{"id":"https://openalex.org/W4372342062","doi":"https://doi.org/10.1109/icassp49357.2023.10095762","title":"Multi-Modal Food Classification in a Diet Tracking System with Spoken and Visual Inputs","display_name":"Multi-Modal Food Classification in a Diet Tracking System with Spoken and Visual Inputs","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372342062","doi":"https://doi.org/10.1109/icassp49357.2023.10095762"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095762","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10095762","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5030461592","display_name":"Shivani Gowda","orcid":null},"institutions":[{"id":"https://openalex.org/I35566140","display_name":"Loyola Marymount University","ror":"https://ror.org/00xhj8c72","country_code":"US","type":"education","lineage":["https://openalex.org/I35566140"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Shivani Gowda","raw_affiliation_strings":["Loyola Marymount University,Computer Science Department,Los Angeles,CA,USA","Computer Science Department, Loyola Marymount University, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"Loyola Marymount University,Computer Science Department,Los Angeles,CA,USA","institution_ids":["https://openalex.org/I35566140"]},{"raw_affiliation_string":"Computer Science Department, Loyola Marymount University, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I35566140"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100708726","display_name":"Yifan Hu","orcid":"https://orcid.org/0000-0003-2017-924X"},"institutions":[{"id":"https://openalex.org/I35566140","display_name":"Loyola Marymount University","ror":"https://ror.org/00xhj8c72","country_code":"US","type":"education","lineage":["https://openalex.org/I35566140"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yifan Hu","raw_affiliation_strings":["Loyola Marymount University,Computer Science Department,Los Angeles,CA,USA","Computer Science Department, Loyola Marymount University, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"Loyola Marymount University,Computer Science Department,Los Angeles,CA,USA","institution_ids":["https://openalex.org/I35566140"]},{"raw_affiliation_string":"Computer Science Department, Loyola Marymount University, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I35566140"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013714205","display_name":"Mandy Korpusik","orcid":null},"institutions":[{"id":"https://openalex.org/I35566140","display_name":"Loyola Marymount University","ror":"https://ror.org/00xhj8c72","country_code":"US","type":"education","lineage":["https://openalex.org/I35566140"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mandy Korpusik","raw_affiliation_strings":["Loyola Marymount University,Computer Science Department,Los Angeles,CA,USA","Computer Science Department, Loyola Marymount University, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"Loyola Marymount University,Computer Science Department,Los Angeles,CA,USA","institution_ids":["https://openalex.org/I35566140"]},{"raw_affiliation_string":"Computer Science Department, Loyola Marymount University, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I35566140"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5030461592"],"corresponding_institution_ids":["https://openalex.org/I35566140"],"apc_list":null,"apc_paid":null,"fwci":0.5812,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.6830869,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10866","display_name":"Nutritional Studies and Diet","score":0.9944000244140625,"subfield":{"id":"https://openalex.org/subfields/2739","display_name":"Public Health, Environmental and Occupational Health"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10866","display_name":"Nutritional Studies and Diet","score":0.9944000244140625,"subfield":{"id":"https://openalex.org/subfields/2739","display_name":"Public Health, Environmental and Occupational Health"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9470000267028809,"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/T11667","display_name":"Advanced Chemical Sensor Technologies","score":0.9180999994277954,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.7302923202514648},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6931750774383545},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5635015964508057},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.536093533039093},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4494110345840454},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4396294057369232},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4213279187679291},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35860222578048706},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08123388886451721}],"concepts":[{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7302923202514648},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6931750774383545},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5635015964508057},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.536093533039093},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4494110345840454},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4396294057369232},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4213279187679291},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35860222578048706},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08123388886451721},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095762","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10095762","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Zero hunger","score":0.6299999952316284,"id":"https://metadata.un.org/sdg/2"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1522301498","https://openalex.org/W1686810756","https://openalex.org/W1849277567","https://openalex.org/W1967702788","https://openalex.org/W1982635469","https://openalex.org/W2064675550","https://openalex.org/W2072128103","https://openalex.org/W2097117768","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2293499654","https://openalex.org/W2341345999","https://openalex.org/W2404910842","https://openalex.org/W2466671568","https://openalex.org/W2548196899","https://openalex.org/W2593614619","https://openalex.org/W2746155567","https://openalex.org/W2801667291","https://openalex.org/W2808487880","https://openalex.org/W2884001105","https://openalex.org/W2891635869","https://openalex.org/W2896457183","https://openalex.org/W2900770945","https://openalex.org/W2946245082","https://openalex.org/W2957307908","https://openalex.org/W2966715458","https://openalex.org/W2968124245","https://openalex.org/W2969876226","https://openalex.org/W2970231061","https://openalex.org/W2972566716","https://openalex.org/W2997544875","https://openalex.org/W3014494055","https://openalex.org/W3090449556","https://openalex.org/W3094502228","https://openalex.org/W3126792443","https://openalex.org/W3156333129","https://openalex.org/W3170034074","https://openalex.org/W4385245566","https://openalex.org/W6630875275","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6639204139","https://openalex.org/W6684191040","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6766037382","https://openalex.org/W6766904570","https://openalex.org/W6767211374","https://openalex.org/W6767279747","https://openalex.org/W6776721752","https://openalex.org/W6784333009","https://openalex.org/W6789753369"],"related_works":["https://openalex.org/W2118758177","https://openalex.org/W4330338194","https://openalex.org/W2153520307","https://openalex.org/W2151459719","https://openalex.org/W623261610","https://openalex.org/W2316630966","https://openalex.org/W4401374939","https://openalex.org/W1976696937","https://openalex.org/W2059453987","https://openalex.org/W2036523811"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"present":[4],"multi-modal":[5,69,116],"approaches":[6,72],"to":[7,31,104],"diet":[8,20],"tracking.":[9,52],"As":[10],"health":[11],"and":[12,93],"well-being":[13],"become":[14],"increasingly":[15],"important,":[16],"mobile":[17],"applications":[18,27],"for":[19,63,98],"tracking":[21],"attract":[22],"much":[23],"interest.":[24],"However,":[25],"these":[26],"often":[28],"require":[29],"users":[30],"log":[32],"their":[33],"meals":[34],"based":[35],"on":[36,73],"relatively":[37],"unreliable":[38],"memory":[39],"recall,":[40],"thereby":[41],"underestimating":[42],"nutritional":[43],"intake":[44],"and,":[45],"thus,":[46],"undermining":[47],"the":[48,111],"efforts":[49],"of":[50,91,96,113],"nutrition":[51],"To":[53],"accurately":[54],"record":[55],"dietary":[56],"intake,":[57],"there":[58],"is":[59],"an":[60],"increasing":[61],"need":[62],"image":[64],"computational":[65],"methods.":[66],"We":[67,102],"investigated":[68],"transfer":[70],"learning":[71,118],"a":[74,80,85],"novel,":[75],"food-specific":[76],"image-text":[77],"dataset,":[78],"specifically":[79],"Vision-and-Language":[81],"Transformer":[82],"that":[83],"achieves":[84],"held-out":[86],"test":[87],"set":[88],"Micro-F1":[89],"score":[90,95],"77.70%":[92],"Macro-F1":[94],"51.43%":[97],"696":[99],"food":[100],"categories.":[101],"aim":[103],"give":[105],"other":[106],"researchers":[107],"new":[108],"insight":[109],"into":[110],"process":[112],"developing":[114],"domain-specific,":[115],"deep":[117],"models":[119],"with":[120],"small":[121],"datasets.":[122]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2025-10-10T00:00:00"}