{"id":"https://openalex.org/W3033103428","doi":"https://doi.org/10.1145/3372278.3390681","title":"Sentence-based and Noise-robust Cross-modal Retrieval on Cooking Recipes and Food Images","display_name":"Sentence-based and Noise-robust Cross-modal Retrieval on Cooking Recipes and Food Images","publication_year":2020,"publication_date":"2020-06-02","ids":{"openalex":"https://openalex.org/W3033103428","doi":"https://doi.org/10.1145/3372278.3390681","mag":"3033103428"},"language":"en","primary_location":{"id":"doi:10.1145/3372278.3390681","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3372278.3390681","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 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/A5059912501","display_name":"Zichen Zan","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":true,"raw_author_name":"Zichen Zan","raw_affiliation_strings":["Wuhan University of Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Wuhan University of Technology, Wuhan, China","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100412815","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":["Wuhan University of Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Wuhan University of Technology, Wuhan, China","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079797505","display_name":"Jianquan Liu","orcid":"https://orcid.org/0000-0003-4303-9020"},"institutions":[{"id":"https://openalex.org/I118347220","display_name":"NEC (Japan)","ror":"https://ror.org/04jndar25","country_code":"JP","type":"company","lineage":["https://openalex.org/I118347220"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jianquan Liu","raw_affiliation_strings":["NEC Corporation, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"NEC Corporation, Tokyo, Japan","institution_ids":["https://openalex.org/I118347220"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100639988","display_name":"Dong Zhou","orcid":"https://orcid.org/0000-0002-3310-8347"},"institutions":[{"id":"https://openalex.org/I121296143","display_name":"Hunan University of Science and Technology","ror":"https://ror.org/02m9vrb24","country_code":"CN","type":"education","lineage":["https://openalex.org/I121296143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Zhou","raw_affiliation_strings":["Hunan University of Science and Technology, Hunan, China"],"affiliations":[{"raw_affiliation_string":"Hunan University of Science and Technology, Hunan, China","institution_ids":["https://openalex.org/I121296143"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5059912501"],"corresponding_institution_ids":["https://openalex.org/I196699116"],"apc_list":null,"apc_paid":null,"fwci":1.6609,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.86264032,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"117","last_page":"125"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9923999905586243,"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":0.9923999905586243,"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":0.9890000224113464,"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":0.9886999726295471,"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":0.8160101175308228},{"id":"https://openalex.org/keywords/recipe","display_name":"Recipe","score":0.6705383062362671},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5779881477355957},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5428377389907837},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5064445734024048},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5032584071159363},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.4778137505054474},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.47278520464897156},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.4696209728717804},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.43318748474121094},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3805622160434723},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.21774205565452576}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8160101175308228},{"id":"https://openalex.org/C2778671685","wikidata":"https://www.wikidata.org/wiki/Q219239","display_name":"Recipe","level":2,"score":0.6705383062362671},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5779881477355957},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5428377389907837},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5064445734024048},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5032584071159363},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.4778137505054474},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.47278520464897156},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.4696209728717804},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.43318748474121094},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3805622160434723},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.21774205565452576},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3372278.3390681","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3372278.3390681","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Zero hunger","score":0.46000000834465027,"id":"https://metadata.un.org/sdg/2"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1969752030","https://openalex.org/W2194775991","https://openalex.org/W2209920088","https://openalex.org/W2527643446","https://openalex.org/W2545564314","https://openalex.org/W2565041183","https://openalex.org/W2582558662","https://openalex.org/W2583892095","https://openalex.org/W2594259972","https://openalex.org/W2598634450","https://openalex.org/W2606965845","https://openalex.org/W2728515412","https://openalex.org/W2737041163","https://openalex.org/W2761189739","https://openalex.org/W2799150641","https://openalex.org/W2897152025","https://openalex.org/W2948037078","https://openalex.org/W2948947170","https://openalex.org/W2962691457","https://openalex.org/W2963217233","https://openalex.org/W2963633722","https://openalex.org/W2963997278","https://openalex.org/W2964216321","https://openalex.org/W2981631843","https://openalex.org/W2981771452","https://openalex.org/W3105204788","https://openalex.org/W4249033934","https://openalex.org/W4297826496"],"related_works":["https://openalex.org/W258429745","https://openalex.org/W3161239248","https://openalex.org/W1584543623","https://openalex.org/W2561508161","https://openalex.org/W3195543079","https://openalex.org/W2098178683","https://openalex.org/W2740680361","https://openalex.org/W3187068967","https://openalex.org/W2604742737","https://openalex.org/W4386893202"],"abstract_inverted_index":{"In":[0,85],"recent":[1],"years,":[2],"people":[3],"are":[4],"facing":[5],"with":[6,137,158],"billions":[7],"of":[8,43,66,185],"food":[9,28,52,76,134],"images,":[10],"videos":[11],"and":[12,30,48,68,72,108,140,188],"recipes":[13,47],"on":[14,38,113,168,194],"social":[15],"medias.":[16],"An":[17],"appropriate":[18],"technology":[19],"is":[20],"highly":[21],"desired":[22],"to":[23,78,93,119,129,146,163],"retrieve":[24],"accurate":[25],"contents":[26],"across":[27],"images":[29,53,77,135],"cooking":[31],"recipes,":[32,71],"like":[33],"cross-modal":[34],"retrieval":[35,56,96,169],"framework.":[36],"Based":[37],"our":[39,86,176],"observations,":[40],"the":[41,49,62,95,165,180,195],"order":[42],"sequential":[44,64],"sentences":[45],"in":[46,51,70,75,105,183],"noises":[50],"will":[54],"affect":[55],"results.":[57,170],"We":[58,99,125,151],"take":[59],"into":[60],"account":[61],"sentence-level":[63],"orders":[65],"instructions":[67,104],"ingredients":[69],"noise":[73,166],"portion":[74],"propose":[79,89],"a":[80,153],"new":[81,91,154],"framework":[82,177],"for":[83],"cross-retrieval.":[84],"framework,":[87],"we":[88],"three":[90,110],"strategies":[92],"improve":[94],"accuracy.":[97],"(1)":[98],"encode":[100],"recipe":[101,138],"titles,":[102],"ingredients,":[103],"sentence":[106],"level,":[107],"adopt":[109,141],"attention":[111,127],"networks":[112],"multi-layer":[114],"hidden":[115],"state":[116],"features":[117,132],"separately":[118],"capture":[120],"more":[121],"semantic":[122],"information.":[123],"(2)":[124],"apply":[126],"mechanism":[128],"select":[130],"effective":[131,160],"from":[133],"incorporating":[136],"embeddings,":[139],"an":[142,159],"adversarial":[143],"learning":[144],"strategy":[145,162],"enhance":[147],"modality":[148],"alignment.":[149],"(3)":[150],"design":[152],"triplet":[155],"loss":[156],"scheme":[157],"sampling":[161],"reduce":[164],"impact":[167],"The":[171],"experimental":[172],"results":[173],"show":[174],"that":[175],"clearly":[178],"outperforms":[179],"state-of-art":[181],"methods":[182],"terms":[184],"median":[186],"rank":[187],"recall":[189],"rate":[190],"at":[191],"top":[192],"k":[193],"Recipe":[196],"1M":[197],"dataset.":[198]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}