{"id":"https://openalex.org/W4376852326","doi":"https://doi.org/10.1145/3573942.3574088","title":"First Describe, Then Depict: Generating Covers for Music and Books via Extracting Keywords","display_name":"First Describe, Then Depict: Generating Covers for Music and Books via Extracting Keywords","publication_year":2022,"publication_date":"2022-09-23","ids":{"openalex":"https://openalex.org/W4376852326","doi":"https://doi.org/10.1145/3573942.3574088"},"language":"en","primary_location":{"id":"doi:10.1145/3573942.3574088","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3573942.3574088","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition","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/A5025704136","display_name":"Valeria Efimova","orcid":"https://orcid.org/0000-0002-5309-2207"},"institutions":[{"id":"https://openalex.org/I173089394","display_name":"ITMO University","ror":"https://ror.org/04txgxn49","country_code":"RU","type":"education","lineage":["https://openalex.org/I173089394"]}],"countries":["RU"],"is_corresponding":true,"raw_author_name":"Valeria Efimova","raw_affiliation_strings":["ML Lab, ITMO University, Russia"],"raw_orcid":"https://orcid.org/0000-0002-5309-2207","affiliations":[{"raw_affiliation_string":"ML Lab, ITMO University, Russia","institution_ids":["https://openalex.org/I173089394"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021654730","display_name":"Viacheslav Shalamov","orcid":"https://orcid.org/0000-0002-5647-6521"},"institutions":[{"id":"https://openalex.org/I173089394","display_name":"ITMO University","ror":"https://ror.org/04txgxn49","country_code":"RU","type":"education","lineage":["https://openalex.org/I173089394"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Viacheslav Shalamov","raw_affiliation_strings":["ML Lab, ITMO University, Russia"],"raw_orcid":"https://orcid.org/0000-0002-5647-6521","affiliations":[{"raw_affiliation_string":"ML Lab, ITMO University, Russia","institution_ids":["https://openalex.org/I173089394"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112028318","display_name":"Andrey Filchenkov","orcid":null},"institutions":[{"id":"https://openalex.org/I173089394","display_name":"ITMO University","ror":"https://ror.org/04txgxn49","country_code":"RU","type":"education","lineage":["https://openalex.org/I173089394"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Andrey Filchenkov","raw_affiliation_strings":["ML Lab, ITMO University, Russia"],"raw_orcid":"https://orcid.org/0000-0002-1133-8432","affiliations":[{"raw_affiliation_string":"ML Lab, ITMO University, Russia","institution_ids":["https://openalex.org/I173089394"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5025704136"],"corresponding_institution_ids":["https://openalex.org/I173089394"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1980487,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"734","last_page":"739"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9939000010490417,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11309","display_name":"Music and Audio Processing","score":0.9939000010490417,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9936000108718872,"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":0.9930999875068665,"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/computer-science","display_name":"Computer science","score":0.7994368076324463},{"id":"https://openalex.org/keywords/harmonization","display_name":"Harmonization","score":0.6083643436431885},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.6067314743995667},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5830920934677124},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5747120380401611},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5516687631607056},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4372890889644623},{"id":"https://openalex.org/keywords/image-file-formats","display_name":"Image file formats","score":0.42542314529418945},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.42331066727638245},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3951599597930908},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.35141149163246155},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3358103632926941},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.30819207429885864},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.18793436884880066}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7994368076324463},{"id":"https://openalex.org/C2779962950","wikidata":"https://www.wikidata.org/wiki/Q5659376","display_name":"Harmonization","level":2,"score":0.6083643436431885},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.6067314743995667},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5830920934677124},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5747120380401611},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5516687631607056},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4372890889644623},{"id":"https://openalex.org/C65377053","wikidata":"https://www.wikidata.org/wiki/Q1572121","display_name":"Image file formats","level":3,"score":0.42542314529418945},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.42331066727638245},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3951599597930908},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35141149163246155},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3358103632926941},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.30819207429885864},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.18793436884880066},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3573942.3574088","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3573942.3574088","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7400000095367432}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1852422273","https://openalex.org/W2164147879","https://openalex.org/W2907159568","https://openalex.org/W4236965008","https://openalex.org/W4301409532","https://openalex.org/W6600033936","https://openalex.org/W6600120041","https://openalex.org/W6600586173","https://openalex.org/W6604594194","https://openalex.org/W6631455383","https://openalex.org/W6679339028","https://openalex.org/W6766867563","https://openalex.org/W6818723395","https://openalex.org/W6819060087"],"related_works":["https://openalex.org/W2006073222","https://openalex.org/W2488916264","https://openalex.org/W2323573032","https://openalex.org/W198625436","https://openalex.org/W1908077024","https://openalex.org/W2095388346","https://openalex.org/W2379751185","https://openalex.org/W2379404183","https://openalex.org/W2004509987","https://openalex.org/W2185986540"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,39],"consider":[4],"the":[5,71,82],"two":[6],"algorithms":[7,73],"of":[8,55],"generating":[9],"artwork":[10],"covers":[11,58,62],"based":[12],"on":[13],"texts":[14],"or":[15,47],"audio":[16],"file":[17],"features.":[18],"The":[19,53,85],"resulting":[20],"image":[21,33],"is":[22],"combined":[23],"from":[24],"existing":[25,83],"images":[26,100],"labelled":[27],"with":[28],"keywords":[29],"after":[30],"applying":[31],"filter-based":[32],"harmonization.":[34],"To":[35],"achieve":[36,89],"realistic":[37],"composition,":[38],"train":[40],"GAN":[41],"to":[42,68,75,81],"predict":[43],"an":[44],"appropriate":[45],"filter":[46],"apply":[48],"emotion-based":[49],"Neural":[50],"Style":[51],"Transfer.":[52],"quality":[54,91],"generated":[56,99],"book":[57],"and":[59,92],"music":[60],"album":[61],"was":[63],"evaluated":[64],"by":[65],"assessors.":[66],"According":[67],"their":[69],"assessment,":[70],"suggested":[72,86],"appeared":[74],"produce":[76],"a":[77],"better":[78],"result":[79],"compared":[80],"solutions.":[84],"methods":[87],"also":[88],"printing":[90],"require":[93],"less":[94],"time":[95],"for":[96],"computations,":[97],"moreover,":[98],"can":[101],"be":[102],"used":[103],"without":[104],"copyright":[105],"infringement.":[106]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
