{"id":"https://openalex.org/W3206660842","doi":"https://doi.org/10.1145/3474085.3475465","title":"Cross-modal Retrieval and Synthesis (X-MRS): Closing the Modality Gap in Shared Subspace Learning","display_name":"Cross-modal Retrieval and Synthesis (X-MRS): Closing the Modality Gap in Shared Subspace Learning","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3206660842","doi":"https://doi.org/10.1145/3474085.3475465","mag":"3206660842"},"language":"en","primary_location":{"id":"doi:10.1145/3474085.3475465","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475465","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/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, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung AI Center, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I4210117523"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017287333","display_name":"Hai Pham","orcid":"https://orcid.org/0000-0001-9391-5514"},"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":"Hai X. Pham","raw_affiliation_strings":["Samsung AI Center, Cambridge, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung AI Center, 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, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung AI Center, 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":2.7689,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":{"value":0.93867774,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3192","last_page":"3201"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9925000071525574,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9925000071525574,"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":0.991100013256073,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9641000032424927,"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":0.7504695653915405},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5761868357658386},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5457947850227356},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5373713970184326},{"id":"https://openalex.org/keywords/semantic-gap","display_name":"Semantic gap","score":0.5299630761146545},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.47353455424308777},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.46294060349464417},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4588201344013214},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4492083489894867},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.41614747047424316},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.4143190383911133},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3718632459640503},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3340548276901245},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2369149625301361},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.2143876850605011}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7504695653915405},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5761868357658386},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5457947850227356},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5373713970184326},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.5299630761146545},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47353455424308777},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.46294060349464417},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4588201344013214},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4492083489894867},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.41614747047424316},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.4143190383911133},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3718632459640503},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3340548276901245},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2369149625301361},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.2143876850605011},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3474085.3475465","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475465","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":[{"display_name":"Zero hunger","score":0.5699999928474426,"id":"https://metadata.un.org/sdg/2"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W606460737","https://openalex.org/W1773149199","https://openalex.org/W1895577753","https://openalex.org/W2064675550","https://openalex.org/W2124095343","https://openalex.org/W2153579005","https://openalex.org/W2157331557","https://openalex.org/W2194775991","https://openalex.org/W2481240925","https://openalex.org/W2737041163","https://openalex.org/W2897152025","https://openalex.org/W2933138175","https://openalex.org/W2948037078","https://openalex.org/W2962964995","https://openalex.org/W2963055199","https://openalex.org/W2963216553","https://openalex.org/W2963966654","https://openalex.org/W2963997278","https://openalex.org/W2964024144","https://openalex.org/W2966792645","https://openalex.org/W2979304729","https://openalex.org/W2995025772","https://openalex.org/W3009381623","https://openalex.org/W3034667500","https://openalex.org/W3035032757","https://openalex.org/W3106031848","https://openalex.org/W3108413361","https://openalex.org/W3111790582","https://openalex.org/W3137684688"],"related_works":["https://openalex.org/W1980381208","https://openalex.org/W2364594919","https://openalex.org/W2081900870","https://openalex.org/W1861706286","https://openalex.org/W2219338811","https://openalex.org/W2167092671","https://openalex.org/W2149583853","https://openalex.org/W2143002539","https://openalex.org/W2130386332","https://openalex.org/W1120847856"],"abstract_inverted_index":{"Computational":[0],"food":[1,53,68,151],"analysis":[2,114],"(CFA)":[3],"naturally":[4],"requires":[5],"multi-modal":[6,24],"evidence":[7],"of":[8,35,42,92,142,167,179],"a":[9,32,50,82,149],"particular":[10],"food,":[11],"e.g.,":[12],"images,":[13],"recipe":[14,78,157,183],"text,":[15],"etc.":[16],"A":[17],"key":[18],"to":[19,30,96],"making":[20],"CFA":[21],"possible":[22],"is":[23,146],"shared":[25,56],"representation":[26,34,57,123,145,174],"learning,":[27],"which":[28],"aims":[29],"create":[31],"joint":[33,177],"the":[36,43,61,67,90,99,103,116,122,126,131,139,143,164,172,176,181,190],"multiple":[37,109],"views":[38],"(text":[39],"and":[40,111,184],"image)":[41],"data.":[44,69],"In":[45],"this":[46],"work":[47],"we":[48,88],"propose":[49,89],"method":[51,72,128],"for":[52],"domain":[54],"cross-modal":[55],"learning":[58],"that":[59,121,171],"preserves":[60],"vast":[62],"semantic":[63],"richness":[64],"present":[65],"in":[66],"Our":[70],"proposed":[71,127],"employs":[73],"an":[74],"effective":[75],"transformer-based":[76],"multilingual":[77,94],"encoder":[79],"coupled":[80],"with":[81],"traditional":[83],"image":[84,152],"embedding":[85],"architecture.":[86],"Here,":[87],"use":[91],"imperfect":[93],"translations":[95],"effectively":[97,162],"regularize":[98],"model":[100,154],"while":[101],"at":[102],"same":[104],"time":[105],"adding":[106],"functionality":[107],"across":[108],"languages":[110],"alphabets.":[112],"Experimental":[113],"on":[115,135,156],"public":[117],"Recipe1M":[118],"dataset":[119],"shows":[120],"learned":[124,144,173],"via":[125],"significantly":[129],"outperforms":[130],"current":[132],"state-of-the-arts":[133],"(SOTA)":[134],"retrieval":[136],"tasks.":[137],"Furthermore,":[138],"representational":[140],"power":[141],"demonstrated":[147],"through":[148],"generative":[150],"synthesis":[153],"conditioned":[155],"embeddings.":[158],"Synthesized":[159],"images":[160],"can":[161],"reproduce":[163],"visual":[165,186],"appearance":[166],"paired":[168],"samples,":[169],"indicating":[170],"captures":[175],"semantics":[178],"both":[180],"textual":[182],"its":[185],"content,":[187],"thus":[188],"narrowing":[189],"modality":[191],"gap.":[192]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}