{"id":"https://openalex.org/W4387968120","doi":"https://doi.org/10.1145/3581783.3611994","title":"Food-500 Cap: A Fine-Grained Food Caption Benchmark for Evaluating Vision-Language Models","display_name":"Food-500 Cap: A Fine-Grained Food Caption Benchmark for Evaluating Vision-Language Models","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387968120","doi":"https://doi.org/10.1145/3581783.3611994"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3611994","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611994","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101942699","display_name":"Zheng Ma","orcid":"https://orcid.org/0009-0006-1101-3263"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Ma","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0006-1101-3263","affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041468227","display_name":"Mianzhi Pan","orcid":"https://orcid.org/0009-0008-5971-5285"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mianzhi Pan","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0008-5971-5285","affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041981673","display_name":"Wenhan Wu","orcid":"https://orcid.org/0009-0003-9448-3479"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenhan Wu","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0003-9448-3479","affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001863177","display_name":"Kanzhi Cheng","orcid":"https://orcid.org/0009-0004-4532-1446"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kanzhi Cheng","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0004-4532-1446","affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046733861","display_name":"Jianbing Zhang","orcid":"https://orcid.org/0009-0005-8193-8344"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianbing Zhang","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0005-8193-8344","affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102865824","display_name":"Shujian Huang","orcid":"https://orcid.org/0000-0003-4869-0832"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shujian Huang","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-4869-0832","affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103039793","display_name":"Jiajun Chen","orcid":"https://orcid.org/0000-0002-9859-6898"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiajun Chen","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-9859-6898","affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5674","last_page":"5685"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9926000237464905,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9362000226974487,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/interpretability","display_name":"Interpretability","score":0.8637202978134155},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7828692197799683},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6333267688751221},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5083803534507751},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.508372962474823},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5025146007537842},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4251742362976074},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3783944845199585},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.08766385912895203}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.8637202978134155},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7828692197799683},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6333267688751221},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5083803534507751},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.508372962474823},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5025146007537842},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4251742362976074},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3783944845199585},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.08766385912895203},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3611994","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611994","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5400000214576721,"id":"https://metadata.un.org/sdg/2","display_name":"Zero hunger"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W12634471","https://openalex.org/W398859631","https://openalex.org/W1030521295","https://openalex.org/W1861492603","https://openalex.org/W1956340063","https://openalex.org/W2031489346","https://openalex.org/W2108598243","https://openalex.org/W2183341477","https://openalex.org/W2185175083","https://openalex.org/W2277195237","https://openalex.org/W2296448531","https://openalex.org/W2526198870","https://openalex.org/W2560674852","https://openalex.org/W2747329762","https://openalex.org/W2761189739","https://openalex.org/W2960416371","https://openalex.org/W2962735233","https://openalex.org/W2970231061","https://openalex.org/W2972610293","https://openalex.org/W2982450728","https://openalex.org/W3093234244","https://openalex.org/W3098267758","https://openalex.org/W3138516171","https://openalex.org/W3153469116","https://openalex.org/W3177487519","https://openalex.org/W3198377975","https://openalex.org/W3207251446","https://openalex.org/W4206070857","https://openalex.org/W4281485151","https://openalex.org/W4281633937","https://openalex.org/W4282028325","https://openalex.org/W4283821388","https://openalex.org/W4287854770","https://openalex.org/W4295884246","https://openalex.org/W4306705634","https://openalex.org/W4311730907","https://openalex.org/W4312090938","https://openalex.org/W4312261477","https://openalex.org/W4312877428","https://openalex.org/W4312910992","https://openalex.org/W4312933868","https://openalex.org/W4320458302","https://openalex.org/W4385572747"],"related_works":["https://openalex.org/W2905433371","https://openalex.org/W4390569940","https://openalex.org/W2888392564","https://openalex.org/W4361193272","https://openalex.org/W4310278675","https://openalex.org/W4388422664","https://openalex.org/W2806259446","https://openalex.org/W2963326959","https://openalex.org/W4312407344","https://openalex.org/W2894289927"],"abstract_inverted_index":{"Vision-language":[0],"models":[1],"(VLMs)":[2],"have":[3,38],"shown":[4],"impressive":[5],"performance":[6,17,176,200],"in":[7,88,107,170,180,193,201,211],"substantial":[8],"downstream":[9,19],"multi-modal":[10],"tasks.":[11],"However,":[12],"only":[13],"comparing":[14],"the":[15,23,84,102,111,148,175,194,202,237,256],"fine-tuned":[16],"on":[18,166,184],"tasks":[20],"leads":[21],"to":[22,31,51,74,172,214,232,235,249,255,267],"poor":[24],"interpretability":[25],"of":[26,64,86,104,144,178,258],"VLMs,":[27],"which":[28,125],"is":[29,135],"adverse":[30],"their":[32,199],"future":[33],"improvement.":[34],"Several":[35],"prior":[36],"works":[37],"identified":[39],"this":[40,97,115,269],"issue":[41],"and":[42,80,151,227,263],"used":[43],"various":[44],"probing":[45,225],"methods":[46,226],"under":[47],"a":[48,108,119,138,156],"zero-shot":[49],"setting":[50],"detect":[52],"VLMs'":[53,212],"limitations,":[54],"but":[55],"they":[56],"all":[57],"examine":[58],"VLMs":[59,70,87,106,191,230],"using":[60],"general":[61,203],"datasets":[62,187],"instead":[63],"specialized":[65],"ones.":[66],"In":[67,96],"practical":[68],"applications,":[69],"are":[71],"usually":[72],"applied":[73],"specific":[75,89,109],"scenarios,":[76],"such":[77,146],"as":[78,147],"e-commerce":[79],"news":[81],"fields,":[82],"so":[83],"generalization":[85],"domains":[90],"should":[91],"be":[92],"given":[93],"more":[94],"attention.":[95],"paper,":[98],"we":[99,117],"comprehensively":[100],"investigate":[101],"capabilities":[103],"popular":[105,190],"field,":[110],"food":[112,120,128,163,195,216,259],"domain.":[113,204],"To":[114],"end,":[116],"build":[118],"caption":[121],"dataset,":[122],"Food-500":[123],"Cap,":[124],"contains":[126],"24,700":[127],"images":[129],"with":[130,198],"494":[131],"categories.":[132],"Each":[133],"image":[134],"accompanied":[136],"by":[137],"detailed":[139],"caption,":[140],"including":[141],"fine-grained":[142],"attributes":[143],"food,":[145],"ingredient,":[149],"shape,":[150],"color.":[152],"We":[153,222,240],"also":[154],"provide":[155],"culinary":[157,261],"culture":[158],"taxonomy":[159],"that":[160,189,242],"classifies":[161],"each":[162],"category":[164],"based":[165],"its":[167],"geographic":[168,220],"origin":[169],"order":[171],"better":[173],"analyze":[174],"differences":[177],"VLM":[179],"different":[181,219,233],"regions.":[182,221],"Experiments":[183],"our":[185,206,243],"proposed":[186],"demonstrate":[188],"underperform":[192],"domain":[196,257],"compared":[197],"Furthermore,":[205],"research":[207],"reveals":[208],"severe":[209],"bias":[210],"ability":[213],"handle":[215],"items":[217],"from":[218],"adopt":[223],"diverse":[224],"evaluate":[228],"nine":[229],"belonging":[231],"architectures":[234],"verify":[236],"aforementioned":[238],"observations.":[239],"hope":[241],"study":[244],"will":[245],"bring":[246],"researchers'":[247],"attention":[248],"VLM's":[250],"limitations":[251],"when":[252],"applying":[253],"them":[254],"or":[260],"cultures,":[262],"spur":[264],"further":[265],"investigations":[266],"address":[268],"issue.":[270]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}