{"id":"https://openalex.org/W4399120447","doi":"https://doi.org/10.1145/3654823.3654862","title":"Semantic Driven Stylized Image Captioning For Artworks","display_name":"Semantic Driven Stylized Image Captioning For Artworks","publication_year":2024,"publication_date":"2024-03-22","ids":{"openalex":"https://openalex.org/W4399120447","doi":"https://doi.org/10.1145/3654823.3654862"},"language":"en","primary_location":{"id":"doi:10.1145/3654823.3654862","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3654823.3654862","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 3rd Asia Conference on Algorithms, Computing and Machine Learning","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/A5081697031","display_name":"Yinfeng Wang","orcid":"https://orcid.org/0009-0006-4034-2584"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yinfeng Wang","raw_affiliation_strings":["School of Communication Engineering, Hangzhou Dianzi University, China"],"raw_orcid":"https://orcid.org/0009-0001-8587-9290","affiliations":[{"raw_affiliation_string":"School of Communication Engineering, Hangzhou Dianzi University, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054884347","display_name":"Tingyu Wang","orcid":"https://orcid.org/0000-0002-4169-1595"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tingyu Wang","raw_affiliation_strings":["School of Communication Engineering, Hangzhou Dianzi University, China"],"raw_orcid":"https://orcid.org/0000-0002-4169-1595","affiliations":[{"raw_affiliation_string":"School of Communication Engineering, Hangzhou Dianzi University, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100357392","display_name":"Weidong Chen","orcid":"https://orcid.org/0000-0003-2774-2875"},"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":"Weidong Chen","raw_affiliation_strings":["University of Science and Technology of China, China"],"raw_orcid":"https://orcid.org/0000-0003-2774-2875","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5081697031"],"corresponding_institution_ids":["https://openalex.org/I50760025"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.062854,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"212","last_page":"216"},"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":0.995199978351593,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9767000079154968,"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":0.9491552114486694},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8402506113052368},{"id":"https://openalex.org/keywords/stylized-fact","display_name":"Stylized fact","score":0.781514048576355},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6426998972892761},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6219078302383423},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.49856114387512207},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48790380358695984},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4740597605705261},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.4717608094215393},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.46873196959495544},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.44661635160446167},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4181169867515564},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.413544237613678}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9491552114486694},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8402506113052368},{"id":"https://openalex.org/C38935604","wikidata":"https://www.wikidata.org/wiki/Q4330363","display_name":"Stylized fact","level":2,"score":0.781514048576355},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6426998972892761},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6219078302383423},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.49856114387512207},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48790380358695984},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4740597605705261},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4717608094215393},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.46873196959495544},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.44661635160446167},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4181169867515564},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.413544237613678},{"id":"https://openalex.org/C139719470","wikidata":"https://www.wikidata.org/wiki/Q39680","display_name":"Macroeconomics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3654823.3654862","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3654823.3654862","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 3rd Asia Conference on Algorithms, Computing and Machine Learning","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W1905882502","https://openalex.org/W2745461083","https://openalex.org/W2963267809","https://openalex.org/W2997248215","https://openalex.org/W3135367836"],"related_works":["https://openalex.org/W2529311304","https://openalex.org/W4248275646","https://openalex.org/W4210416330","https://openalex.org/W2992609826","https://openalex.org/W3124809058","https://openalex.org/W2552900035","https://openalex.org/W2162875951","https://openalex.org/W2062875858","https://openalex.org/W4380047323","https://openalex.org/W1177522693"],"abstract_inverted_index":{"Most":[0],"existing":[1],"image":[2,117],"captioning":[3],"methods":[4],"have":[5],"shown":[6],"impressive":[7],"performance":[8,168],"on":[9,21,49,115,169],"real-life":[10],"images,":[11],"but":[12],"few":[13],"of":[14],"them":[15],"explore":[16],"to":[17,52,71,78,111,135,154],"generate":[18,155],"stylized":[19,157],"captions":[20],"artificial":[22],"images":[23],"like":[24],"artworks.":[25],"There":[26],"are":[27],"two":[28],"challenges":[29],"in":[30,68,73,172],"this":[31],"task:":[32],"firstly,":[33],"modern":[34],"techniques":[35],"usually":[36],"extract":[37],"fine-grained":[38],"visual":[39,86,113,145],"features":[40],"by":[41],"using":[42],"pretrained":[43],"object":[44,95],"detectors,":[45],"which":[46],"perform":[47],"poorly":[48],"artworks":[50],"due":[51],"the":[53,58,144,156],"domain":[54],"gap,":[55],"further":[56],"limits":[57],"whole":[59],"model\u2019s":[60],"performance.":[61],"Secondly,":[62],"diverse":[63],"emotional":[64],"inclinations":[65],"may":[66],"result":[67],"varying":[69],"attention":[70],"semantics":[72],"image,":[74],"making":[75],"it":[76,121],"challenging":[77],"establish":[79],"a":[80,129,151],"clear":[81],"correlation":[82],"between":[83],"emotion":[84,125],"and":[85,147],"input.":[87],"To":[88,103],"address":[89],"these":[90],"issues,":[91],"we":[92,106,142],"propose":[93],"our":[94,164],"detector-free":[96],"Semantic-Driven":[97],"Stylized":[98],"Image":[99],"Captioning":[100],"Networks":[101],"(SD-Net).":[102],"be":[104],"specific,":[105],"initially":[107],"utilize":[108],"an":[109,123],"encoder":[110],"acquire":[112],"tokens":[114,146],"CLIP":[116],"features,":[118],"then":[119],"enhance":[120],"with":[122],"additional":[124],"token.":[126],"After":[127],"that,":[128],"semantic":[130,139,148],"retrieval":[131],"module":[132],"is":[133],"employed":[134],"directly":[136],"reconstruct":[137],"emotion-related":[138],"words.":[140],"Finally,":[141],"integrate":[143],"words":[149],"into":[150],"sentence":[152],"decoder":[153],"caption.":[158],"Our":[159],"experimental":[160],"results":[161],"demonstrate":[162],"that":[163],"approach":[165],"achieves":[166],"competitive":[167],"Artemis":[170],"dataset":[171],"various":[173],"benchmarks.":[174]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}