{"id":"https://openalex.org/W7224936832","doi":"https://doi.org/10.48550/arxiv.2610.37867","title":"What Constitutes Food Similarity? Visual Representations and Retrieval in Indian Cuisine","display_name":"What Constitutes Food Similarity? Visual Representations and Retrieval in Indian Cuisine","publication_year":2026,"publication_date":"2026-10-27","ids":{"openalex":"https://openalex.org/W7224936832","doi":"https://doi.org/10.48550/arxiv.2610.37867"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.37867","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.37867","pdf_url":"https://arxiv.org/pdf/2610.37867","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.37867","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109791574","display_name":"Saransh Kumar Gupta","orcid":"https://orcid.org/0009-0000-5887-2301","observed_orcids":["https://orcid.org/0009-0000-5887-2301"]},"institutions":[{"id":"https://openalex.org/I347237974","display_name":"Ashoka University","ror":"https://ror.org/02j1xr113","country_code":"IN","type":"education","lineage":["https://openalex.org/I347237974"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Gupta, Saransh Kumar","raw_affiliation_strings":["Ashoka University , India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ashoka University , India","institution_ids":["https://openalex.org/I347237974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160208314","display_name":"Akshadha Sharma","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I347237974","display_name":"Ashoka University","ror":"https://ror.org/02j1xr113","country_code":"IN","type":"education","lineage":["https://openalex.org/I347237974"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sharma, Akshadha","raw_affiliation_strings":["Ashoka University , India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ashoka University , India","institution_ids":["https://openalex.org/I347237974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102724695","display_name":"Lipika Dey","orcid":"https://orcid.org/0000-0003-3831-5545","observed_orcids":["https://orcid.org/0000-0003-3831-5545"]},"institutions":[{"id":"https://openalex.org/I347237974","display_name":"Ashoka University","ror":"https://ror.org/02j1xr113","country_code":"IN","type":"education","lineage":["https://openalex.org/I347237974"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Dey, Lipika","raw_affiliation_strings":["Ashoka University , India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ashoka University , India","institution_ids":["https://openalex.org/I347237974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148881244","display_name":"Partha Pratim Das","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I347237974","display_name":"Ashoka University","ror":"https://ror.org/02j1xr113","country_code":"IN","type":"education","lineage":["https://openalex.org/I347237974"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Das, Partha Pratim","raw_affiliation_strings":["Ashoka University , India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ashoka University , India","institution_ids":["https://openalex.org/I347237974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5148901337","display_name":"Ramesh Jain","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jain, Ramesh","raw_affiliation_strings":["Institute for Future Health , UC Irvine , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Future Health , UC Irvine , USA","institution_ids":["https://openalex.org/I204250578"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.3840000033378601,"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":0.3840000033378601,"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":0.22110000252723694,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.17249999940395355,"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/indian-cuisine","display_name":"Indian cuisine","score":0.8199999928474426},{"id":"https://openalex.org/keywords/image-text-alignment","display_name":"image-text alignment","score":0.328000009059906},{"id":"https://openalex.org/keywords/food-recommendation","display_name":"food recommendation","score":0.35899999737739563}],"concepts":[{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.7123000025749207},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.49939998984336853},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.475600004196167},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.4683000147342682},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.4636000096797943},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.4593999981880188},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4253999888896942},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.4133000075817108},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.37720000743865967},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.36820000410079956},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.3488999903202057},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3330000042915344},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.32679998874664307},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3264999985694885},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3084000051021576},{"id":"https://openalex.org/C2987718291","wikidata":"https://www.wikidata.org/wiki/Q2095","display_name":"Food products","level":2,"score":0.30709999799728394},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.29089999198913574},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.287200003862381},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.2732999920845032},{"id":"https://openalex.org/C2777798969","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Assemblage (archaeology)","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.25690001249313354},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25040000677108765}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.37867","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.37867","pdf_url":"https://arxiv.org/pdf/2610.37867","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.37867","doi":"https://doi.org/10.48550/arxiv.2610.37867","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.37867","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.37867","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.37867","pdf_url":"https://arxiv.org/pdf/2610.37867","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/2","score":0.40450000762939453,"display_name":"Zero hunger"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7224936832.pdf","grobid_xml":"https://content.openalex.org/works/W7224936832.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W2613010453","https://openalex.org/W2897709118","https://openalex.org/W2957307908","https://openalex.org/W3094502228","https://openalex.org/W4366208220","https://openalex.org/W4366341473","https://openalex.org/W4414756198","https://openalex.org/W6910554155","https://openalex.org/W7171985912"],"related_works":["https://openalex.org/W4385198354","https://openalex.org/W2727229559","https://openalex.org/W4415708808","https://openalex.org/W2552501394","https://openalex.org/W3164325351","https://openalex.org/W7106334373","https://openalex.org/W2562417371","https://openalex.org/W7167284326","https://openalex.org/W3035032757","https://openalex.org/W3034303366"],"abstract_inverted_index":{"Food":[0],"similarity":[1,26,123,129,178],"underlies":[2],"retrieval,":[3],"recommendation,":[4],"substitution,":[5],"and":[6,46,86,95,103,111,126,183],"other":[7],"food":[8,12,25,177,194,206],"computing":[9],"tasks,":[10],"yet":[11],"representations":[13,32,90,118],"are":[14],"typically":[15],"evaluated":[16],"by":[17],"identity":[18],"preservation.":[19],"We":[20,114],"ask":[21],"what":[22,38],"happens":[23],"to":[24,119,203],"beyond":[27],"identity:":[28],"how":[29,47],"different":[30,67],"visual":[31,89,122,152],"organize":[33],"foods":[34,64,71],"into":[35,209],"relational":[36,175],"neighborhoods,":[37,105],"culinary":[39,68,74],"relationships":[40],"these":[41,49,197],"neighborhoods":[42,135],"reveal":[43],"or":[44],"obscure,":[45],"consistently":[48],"structures":[50,198],"emerge":[51],"across":[52,124,138,142],"representations.":[53],"Indian":[54],"cuisine":[55],"provides":[56],"a":[57,73,189,201,210],"challenging":[58],"setting":[59],"in":[60,79],"which":[61],"visually":[62],"similar":[63],"may":[65],"have":[66],"identities,":[69],"while":[70],"within":[72],"family":[75],"can":[76],"vary":[77,136],"substantially":[78,137],"appearance.":[80],"Using":[81],"an":[82],"expanded":[83],"Khana":[84],"dataset":[85],"seven":[87],"pretrained":[88],"spanning":[91],"convolutional,":[92],"transformer-based,":[93],"self-supervised,":[94],"image-text":[96],"aligned":[97],"models,":[98],"we":[99],"evaluate":[100],"image-to-image":[101],"retrieval":[102],"image-to-dish":[104],"examining":[106],"culinary-family":[107,143],"structure,":[108],"contrast":[109],"cases,":[110],"cross-representation":[112],"agreement.":[113],"also":[115],"aggregate":[116],"image":[117],"compare":[120],"dish-level":[121],"models":[125],"against":[127],"recipe-derived":[128,164],"for":[130],"the":[131,146,193],"same":[132],"dishes.":[133],"Image-level":[134],"representations,":[139],"including":[140],"similarities":[141],"boundaries.":[144],"At":[145],"dish":[147],"level,":[148],"aggregation":[149],"reveals":[150],"common":[151],"structure":[153,159],"despite":[154],"local":[155],"variation,":[156],"but":[157],"this":[158],"corresponds":[160],"less":[161],"strongly":[162],"with":[163],"similarity.":[165,214],"These":[166],"findings":[167],"show":[168],"that":[169],"recognition":[170],"performance":[171],"alone":[172],"cannot":[173],"characterize":[174],"structure:":[176],"depends":[179],"on":[180],"representation,":[181],"modality,":[182],"abstraction":[184],"level":[185],"rather":[186],"than":[187],"being":[188],"fixed":[190],"property":[191],"of":[192,213],"collection.":[195],"Understanding":[196],"is":[199],"therefore":[200],"prerequisite":[202],"combining":[204],"multiple":[205],"information":[207],"modalities":[208],"coherent":[211],"notion":[212]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-31T00:00:00"}