{"id":"https://openalex.org/W3206452946","doi":"https://doi.org/10.1145/3474085.3475448","title":"Learning Disentangled Factors from Paired Data in Cross-Modal Retrieval: An Implicit Identifiable VAE Approach","display_name":"Learning Disentangled Factors from Paired Data in Cross-Modal Retrieval: An Implicit Identifiable VAE Approach","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3206452946","doi":"https://doi.org/10.1145/3474085.3475448","mag":"3206452946"},"language":"en","primary_location":{"id":"doi:10.1145/3474085.3475448","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475448","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100670942","display_name":"Minyoung Kim","orcid":"https://orcid.org/0000-0002-5078-7142"},"institutions":[{"id":"https://openalex.org/I4210117523","display_name":"Samsung (United Kingdom)","ror":"https://ror.org/01w6gjq94","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210117523"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Minyoung Kim","raw_affiliation_strings":["Samsung AI Center Cambridge, Cambridge, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung AI Center Cambridge, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I4210117523"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056128187","display_name":"Ricardo Guerrero","orcid":null},"institutions":[{"id":"https://openalex.org/I4210117523","display_name":"Samsung (United Kingdom)","ror":"https://ror.org/01w6gjq94","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210117523"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ricardo Guerrero","raw_affiliation_strings":["Samsung AI Center Cambridge, Cambridge, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung AI Center Cambridge, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I4210117523"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020368096","display_name":"Vladimir Pavlovi\u0107","orcid":"https://orcid.org/0000-0003-3979-1236"},"institutions":[{"id":"https://openalex.org/I4210117523","display_name":"Samsung (United Kingdom)","ror":"https://ror.org/01w6gjq94","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210117523"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Vladimir Pavlovic","raw_affiliation_strings":["Samsung AI Center Cambridge, Cambridge, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung AI Center Cambridge, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I4210117523"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210117523"],"apc_list":null,"apc_paid":null,"fwci":0.2931,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.53986615,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2862","last_page":"2870"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9998000264167786,"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"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9997000098228455,"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":0.9994999766349792,"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/autoencoder","display_name":"Autoencoder","score":0.7789009809494019},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.7399365901947021},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7231135964393616},{"id":"https://openalex.org/keywords/jacobian-matrix-and-determinant","display_name":"Jacobian matrix and determinant","score":0.5844101309776306},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5751827955245972},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5502068996429443},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5394095182418823},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5270871520042419},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.47904789447784424},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4695326089859009},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4592885673046112},{"id":"https://openalex.org/keywords/variable","display_name":"Variable (mathematics)","score":0.44418755173683167},{"id":"https://openalex.org/keywords/latent-variable-model","display_name":"Latent variable model","score":0.44216859340667725},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.42138370871543884},{"id":"https://openalex.org/keywords/kronecker-delta","display_name":"Kronecker delta","score":0.4128345847129822},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.41114088892936707},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.41057026386260986},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.395679771900177},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17157310247421265},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.09889766573905945}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.7789009809494019},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.7399365901947021},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7231135964393616},{"id":"https://openalex.org/C200331156","wikidata":"https://www.wikidata.org/wiki/Q506041","display_name":"Jacobian matrix and determinant","level":2,"score":0.5844101309776306},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5751827955245972},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5502068996429443},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5394095182418823},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5270871520042419},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.47904789447784424},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4695326089859009},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4592885673046112},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.44418755173683167},{"id":"https://openalex.org/C65965080","wikidata":"https://www.wikidata.org/wiki/Q1806885","display_name":"Latent variable model","level":3,"score":0.44216859340667725},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.42138370871543884},{"id":"https://openalex.org/C39482219","wikidata":"https://www.wikidata.org/wiki/Q192826","display_name":"Kronecker delta","level":2,"score":0.4128345847129822},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.41114088892936707},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.41057026386260986},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.395679771900177},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17157310247421265},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.09889766573905945},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3474085.3475448","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475448","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1959608418","https://openalex.org/W2096135798","https://openalex.org/W2112796928","https://openalex.org/W2125290066","https://openalex.org/W2188365844","https://openalex.org/W2266728343","https://openalex.org/W2388114291","https://openalex.org/W2434741482","https://openalex.org/W2530846021","https://openalex.org/W2559823555","https://openalex.org/W2560982456","https://openalex.org/W2565041183","https://openalex.org/W2605649771","https://openalex.org/W2617934075","https://openalex.org/W2737041163","https://openalex.org/W2737198141","https://openalex.org/W2753738274","https://openalex.org/W2765440071","https://openalex.org/W2765707332","https://openalex.org/W2766527109","https://openalex.org/W2785519580","https://openalex.org/W2785961484","https://openalex.org/W2786897815","https://openalex.org/W2805122419","https://openalex.org/W2808359495","https://openalex.org/W2897152025","https://openalex.org/W2914441330","https://openalex.org/W2952300525","https://openalex.org/W2956607501","https://openalex.org/W2960416371","https://openalex.org/W2962738009","https://openalex.org/W2963198154","https://openalex.org/W2963504544","https://openalex.org/W2963693044","https://openalex.org/W2963997278","https://openalex.org/W2964127395","https://openalex.org/W2982905682","https://openalex.org/W4246999471","https://openalex.org/W6600125713"],"related_works":["https://openalex.org/W2988134182","https://openalex.org/W2461917396","https://openalex.org/W1966667550","https://openalex.org/W2037497866","https://openalex.org/W4243467573","https://openalex.org/W1502435251","https://openalex.org/W62001224","https://openalex.org/W3032390039","https://openalex.org/W1584341211","https://openalex.org/W3122667150"],"abstract_inverted_index":{"We":[0],"tackle":[1],"the":[2,6,15,23,40,49,73,79,100,106,116,130,134,148,160],"problem":[3],"of":[4,57,72,99,133],"learning":[5],"underlying":[7],"disentangled":[8],"latent":[9,44,86,166],"factors":[10,150,161],"that":[11,93,129],"are":[12,28,151],"shared":[13],"between":[14],"paired":[16],"bi-modal":[17],"data":[18,24,81,119],"in":[19,25],"cross-modal":[20],"retrieval.":[21],"Typically":[22],"both":[26],"modalities":[27],"complex,":[29],"structured,":[30],"and":[31,36],"high":[32],"dimensional":[33],"(e.g.,":[34],"image":[35],"text),":[37],"for":[38],"which":[39,76,124],"conventional":[41,165],"deep":[42],"auto-encoding":[43],"variable":[45,87,167],"models":[46],"such":[47],"as":[48,120],"Variational":[50],"Autoencoder":[51],"(VAE)":[52],"often":[53],"suffer":[54],"from":[55,84,105],"difficulty":[56],"accurate":[58],"decoder":[59],"training":[60],"or":[61],"realistic":[62],"synthesis.":[63],"In":[64],"this":[65],"paper":[66],"we":[67,111],"propose":[68],"a":[69,85],"novel":[70],"idea":[71],"implicit":[74,90],"decoder,":[75],"completely":[77],"removes":[78],"ambient":[80],"decoding":[82],"module":[83],"model,":[88,110],"via":[89],"encoder":[91],"inversion":[92],"is":[94,156],"achieved":[95],"by":[96],"Jacobian":[97],"regularization":[98],"low-dimensional":[101],"embedding":[102],"function.":[103],"Motivated":[104],"recent":[107],"Identifiable-VAE":[108],"(IVAE)":[109],"modify":[112],"it":[113],"to":[114,127,158],"incorporate":[115],"query":[117],"modality":[118],"conditioning":[121],"auxiliary":[122],"input,":[123],"allows":[125],"us":[126],"prove":[128],"true":[131,149],"parameters":[132],"model":[135,155],"can":[136],"be":[137],"identifiable":[138],"under":[139],"some":[140],"regularity":[141],"conditions.":[142],"Tested":[143],"on":[144],"various":[145],"datasets":[146],"where":[147],"fully/partially":[152],"available,":[153],"our":[154],"shown":[157],"identify":[159],"accurately,":[162],"significantly":[163],"outperforming":[164],"models.":[168]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}