{"id":"https://openalex.org/W3197950609","doi":"https://doi.org/10.1145/3460426.3463618","title":"Cross-Modal Image-Recipe Retrieval via Intra- and Inter-Modality Hybrid Fusion","display_name":"Cross-Modal Image-Recipe Retrieval via Intra- and Inter-Modality Hybrid Fusion","publication_year":2021,"publication_date":"2021-08-24","ids":{"openalex":"https://openalex.org/W3197950609","doi":"https://doi.org/10.1145/3460426.3463618","mag":"3197950609"},"language":"en","primary_location":{"id":"doi:10.1145/3460426.3463618","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3460426.3463618","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","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/A5100419510","display_name":"Jiao Li","orcid":"https://orcid.org/0000-0003-2645-330X"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiao Li","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026394624","display_name":"Jialiang Sun","orcid":"https://orcid.org/0000-0001-9073-3635"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jialiang Sun","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009074046","display_name":"Xing Xu","orcid":"https://orcid.org/0000-0001-5685-3123"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xing Xu","raw_affiliation_strings":["University of Electronic Science and\u00a0Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and\u00a0Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100901963","display_name":"Wei Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Yu","raw_affiliation_strings":["Glasgow College & University of Electronic Science and\u00a0Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"Glasgow College & University of Electronic Science and\u00a0Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074492050","display_name":"Fumin Shen","orcid":"https://orcid.org/0000-0001-7303-3231"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fumin Shen","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100419510"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":1.441,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.84127451,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"173","last_page":"182"},"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":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","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/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/T10824","display_name":"Image Retrieval and Classification Techniques","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/recipe","display_name":"Recipe","score":0.8282550573348999},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.808839738368988},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.6381995677947998},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5761987566947937},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5705977082252502},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5480995774269104},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4939020276069641},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.46429333090782166},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.46314215660095215},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.42978739738464355},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.35525572299957275}],"concepts":[{"id":"https://openalex.org/C2778671685","wikidata":"https://www.wikidata.org/wiki/Q219239","display_name":"Recipe","level":2,"score":0.8282550573348999},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.808839738368988},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6381995677947998},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5761987566947937},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5705977082252502},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5480995774269104},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4939020276069641},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.46429333090782166},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.46314215660095215},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.42978739738464355},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35525572299957275},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C31903555","wikidata":"https://www.wikidata.org/wiki/Q1637030","display_name":"Food science","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3460426.3463618","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3460426.3463618","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/2","display_name":"Zero hunger","score":0.5099999904632568}],"awards":[{"id":"https://openalex.org/G6438814647","display_name":null,"funder_award_id":"ZYGX2019Z015","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G8767697590","display_name":null,"funder_award_id":"61976049, 62072080, 61632007 and U20B2063","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1964073652","https://openalex.org/W2025341678","https://openalex.org/W2058837810","https://openalex.org/W2064675550","https://openalex.org/W2108598243","https://openalex.org/W2194011657","https://openalex.org/W2206370378","https://openalex.org/W2236282269","https://openalex.org/W2339074556","https://openalex.org/W2526198870","https://openalex.org/W2539302589","https://openalex.org/W2545564314","https://openalex.org/W2560674852","https://openalex.org/W2562417371","https://openalex.org/W2604325789","https://openalex.org/W2728515412","https://openalex.org/W2765440071","https://openalex.org/W2765707332","https://openalex.org/W2795389793","https://openalex.org/W2948037078","https://openalex.org/W2962856082","https://openalex.org/W2963055199","https://openalex.org/W2970231061","https://openalex.org/W3005971801","https://openalex.org/W3033103428","https://openalex.org/W3035032757","https://openalex.org/W3035485997","https://openalex.org/W3104826001","https://openalex.org/W3111984153","https://openalex.org/W4297826496","https://openalex.org/W6600302053","https://openalex.org/W6600553734"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W2167701463","https://openalex.org/W2110287964","https://openalex.org/W4307407935","https://openalex.org/W649759291"],"abstract_inverted_index":{"In":[0,134],"recent":[1],"years,":[2],"the":[3,7,19,32,40,43,54,64,72,84,124,129,147,152,159,171,188],"Internet":[4],"has":[5],"stimulated":[6],"explosion":[8],"of":[9,22,34,42,66,86],"multimedia":[10],"data.":[11],"Food-related":[12],"cooking":[13],"videos,":[14],"images,":[15],"and":[16,48,79,91,96,108,122,131,141,146,161],"recipes":[17,142],"promote":[18],"rapid":[20],"development":[21],"food":[23,46],"computing.":[24],"Image-recipe":[25,67],"retrieval":[26],"is":[27,185],"an":[28],"important":[29],"sub-task":[30],"in":[31],"field":[33],"cross-modal":[35],"retrieval,":[36,68],"which":[37],"focuses":[38],"on":[39,170],"measurement":[41],"association":[44],"between":[45,94,151],"image":[47],"recipe":[49],"(title,":[50],"ingredients,":[51],"instructions).":[52],"Although":[53],"existing":[55],"methods":[56],"have":[57],"proposed":[58],"some":[59],"feasible":[60],"solutions":[61],"to":[62,127,187],"achieve":[63],"goal":[65],"there":[69],"are":[70],"still":[71],"following":[73],"issues:":[74],"1)":[75],"complex":[76],"model":[77,115,179],"structure":[78],"time-consuming":[80],"training":[81],"process.":[82],"2)":[83],"lack":[85],"information":[87,92,138,149],"interaction":[88,150],"within":[89],"modalities":[90,154],"integration":[93],"images":[95,140],"recipes.":[97],"To":[98],"this":[99,135],"end,":[100],"we":[101],"propose":[102],"a":[103,117,182],"novel":[104],"lightweight":[105,183],"framework":[106],"namedIntra-":[107],"Inter-Modality":[109],"Hybrid":[110],"Fusion":[111],"(IMHF).":[112],"Our":[113],"IMHF":[114,180],"abandons":[116],"separate":[118],"deep":[119],"vision":[120],"encoder":[121],"utilizes":[123],"transformer":[125],"module":[126],"unify":[128],"visual":[130],"text":[132],"features.":[133],"way,":[136],"valuable":[137],"from":[139],"can":[143,155,164],"be":[144,156,165],"condensed":[145],"direct":[148],"two":[153],"promoted.":[157],"Both":[158],"intra-":[160],"inter-modality":[162],"fusion":[163],"realized.":[166],"Extensive":[167],"experiment":[168],"results":[169],"large-scale":[172],"benchmark":[173],"dataset":[174],"Recipe1M":[175],"demonstrate":[176],"that":[177],"our":[178],"with":[181],"architecture":[184],"superior":[186],"state-of-the-art":[189],"approaches.":[190]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}