"Towards Personalized Aesthetic Image Caption","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3090050016","doi":"https://doi.org/10.1109/ijcnn48605.2020.9206953","mag":"3090050016"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn48605.2020.9206953","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9206953","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 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/A5023824766","display_name":"Kun Xiong","orcid":"https://orcid.org/0000-0003-1431-6586"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kun Xiong","raw_affiliation_strings":["School of software, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of software, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101569350","display_name":"Liu Jiang","orcid":"https://orcid.org/0000-0002-7189-7762"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liu Jiang","raw_affiliation_strings":["School of software, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of software, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072992021","display_name":"Xuan Dang","orcid":"https://orcid.org/0000-0002-6009-7188"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuan Dang","raw_affiliation_strings":["School of software, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of software, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074895308","display_name":"Guolong Wang","orcid":"https://orcid.org/0000-0002-3749-6148"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guolong Wang","raw_affiliation_strings":["School of software, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of software, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018923326","display_name":"Wenwen Ye","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenwen Ye","raw_affiliation_strings":["School of software, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of software, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101460210","display_name":"Zheng Qin","orcid":"https://orcid.org/0000-0002-7090-7869"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Qin","raw_affiliation_strings":["School of software, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of software, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5023824766"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.10512872,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"242","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9984999895095825,"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":0.9977999925613403,"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/closed-captioning","display_name":"Closed captioning","score":0.8999396562576294},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7858704924583435},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.6399204730987549},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5378166437149048},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5320234298706055},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4709547460079193},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44850954413414},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.417999804019928},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3633241057395935}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8999396562576294},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7858704924583435},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6399204730987549},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5378166437149048},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5320234298706055},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4709547460079193},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44850954413414},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.417999804019928},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3633241057395935},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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:10.1109/ijcnn48605.2020.9206953","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9206953","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5299999713897705,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1511924373","https://openalex.org/W1514535095","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1896080482","https://openalex.org/W1956340063","https://openalex.org/W2078807908","https://openalex.org/W2101105183","https://openalex.org/W2108325777","https://openalex.org/W2123301721","https://openalex.org/W2130942839","https://openalex.org/W2185175083","https://openalex.org/W2217895792","https://openalex.org/W2294624972","https://openalex.org/W2607579284","https://openalex.org/W2613904329","https://openalex.org/W2625940279","https://openalex.org/W2745461083","https://openalex.org/W2779483295","https://openalex.org/W2780162533","https://openalex.org/W2931027027","https://openalex.org/W2963258075","https://openalex.org/W2964265128","https://openalex.org/W2984138079","https://openalex.org/W2990564716","https://openalex.org/W3012364787","https://openalex.org/W6630520941","https://openalex.org/W6630875275","https://openalex.org/W6678262379","https://openalex.org/W6679436768","https://openalex.org/W6697253549","https://openalex.org/W6737778391","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W3164229987","https://openalex.org/W3215212336","https://openalex.org/W4290852288","https://openalex.org/W3217388757","https://openalex.org/W3122720459","https://openalex.org/W4298897568","https://openalex.org/W4289422896","https://openalex.org/W1938708284","https://openalex.org/W4380190185"],"abstract_inverted_index":{"Image":[0],"captioning":[1,45],"(IC)":[2],"is":[3,134,142,161,188],"a":[4,62,85,99,128,191],"commonly-used":[5],"technique":[6],"for":[7,36,78,107,113,144,190],"generating":[8,37],"textual":[9],"image":[10,18,22,44,103,130,158,197],"description,":[11],"which":[12,187],"finds":[13],"its":[14],"applications":[15,80],"on":[16,30,53,69,88],"semantic":[17],"retrieval":[19],"and":[20,71,109,127,172],"multi-modal":[21],"understanding,":[23],"among":[24],"many":[25],"others.":[26],"This":[27],"paper":[28],"focuses":[29],"an":[31],"important":[32],"IC":[33],"method":[34],"specialized":[35],"aesthetic":[38,43,73,102,196],"descriptions":[39],"of":[40,50,64,66,92],"images,":[41],"i.e.,":[42],"(AIC).":[46],"Despite":[47],"some":[48],"effectiveness":[49],"initial":[51],"work":[52],"AIC,":[54],"their":[55],"performances":[56],"are":[57],"inherently":[58],"limited":[59,151],"due":[60],"to":[61,136,163],"lack":[63],"consideration":[65],"user":[67,111,147,170],"preferences":[68,112],"aesthetics":[70,91],"better":[72],"feature,":[74,140],"making":[75],"it":[76],"unusable":[77],"real-world":[79],"where":[81],"human":[82],"users":[83],"present":[84],"large":[86],"variation":[87],"evaluating":[89],"visual":[90],"images.":[93],"To":[94],"tackle":[95],"this,":[96],"we":[97],"propose":[98],"novel":[100],"personalized":[101,129,195],"caption":[104,131,159,166],"(PAIC)":[105],"approach":[106,117],"capturing":[108],"incorporating":[110],"AIC":[114],"tasks.":[115],"Our":[116],"mainly":[118],"contains":[119],"Aesthetic":[120],"feature":[121],"Extraction":[122],"Network(AEN),":[123],"User":[124],"Encoder":[125],"network(UEN)":[126],"model.":[132],"AEN":[133],"designed":[135],"extract":[137],"more":[138],"expressive":[139],"UEN":[141],"introduced":[143],"learning":[145],"the":[146,150,165,169],"vector":[148],"from":[149],"information":[152],"in":[153],"our":[154,180],"AVA-PCap":[155],"dataset.":[156],"Personalized":[157],"model":[160],"constructed":[162],"generate":[164],"when":[167],"given":[168],"id":[171],"photo":[173],"pairs.":[174],"The":[175],"experimental":[176],"results":[177],"show":[178],"that":[179],"methods":[181],"outperform":[182],"baselines":[183],"by":[184],"10%":[185],",":[186],"encouraging":[189],"first":[192],"step":[193],"towards":[194],"caption.":[198]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}