{"id":"https://openalex.org/W3190517769","doi":"https://doi.org/10.1145/3459637.3482270","title":"Learning Joint Embedding with Modality Alignments for Cross-Modal Retrieval of Recipes and Food Images","display_name":"Learning Joint Embedding with Modality Alignments for Cross-Modal Retrieval of Recipes and Food Images","publication_year":2021,"publication_date":"2021-10-26","ids":{"openalex":"https://openalex.org/W3190517769","doi":"https://doi.org/10.1145/3459637.3482270","mag":"3190517769"},"language":"en","primary_location":{"id":"doi:10.1145/3459637.3482270","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3459637.3482270","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2108.03788","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Zhongwei Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhongwei Xie","raw_affiliation_strings":["Georgia Institute of Technology & Wuhan University of Technology, Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology & Wuhan University of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ling Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ling Liu","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Lin Li","orcid":null},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Li","raw_affiliation_strings":["Wuhan University of Technology, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University of Technology, Wuhan, China","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"last","author":{"id":null,"display_name":"Luo Zhong","orcid":null},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Luo Zhong","raw_affiliation_strings":["Wuhan University of Technology, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University of Technology, Wuhan, China","institution_ids":["https://openalex.org/I196699116"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6682,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.78705123,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2221","last_page":"2230"},"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":0.9990000128746033,"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":0.9990000128746033,"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":0.9980000257492065,"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":0.9969000220298767,"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/embedding","display_name":"Embedding","score":0.8989999890327454},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5770999789237976},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5407999753952026},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5063999891281128},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.49959999322891235},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48590001463890076},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.45170000195503235},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4205999970436096},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.3910999894142151}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.8989999890327454},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6748999953269958},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6474000215530396},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5770999789237976},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5407999753952026},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5063999891281128},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.49959999322891235},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48590001463890076},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.45170000195503235},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4205999970436096},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4025999903678894},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.3910999894142151},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.34779998660087585},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.32199999690055847},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.3190999925136566},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.3010999858379364},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.2973000109195709},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2953000068664551},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.2863999903202057},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.27459999918937683},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.26809999346733093},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.26570001244544983},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.25450000166893005},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25049999356269836}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3459637.3482270","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3459637.3482270","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2108.03788","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2108.03788","pdf_url":"https://arxiv.org/pdf/2108.03788","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2108.03788","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2108.03788","pdf_url":"https://arxiv.org/pdf/2108.03788","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W12634471","https://openalex.org/W1964073652","https://openalex.org/W1978394996","https://openalex.org/W1982635469","https://openalex.org/W2092361219","https://openalex.org/W2106277773","https://openalex.org/W2137918516","https://openalex.org/W2194775991","https://openalex.org/W2293499654","https://openalex.org/W2526198870","https://openalex.org/W2549139847","https://openalex.org/W2565041183","https://openalex.org/W2604325789","https://openalex.org/W2728515412","https://openalex.org/W2737041163","https://openalex.org/W2765440071","https://openalex.org/W2767221212","https://openalex.org/W2897152025","https://openalex.org/W2948037078","https://openalex.org/W2963055199","https://openalex.org/W2963997278","https://openalex.org/W3034303366","https://openalex.org/W3035032757","https://openalex.org/W6741409233"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,77,131],"three-tier":[4],"modality":[5,67,87],"alignment":[6,68,88,104,119,141,149],"approach":[7,171],"to":[8,100,121,134,143,150],"learning":[9,109],"text-image":[10],"joint":[11,72,108,136,154],"embedding,":[12],"coined":[13],"as":[14,95,130],"JEMA,":[15],"for":[16,178],"cross-modal":[17,118,139,175],"retrieval":[18],"of":[19,92,110],"cooking":[20],"recipes":[21,162],"and":[22,40,45,181],"food":[23],"images.":[24],"The":[25,64,85,116,138],"first":[26],"tier":[27,66],"improves":[28],"recipe":[29,128],"text":[30],"embedding":[31,49,59,73,114,147,155,176],"by":[32,50],"optimizing":[33],"the":[34,47,52,57,70,96,103,107,111,123,127,135,145,153,160,168,173],"LSTM":[35],"networks":[36],"with":[37,56,62,82,126,159],"term":[38],"extraction":[39],"ranking":[41],"enhanced":[42],"sequence":[43],"patterns,":[44],"optimizes":[46,69],"image":[48,54,124],"combining":[51],"ResNeXt-101":[53],"encoder":[55],"category":[58,125,129],"using":[60,76],"wideResNet-50":[61],"word2vec.":[63],"second":[65],"textual-visual":[71],"loss":[74,81,98,132],"function":[75],"double":[78],"batch-hard":[79],"triplet":[80],"soft-margin":[83],"optimization.":[84],"third":[86],"incorporates":[89],"two":[90,112],"types":[91],"cross-modality":[93],"alignments":[94],"auxiliary":[97],"regularizations":[99],"further":[101,151],"reduce":[102],"errors":[105],"in":[106],"modality-specific":[113],"functions.":[115],"category-based":[117],"aims":[120,142],"align":[122],"regularization":[133],"embedding.":[137],"discriminator-based":[140],"add":[144],"visual-textual":[146],"distribution":[148],"regularize":[152],"loss.":[156],"Extensive":[157],"experiments":[158],"one-million":[161],"benchmark":[163],"dataset":[164],"Recipe1M":[165],"demonstrate":[166],"that":[167],"proposed":[169],"JEMA":[170],"outperforms":[172],"state-of-the-art":[174],"methods":[177],"both":[179],"image-to-recipe":[180],"recipe-to-image":[182],"retrievals.":[183]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3}],"updated_date":"2026-08-06T08:24:18.245995","created_date":"2021-08-16T00:00:00"}