{"id":"https://openalex.org/W3186223381","doi":"https://doi.org/10.1109/tsc.2021.3098834","title":"Learning TFIDF Enhanced Joint Embedding for Recipe-Image Cross-Modal Retrieval Service","display_name":"Learning TFIDF Enhanced Joint Embedding for Recipe-Image Cross-Modal Retrieval Service","publication_year":2021,"publication_date":"2021-07-26","ids":{"openalex":"https://openalex.org/W3186223381","doi":"https://doi.org/10.1109/tsc.2021.3098834","mag":"3186223381"},"language":"en","primary_location":{"id":"doi:10.1109/tsc.2021.3098834","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsc.2021.3098834","pdf_url":null,"source":{"id":"https://openalex.org/S204223317","display_name":"IEEE Transactions on Services Computing","issn_l":"1939-1374","issn":["1939-1374","2372-0204"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Services Computing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2108.00724","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Zhongwei Xie","orcid":"https://orcid.org/0000-0001-6346-0707"},"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":["School of Computer Science, Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":"https://orcid.org/0000-0001-6346-0707","affiliations":[{"raw_affiliation_string":"School of Computer Science, Georgia Institute 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":["School of Computer Science, Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yanzhao Wu","orcid":"https://orcid.org/0000-0001-8761-5486"},"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":"Yanzhao Wu","raw_affiliation_strings":["School of Computer Science, Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":"https://orcid.org/0000-0001-8761-5486","affiliations":[{"raw_affiliation_string":"School of Computer Science, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Lin Li","orcid":"https://orcid.org/0000-0001-7553-6916"},"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":["School of Computer Science and Technology, Wuhan University of Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0001-7553-6916","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, 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":["School of Computer Science and Technology, Wuhan University of Technology, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, 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":1.6343,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.84177716,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"15","issue":"6","first_page":"3304","last_page":"3316"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.6281999945640564,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.6281999945640564,"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":0.12430000305175781,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.058400001376867294,"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/tf\u2013idf","display_name":"tf\u2013idf","score":0.8889999985694885},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5715000033378601},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.534500002861023},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5335999727249146},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5187000036239624},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.5037999749183655},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.42800000309944153},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.40400001406669617},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.40389999747276306}],"concepts":[{"id":"https://openalex.org/C81758059","wikidata":"https://www.wikidata.org/wiki/Q796584","display_name":"tf\u2013idf","level":3,"score":0.8889999985694885},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.835099995136261},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5715000033378601},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.534500002861023},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5335999727249146},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5309000015258789},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5231999754905701},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5187000036239624},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.5037999749183655},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.42800000309944153},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.40400001406669617},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.40389999747276306},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.38040000200271606},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3765000104904175},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.3727000057697296},{"id":"https://openalex.org/C89686163","wikidata":"https://www.wikidata.org/wiki/Q1187982","display_name":"Vector space model","level":2,"score":0.3386000096797943},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3294000029563904},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3280999958515167},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.30469998717308044},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.2770000100135803},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C2780479914","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Document classification","level":2,"score":0.2705000042915344},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.2694000005722046},{"id":"https://openalex.org/C2778671685","wikidata":"https://www.wikidata.org/wiki/Q219239","display_name":"Recipe","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.2615000009536743},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.25589999556541443},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tsc.2021.3098834","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsc.2021.3098834","pdf_url":null,"source":{"id":"https://openalex.org/S204223317","display_name":"IEEE Transactions on Services Computing","issn_l":"1939-1374","issn":["1939-1374","2372-0204"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Services Computing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2108.00724","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2108.00724","pdf_url":"https://arxiv.org/pdf/2108.00724","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:2108.00724","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2108.00724","pdf_url":"https://arxiv.org/pdf/2108.00724","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":[{"id":"https://openalex.org/G505506343","display_name":null,"funder_award_id":"1564097","funder_id":"https://openalex.org/F4320335353","funder_display_name":"National Science Foundation of Sri Lanka"},{"id":"https://openalex.org/G634024503","display_name":null,"funder_award_id":"NSF 2038029","funder_id":"https://openalex.org/F4320335353","funder_display_name":"National Science Foundation of Sri Lanka"}],"funders":[{"id":"https://openalex.org/F4320309321","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44"},{"id":"https://openalex.org/F4320324638","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173"},{"id":"https://openalex.org/F4320335353","display_name":"National Science Foundation of Sri Lanka","ror":"https://ror.org/010xaa060"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1895577753","https://openalex.org/W1933349210","https://openalex.org/W1949478088","https://openalex.org/W1964073652","https://openalex.org/W1982635469","https://openalex.org/W2062903088","https://openalex.org/W2092361219","https://openalex.org/W2106277773","https://openalex.org/W2194775991","https://openalex.org/W2283195891","https://openalex.org/W2293499654","https://openalex.org/W2526198870","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/W2964137095","https://openalex.org/W3034303366","https://openalex.org/W3035032757","https://openalex.org/W4249992252","https://openalex.org/W6629028937","https://openalex.org/W6631190155","https://openalex.org/W6636510571","https://openalex.org/W6637373629","https://openalex.org/W6674875818","https://openalex.org/W6678470764","https://openalex.org/W6682691769","https://openalex.org/W6697395949","https://openalex.org/W6735531217","https://openalex.org/W6741409233","https://openalex.org/W6747980015","https://openalex.org/W6770595674"],"related_works":[],"abstract_inverted_index":{"It":[0],"is":[1,12,141],"widely":[2],"acknowledged":[3],"that":[4],"learning":[5,37,180],"joint":[6,183],"embeddings":[7],"of":[8,21,53,79,85,167,181],"recipes":[9],"with":[10,49,93,130],"images":[11],"challenging":[13],"due":[14],"to":[15,163,171],"the":[16,43,50,69,73,83,119,126,131,145,165,173,178,187,192,196],"diverse":[17],"composition":[18],"and":[19,47,76,111,151,170],"deformation":[20],"ingredients":[22,75],"in":[23,118,143],"cooking":[24,77,121],"procedures.":[25],"We":[26],"present":[27],"a":[28,38,99,102,149],"Multi-modal":[29],"Semantics":[30],"enhanced":[31,160],"Joint":[32],"Embedding":[33],"approach":[34,61,194],"(MSJE)":[35],"for":[36,106],"common":[39],"feature":[40,71,129,134],"space":[41],"between":[42,148],"two":[44],"modalities":[45],"(text":[46],"image),":[48],"ultimate":[51],"goal":[52],"providing":[54],"high-performance":[55],"cross-modal":[56,182],"retrieval":[57],"services.":[58],"Our":[59],"MSJE":[60],"has":[62],"three":[63],"unique":[64,146],"features.":[65],"First,":[66],"we":[67,97,124,156],"extract":[68],"TFIDF":[70,95,103,128,159],"from":[72],"title,":[74],"instructions":[78],"recipes.":[80],"By":[81],"determining":[82],"significance":[84],"word":[86],"sequences":[87],"through":[88,136],"combining":[89],"LSTM":[90,138],"learned":[91],"features":[92],"their":[94],"features,":[96],"encode":[98],"recipe":[100,127,132,150],"into":[101],"weighted":[104],"vector":[105],"capturing":[107,144],"significant":[108],"key":[109,114],"terms":[110,115],"how":[112],"such":[113],"are":[116],"used":[117],"corresponding":[120],"instructions.":[122],"Second,":[123],"combine":[125],"sequence":[133],"extracted":[135],"two-stage":[137],"networks,":[139],"which":[140],"effective":[142],"relationship":[147],"its":[152],"associated":[153],"image(s).":[154],"Third,":[155],"further":[157],"incorporate":[158],"category":[161],"semantics":[162],"improve":[164],"mapping":[166],"image":[168],"modality":[169],"regulate":[172],"similarity":[174],"loss":[175],"function":[176],"during":[177],"iterative":[179],"embedding.":[184],"Experiments":[185],"on":[186],"benchmark":[188],"dataset":[189],"Recipe1M":[190],"show":[191],"proposed":[193],"outperforms":[195],"state-of-the-art":[197],"approaches.":[198]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2021-08-02T00:00:00"}