{"id":"https://openalex.org/W4412747880","doi":"https://doi.org/10.1109/tmm.2025.3590924","title":"FoodLMM: A Versatile Food Assistant Using Large Multi-Modal Model","display_name":"FoodLMM: A Versatile Food Assistant Using Large Multi-Modal Model","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412747880","doi":"https://doi.org/10.1109/tmm.2025.3590924"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2025.3590924","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3590924","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-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/A5037464978","display_name":"Yuehao Yin","orcid":"https://orcid.org/0000-0002-2194-5594"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuehao Yin","raw_affiliation_strings":["School of Computer Science and Technology, Fudan University, Shanghai, China","Visual Laboratory of Fudan University, Shanghai Collaborative Innovation Center of Intelligent Visual Computing, School of Computer Science and Technology, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-2194-5594","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Visual Laboratory of Fudan University, Shanghai Collaborative Innovation Center of Intelligent Visual Computing, School of Computer Science and Technology, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043089518","display_name":"Huiyan Qi","orcid":"https://orcid.org/0009-0002-7591-6016"},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Huiyan Qi","raw_affiliation_strings":["School of Computing and Information Systems, Singapore Management University, Singapore"],"raw_orcid":"https://orcid.org/0009-0002-7591-6016","affiliations":[{"raw_affiliation_string":"School of Computing and Information Systems, Singapore Management University, Singapore","institution_ids":["https://openalex.org/I79891267"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Bin Zhu","orcid":"https://orcid.org/0000-0002-9213-2611"},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Bin Zhu","raw_affiliation_strings":["School of Computing and Information Systems, Singapore Management University, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-9213-2611","affiliations":[{"raw_affiliation_string":"School of Computing and Information Systems, Singapore Management University, Singapore","institution_ids":["https://openalex.org/I79891267"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100373492","display_name":"Jingjing Chen","orcid":"https://orcid.org/0000-0003-3148-264X"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingjing Chen","raw_affiliation_strings":["School of Computer Science and Technology, Fudan University, Shanghai, China","Visual Laboratory of Fudan University, Shanghai Collaborative Innovation Center of Intelligent Visual Computing, School of Computer Science and Technology, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-3148-264X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Visual Laboratory of Fudan University, Shanghai Collaborative Innovation Center of Intelligent Visual Computing, School of Computer Science and Technology, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047962986","display_name":"Yu\u2013Gang Jiang","orcid":"https://orcid.org/0000-0002-1907-8567"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu-Gang Jiang","raw_affiliation_strings":["School of Computer Science and Technology, Fudan University, Shanghai, China","Visual Laboratory of Fudan University, Shanghai Collaborative Innovation Center of Intelligent Visual Computing, School of Computer Science and Technology, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-1907-8567","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Visual Laboratory of Fudan University, Shanghai Collaborative Innovation Center of Intelligent Visual Computing, School of Computer Science and Technology, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010722442","display_name":"Chong\u2010Wah Ngo","orcid":"https://orcid.org/0000-0003-4182-8261"},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chong-Wah Ngo","raw_affiliation_strings":["School of Computing and Information Systems, Singapore Management University, Singapore"],"raw_orcid":"https://orcid.org/0000-0003-4182-8261","affiliations":[{"raw_affiliation_string":"School of Computing and Information Systems, Singapore Management University, Singapore","institution_ids":["https://openalex.org/I79891267"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":11.152,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.98883002,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"27","issue":null,"first_page":"6949","last_page":"6961"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12486","display_name":"Food Supply Chain Traceability","score":0.8930000066757202,"subfield":{"id":"https://openalex.org/subfields/1106","display_name":"Food Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T12486","display_name":"Food Supply Chain Traceability","score":0.8930000066757202,"subfield":{"id":"https://openalex.org/subfields/1106","display_name":"Food Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8402740955352783},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6029489040374756},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34661734104156494}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8402740955352783},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6029489040374756},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34661734104156494},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2025.3590924","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3590924","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7599999904632568,"display_name":"Zero hunger","id":"https://metadata.un.org/sdg/2"}],"awards":[{"id":"https://openalex.org/G3970387658","display_name":"\u77e5\u8bc6\u9a71\u52a8\u7684\u5c0f\u6837\u672c\u89c6\u89c9\u8bc6\u522b\u7814\u7a76","funder_award_id":"62072116","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W12634471","https://openalex.org/W1030521295","https://openalex.org/W1975715116","https://openalex.org/W2021543368","https://openalex.org/W2058837810","https://openalex.org/W2071487122","https://openalex.org/W2179355739","https://openalex.org/W2302548814","https://openalex.org/W2374399370","https://openalex.org/W2414162830","https://openalex.org/W2526198870","https://openalex.org/W2583892095","https://openalex.org/W2594259972","https://openalex.org/W2643943583","https://openalex.org/W2728515412","https://openalex.org/W2737041163","https://openalex.org/W2765707332","https://openalex.org/W2798556392","https://openalex.org/W2803503299","https://openalex.org/W2876852810","https://openalex.org/W2897152025","https://openalex.org/W2948037078","https://openalex.org/W2950839819","https://openalex.org/W2954801189","https://openalex.org/W2962914239","https://openalex.org/W2965024236","https://openalex.org/W2980441700","https://openalex.org/W2995924296","https://openalex.org/W2997987465","https://openalex.org/W3009098945","https://openalex.org/W3015304982","https://openalex.org/W3082811686","https://openalex.org/W3092803786","https://openalex.org/W3106698386","https://openalex.org/W3108413361","https://openalex.org/W3115266926","https://openalex.org/W3120867192","https://openalex.org/W3130296038","https://openalex.org/W3164325351","https://openalex.org/W3170706004","https://openalex.org/W3201770677","https://openalex.org/W3204119129","https://openalex.org/W3207251446","https://openalex.org/W3208444943","https://openalex.org/W3216551675","https://openalex.org/W4200631575","https://openalex.org/W4226210750","https://openalex.org/W4283390451","https://openalex.org/W4285295719","https://openalex.org/W4293198979","https://openalex.org/W4312595704","https://openalex.org/W4316661142","https://openalex.org/W4319996536","https://openalex.org/W4367595583","https://openalex.org/W4379805693","https://openalex.org/W4381930847","https://openalex.org/W4386076522","https://openalex.org/W4387188528","https://openalex.org/W4387197118","https://openalex.org/W4388283708","https://openalex.org/W4390873528","https://openalex.org/W4390874575","https://openalex.org/W4392251617","https://openalex.org/W4394596514","https://openalex.org/W4402754134","https://openalex.org/W4403841656"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Large":[0],"Multi-modal":[1],"Models":[2],"(LMMs)":[3],"have":[4],"made":[5],"impressive":[6],"progress":[7],"in":[8,18,57,144],"many":[9],"vision-language":[10],"tasks.":[11],"Nevertheless,":[12],"the":[13,76,94,108,112,128,145],"performance":[14],"of":[15,69],"general":[16],"LMMs":[17,36],"specific":[19],"domains":[20],"is":[21],"still":[22],"far":[23],"from":[24],"satisfactory.":[25],"This":[26],"paper":[27],"proposes":[28],"FoodLMM,":[29],"a":[30,67,89,117,122],"versatile":[31],"food":[32,41,49,80,101,146,156],"assistant":[33],"based":[34,140],"on":[35,141],"with":[37,59],"various":[38],"capabilities,":[39],"including":[40],"recognition,":[42,44],"ingredient":[43],"recipe":[45],"generation,":[46],"nutrition":[47],"estimation,":[48],"segmentation,":[50],"and":[51,73,83,121,136,161],"multi-round":[52,118],"conversation.":[53],"To":[54],"facilitate":[55],"FoodLMM":[56,150],"dealing":[58],"tasks":[60],"beyond":[61],"pure":[62],"text":[63],"output,":[64],"we":[65,97,115],"introduce":[66],"series":[68],"novel":[70],"task-specific":[71],"tokens":[72],"heads,":[74],"enabling":[75,130],"model":[77],"to":[78,126,132],"predict":[79],"nutritional":[81],"values":[82],"multiple":[84,99],"segmentation":[85,124,138],"masks.":[86],"We":[87],"adopt":[88],"two-stage":[90],"training":[91],"strategy.":[92],"In":[93,111],"first":[95],"stage,":[96,114],"utilize":[98],"public":[100],"benchmarks":[102],"for":[103],"multi-task":[104],"learning":[105],"by":[106],"leveraging":[107],"instruct-following":[109],"paradigm.":[110],"second":[113],"construct":[116],"conversation":[119],"dataset":[120,125],"reasoning":[123,143],"fine-tune":[127],"model,":[129],"it":[131],"conduct":[133],"professional":[134],"dialogues":[135],"generate":[137],"masks":[139],"complex":[142],"domain.":[147],"Our":[148,158],"fine-tuned":[149],"achieves":[151],"state-of-the-art":[152],"results":[153],"across":[154],"several":[155],"benchmarks.":[157],"code,":[159],"models,":[160],"datasets":[162],"are":[163],"available":[164],"at":[165],"<uri":[166],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[167],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/YuehaoYin/FoodLMM</uri>.":[168]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":9}],"updated_date":"2026-07-17T09:13:05.818461","created_date":"2025-10-10T00:00:00"}