{"id":"https://openalex.org/W3153694119","doi":"https://doi.org/10.1145/3404835.3462965","title":"Hybrid Fusion with Intra- and Cross-Modality Attention for Image-Recipe Retrieval","display_name":"Hybrid Fusion with Intra- and Cross-Modality Attention for Image-Recipe Retrieval","publication_year":2021,"publication_date":"2021-07-11","ids":{"openalex":"https://openalex.org/W3153694119","doi":"https://doi.org/10.1145/3404835.3462965","mag":"3153694119"},"language":"en","primary_location":{"id":"doi:10.1145/3404835.3462965","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3404835.3462965","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information 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/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 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/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":["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/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\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/A5020177102","display_name":"Zuo Cao","orcid":"https://orcid.org/0000-0001-9446-5105"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zuo Cao","raw_affiliation_strings":["MEITUAN, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"MEITUAN, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075556202","display_name":"Kai Zuo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kai Zuo","raw_affiliation_strings":["MEITUAN, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"MEITUAN, Shanghai, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052993469","display_name":"Heng Tao Shen","orcid":"https://orcid.org/0000-0002-2999-2088"},"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":"Heng Tao Shen","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"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100419510"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":1.9214,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.87870915,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"244","last_page":"254"},"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":0.9994000196456909,"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":0.9994000196456909,"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":0.9973000288009644,"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/recipe","display_name":"Recipe","score":0.981621503829956},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7373026609420776},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5964756011962891},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5661023855209351},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5491268634796143},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5370316505432129},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.49276283383369446},{"id":"https://openalex.org/keywords/association","display_name":"Association (psychology)","score":0.4353885054588318},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.343363881111145},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3355402946472168}],"concepts":[{"id":"https://openalex.org/C2778671685","wikidata":"https://www.wikidata.org/wiki/Q219239","display_name":"Recipe","level":2,"score":0.981621503829956},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7373026609420776},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5964756011962891},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5661023855209351},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5491268634796143},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5370316505432129},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.49276283383369446},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.4353885054588318},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.343363881111145},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3355402946472168},{"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3404835.3462965","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3404835.3462965","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Zero hunger","id":"https://metadata.un.org/sdg/2","score":0.44999998807907104}],"awards":[{"id":"https://openalex.org/G4875675335","display_name":null,"funder_award_id":"61976049, 61632007, U20B2063","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"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"}],"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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W114517082","https://openalex.org/W1964073652","https://openalex.org/W2012210378","https://openalex.org/W2025341678","https://openalex.org/W2053946370","https://openalex.org/W2058837810","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/W2562417371","https://openalex.org/W2594259972","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/W2962964995","https://openalex.org/W2963055199","https://openalex.org/W2963918631","https://openalex.org/W3005971801","https://openalex.org/W3033103428","https://openalex.org/W3035032757","https://openalex.org/W3111984153","https://openalex.org/W6600238479","https://openalex.org/W6600302053","https://openalex.org/W6600553734","https://openalex.org/W6601867051","https://openalex.org/W6609123738","https://openalex.org/W6835932164"],"related_works":["https://openalex.org/W258429745","https://openalex.org/W3161239248","https://openalex.org/W2561508161","https://openalex.org/W3195543079","https://openalex.org/W2098178683","https://openalex.org/W2740680361","https://openalex.org/W3207562294","https://openalex.org/W2604742737","https://openalex.org/W3021194804","https://openalex.org/W4386893202"],"abstract_inverted_index":{"Image-recipe":[0],"retrieval,":[1,61],"which":[2,167],"aims":[3],"at":[4],"retrieving":[5],"the":[6,28,49,71,76,88,127,139,142,155,165,170,176,184,195],"relevant":[7],"recipe":[8],"from":[9,164,174],"a":[10,32,42,100,134],"food":[11],"image":[12,84,160],"and":[13,25,80,86,93,107,131,136,162,178],"vice":[14],"versa,":[15],"is":[16,151],"now":[17],"attracting":[18],"widespread":[19],"attention,":[20],"since":[21],"sharing":[22],"food-related":[23],"images":[24],"recipes":[26,92],"on":[27,126,183,198],"Internet":[29],"has":[30],"become":[31],"popular":[33],"trend.":[34],"Existing":[35],"methods":[36,54],"have":[37,55],"formulated":[38],"this":[39,96],"problem":[40],"as":[41],"typical":[43],"cross-modal":[44],"retrieval":[45,201],"task":[46],"by":[47],"learning":[48],"image-recipe":[50,60,114,148,172,200],"similarity.":[51,115],"Though":[52],"these":[53],"made":[56],"inspiring":[57],"achievements":[58],"for":[59],"they":[62],"may":[63],"still":[64],"be":[65],"less":[66],"effective":[67],"to":[68,111,124,153],"jointly":[69,168],"incorporate":[70],"three":[72],"crucial":[73],"points:":[74],"(1)":[75],"association":[77],"between":[78,91,129,158],"ingredients":[79,130,163],"instructions,":[81],"(2)":[82],"fine-grained":[83,159],"information,":[85],"(3)":[87],"latent":[89],"alignment":[90],"images.":[94],"To":[95],"end,":[97],"we":[98],"propose":[99],"novel":[101],"framework":[102],"namedHybrid":[103],"Fusion":[104],"with":[105],"Intra-":[106],"Cross-Modality":[108],"Attention":[109],"(HF-ICMA)":[110],"learn":[112],"accurate":[113],"Our":[116],"HF-ICMA":[117],"model":[118,192],"adopts":[119],"an":[120,147],"intra-recipe":[121],"fusion":[122,149],"module":[123,150],"focus":[125],"interaction":[128],"instructions":[132],"within":[133],"recipe,":[135,166],"further":[137],"enriches":[138],"expressions":[140],"of":[141],"two":[143],"separate":[144],"embeddings.":[145],"Meanwhile,":[146],"devised":[152],"explore":[154],"potential":[156],"relationship":[157],"regions":[161],"forms":[169],"final":[171],"similarity":[173],"both":[175],"local":[177],"global":[179],"aspects.":[180],"Extensive":[181],"experiments":[182],"large-scale":[185],"benchmark":[186],"dataset":[187],"Recipe1M":[188],"show":[189],"that":[190],"our":[191],"significantly":[193],"outperforms":[194],"state-of-the-art":[196],"approaches":[197],"various":[199],"scenarios.":[202]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}