{"id":"https://openalex.org/W4404978401","doi":"https://doi.org/10.1145/3681756.3697974","title":"Multimodal Learning for Autoencoders","display_name":"Multimodal Learning for Autoencoders","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4404978401","doi":"https://doi.org/10.1145/3681756.3697974"},"language":"en","primary_location":{"id":"doi:10.1145/3681756.3697974","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3681756.3697974","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3681756.3697974","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIGGRAPH Asia 2024 Posters","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3681756.3697974","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Wajahat Ali Khan","orcid":"https://orcid.org/0009-0003-3633-8783"},"institutions":[{"id":"https://openalex.org/I35928602","display_name":"Kyung Hee University","ror":"https://ror.org/01zqcg218","country_code":"KR","type":"education","lineage":["https://openalex.org/I35928602"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Wajahat Ali Khan","raw_affiliation_strings":["Kyung Hee University, Yongin, South Korea"],"affiliations":[{"raw_affiliation_string":"Kyung Hee University, Yongin, South Korea","institution_ids":["https://openalex.org/I35928602"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101472509","display_name":"Seungkyu Lee","orcid":"https://orcid.org/0000-0002-9721-4093"},"institutions":[{"id":"https://openalex.org/I35928602","display_name":"Kyung Hee University","ror":"https://ror.org/01zqcg218","country_code":"KR","type":"education","lineage":["https://openalex.org/I35928602"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seungkyu Lee","raw_affiliation_strings":["Kyung Hee University, Yongin, South Korea"],"affiliations":[{"raw_affiliation_string":"Kyung Hee University, Yongin, South Korea","institution_ids":["https://openalex.org/I35928602"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I35928602"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21325181,"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":"2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9940999746322632,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9940999746322632,"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/T11309","display_name":"Music and Audio Processing","score":0.9779000282287598,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9498000144958496,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.7272237539291382},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6044096350669861},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35675036907196045},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3223755657672882}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7272237539291382},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6044096350669861},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35675036907196045},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3223755657672882}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3681756.3697974","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3681756.3697974","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3681756.3697974","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIGGRAPH Asia 2024 Posters","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3681756.3697974","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3681756.3697974","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3681756.3697974","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIGGRAPH Asia 2024 Posters","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4699999988079071,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2382875005","display_name":null,"funder_award_id":"2020R1A2C1015146","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G3034753964","display_name":null,"funder_award_id":"grant","funder_id":"https://openalex.org/F4320320671","funder_display_name":"National Research Foundation"},{"id":"https://openalex.org/G342704958","display_name":null,"funder_award_id":"funded","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G982292920","display_name":null,"funder_award_id":"NRF-20","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404978401.pdf","grobid_xml":"https://content.openalex.org/works/W4404978401.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W2787801451"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W3046775127","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474"],"abstract_inverted_index":{"Figure":[0],"1:":[1],"(a):":[2],"Model":[3],"architecture":[4],"and":[5,18,33,47],"training":[6],"scheme":[7],"including":[8],"Multimodal":[9],"Autoencoder,":[10],"Image-to-Text":[11],"Translator,":[12],"pre-trained":[13],"models":[14],"(CLIP,":[15],"ViT,":[16],"GPT-2)":[17],"the":[19],"loss":[20],"functions":[21],",":[22,24],"-":[23,25],".(b):":[26],"Original":[27],"Images":[28],"from":[29,37],"CIFAR-10":[30],"dataset":[31],"(b1)":[32],"their":[34],"reconstructed":[35],"outputs":[36],"image":[38,46],"only":[39,43],"input":[40,44],"(b2),":[41],"text":[42,48],"(b3),":[45],"combined":[49],"inputs":[50],"(b4).":[51]},"counts_by_year":[],"updated_date":"2026-04-17T18:11:37.981687","created_date":"2025-10-10T00:00:00"}