{"id":"https://openalex.org/W4404740677","doi":"https://doi.org/10.1109/rtsi61910.2024.10761839","title":"Exploring Fine-Grained Retail Product Discrimination with Zero-Shot Object Classification Using Vision-Language Models","display_name":"Exploring Fine-Grained Retail Product Discrimination with Zero-Shot Object Classification Using Vision-Language Models","publication_year":2024,"publication_date":"2024-09-18","ids":{"openalex":"https://openalex.org/W4404740677","doi":"https://doi.org/10.1109/rtsi61910.2024.10761839"},"language":"en","primary_location":{"id":"doi:10.1109/rtsi61910.2024.10761839","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/rtsi61910.2024.10761839","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 8th Forum on Research and Technologies for Society and Industry Innovation (RTSI)","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/A5028621401","display_name":"An\u0131l Osman Tur","orcid":null},"institutions":[{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Anil Osman Tur","raw_affiliation_strings":["University of Trento,DISI,Trento,Italy"],"affiliations":[{"raw_affiliation_string":"University of Trento,DISI,Trento,Italy","institution_ids":["https://openalex.org/I193223587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101749512","display_name":"Alessandro Conti","orcid":"https://orcid.org/0000-0002-3044-1320"},"institutions":[{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alessandro Conti","raw_affiliation_strings":["University of Trento,DISI,Trento,Italy"],"affiliations":[{"raw_affiliation_string":"University of Trento,DISI,Trento,Italy","institution_ids":["https://openalex.org/I193223587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057859690","display_name":"Cigdem Beyan","orcid":"https://orcid.org/0000-0002-9583-0087"},"institutions":[{"id":"https://openalex.org/I119439378","display_name":"University of Verona","ror":"https://ror.org/039bp8j42","country_code":"IT","type":"education","lineage":["https://openalex.org/I119439378"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Cigdem Beyan","raw_affiliation_strings":["University of Verona,Dep. of Computer Science,Verona,Italy"],"affiliations":[{"raw_affiliation_string":"University of Verona,Dep. of Computer Science,Verona,Italy","institution_ids":["https://openalex.org/I119439378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064432821","display_name":"Davide Boscaini","orcid":"https://orcid.org/0000-0003-4887-2038"},"institutions":[{"id":"https://openalex.org/I2277624104","display_name":"Fondazione Bruno Kessler","ror":"https://ror.org/01j33xk10","country_code":"IT","type":"facility","lineage":["https://openalex.org/I2277624104"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Davide Boscaini","raw_affiliation_strings":["Technologies of Vision, Fondazione Bruno Kessler,Trento,Italy"],"affiliations":[{"raw_affiliation_string":"Technologies of Vision, Fondazione Bruno Kessler,Trento,Italy","institution_ids":["https://openalex.org/I2277624104"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057136388","display_name":"Roberto Larcher","orcid":"https://orcid.org/0000-0002-4784-8389"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Roberto Larcher","raw_affiliation_strings":["Spindox Labs, Spindox SpA,Trento,Italy"],"affiliations":[{"raw_affiliation_string":"Spindox Labs, Spindox SpA,Trento,Italy","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049085989","display_name":"Stefano Messelodi","orcid":"https://orcid.org/0000-0002-4673-9607"},"institutions":[{"id":"https://openalex.org/I2277624104","display_name":"Fondazione Bruno Kessler","ror":"https://ror.org/01j33xk10","country_code":"IT","type":"facility","lineage":["https://openalex.org/I2277624104"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Stefano Messelodi","raw_affiliation_strings":["Technologies of Vision, Fondazione Bruno Kessler,Trento,Italy"],"affiliations":[{"raw_affiliation_string":"Technologies of Vision, Fondazione Bruno Kessler,Trento,Italy","institution_ids":["https://openalex.org/I2277624104"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067244774","display_name":"Fabio Poiesi","orcid":"https://orcid.org/0000-0002-9769-1279"},"institutions":[{"id":"https://openalex.org/I2277624104","display_name":"Fondazione Bruno Kessler","ror":"https://ror.org/01j33xk10","country_code":"IT","type":"facility","lineage":["https://openalex.org/I2277624104"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Fabio Poiesi","raw_affiliation_strings":["Technologies of Vision, Fondazione Bruno Kessler,Trento,Italy"],"affiliations":[{"raw_affiliation_string":"Technologies of Vision, Fondazione Bruno Kessler,Trento,Italy","institution_ids":["https://openalex.org/I2277624104"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065059558","display_name":"Elisa Ricci","orcid":"https://orcid.org/0000-0002-0228-1147"},"institutions":[{"id":"https://openalex.org/I2277624104","display_name":"Fondazione Bruno Kessler","ror":"https://ror.org/01j33xk10","country_code":"IT","type":"facility","lineage":["https://openalex.org/I2277624104"]},{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Elisa Ricci","raw_affiliation_strings":["University of Trento, Fondazione Bruno Kessler,Trento,Italy"],"affiliations":[{"raw_affiliation_string":"University of Trento, Fondazione Bruno Kessler,Trento,Italy","institution_ids":["https://openalex.org/I2277624104","https://openalex.org/I193223587"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5028621401"],"corresponding_institution_ids":["https://openalex.org/I193223587"],"apc_list":null,"apc_paid":null,"fwci":0.3637,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.69145147,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"97","last_page":"102"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.6883999705314636,"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"}},"topics":[{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.6883999705314636,"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"}},{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.6061999797821045,"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/zero","display_name":"Zero (linguistics)","score":0.6395834684371948},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6118943691253662},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.5900988578796387},{"id":"https://openalex.org/keywords/product","display_name":"Product (mathematics)","score":0.5704736709594727},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.566291868686676},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49249133467674255},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4357845187187195},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16798606514930725},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12645503878593445},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.07727378606796265}],"concepts":[{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6395834684371948},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6118943691253662},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5900988578796387},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.5704736709594727},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.566291868686676},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49249133467674255},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4357845187187195},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16798606514930725},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12645503878593445},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.07727378606796265},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/rtsi61910.2024.10761839","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/rtsi61910.2024.10761839","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 8th Forum on Research and Technologies for Society and Industry Innovation (RTSI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.6399999856948853}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1536680647","https://openalex.org/W1861492603","https://openalex.org/W1989746184","https://openalex.org/W2136137122","https://openalex.org/W2193145675","https://openalex.org/W2910638850","https://openalex.org/W2963037989","https://openalex.org/W2984882023","https://openalex.org/W3105335547","https://openalex.org/W3134095442","https://openalex.org/W3198377975","https://openalex.org/W4226058394","https://openalex.org/W4312458986","https://openalex.org/W4312563428","https://openalex.org/W4312910992","https://openalex.org/W4312960937","https://openalex.org/W4313039942","https://openalex.org/W4321192191","https://openalex.org/W4321789735","https://openalex.org/W4361861844","https://openalex.org/W4386076063","https://openalex.org/W4386076609","https://openalex.org/W6629510986","https://openalex.org/W6748816842","https://openalex.org/W6780006332","https://openalex.org/W6791353385","https://openalex.org/W6794559225","https://openalex.org/W6798805250","https://openalex.org/W6800139874","https://openalex.org/W6802517928","https://openalex.org/W6804095316","https://openalex.org/W6811013733","https://openalex.org/W6811340617","https://openalex.org/W6846007759","https://openalex.org/W6849177959","https://openalex.org/W6851800889","https://openalex.org/W6857394294","https://openalex.org/W6859186507"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W4298312966","https://openalex.org/W2325697621"],"abstract_inverted_index":{"In":[0,47],"smart":[1,202],"retail":[2,84,186,203],"applications,":[3,204],"the":[4,26,30,58,70,89,100,116,209,215,222,227],"large":[5],"number":[6],"of":[7,83,94,231],"products":[8],"and":[9,78,133,212,229],"their":[10],"frequent":[11],"turnover":[12],"necessitate":[13],"reliable":[14],"zero-shot":[15,20,90,198],"object":[16,91,199],"classification":[17,77,92,113,141,200],"methods.":[18],"The":[19,233],"assumption":[21],"is":[22,37,235],"essential":[23],"to":[24,139,214],"avoid":[25],"need":[27,117,184],"for":[28,118,157,201,224],"retraining":[29],"classifier":[31],"every":[32],"time":[33],"a":[34,80,124,164,182],"new":[35],"product":[36,44,64,76,159,189],"introduced":[38],"into":[39,197],"stock":[40],"or":[41],"an":[42],"existing":[43,67],"undergoes":[45],"rebranding.":[46],"this":[48],"paper,":[49],"we":[50,56,87,122,162,205],"make":[51],"three":[52],"key":[53],"contributions.":[54],"Firstly,":[55],"introduce":[57,163],"MIMEX":[59,72,102,210],"dataset,":[60],"comprising":[61],"28":[62],"distinct":[63],"categories.":[65],"Unlike":[66],"datasets":[68],"in":[69,175,185],"literature,":[71],"focuses":[73],"on":[74,99,226],"fine-grained":[75,112,158],"includes":[79],"diverse":[81],"range":[82],"products.":[85],"Secondly,":[86],"benchmark":[88,213],"performance":[93],"state-of-the-art":[95],"vision-language":[96],"models":[97,109],"(VLMs)":[98],"proposed":[101],"dataset.":[103],"Our":[104],"experiments":[105],"reveal":[106],"that":[107,128,168],"these":[108,145],"achieve":[110],"unsatisfactory":[111],"performance,":[114],"highlighting":[115],"specialized":[119],"approaches.":[120],"Lastly,":[121],"propose":[123],"novel":[125],"ensemble":[126,148],"approach":[127,149],"integrates":[129],"embeddings":[130],"from":[131],"CLIP":[132],"DINOv2":[134],"with":[135,172,177],"dimensionality":[136],"reduction":[137],"techniques":[138],"enhance":[140],"performance.":[142],"By":[143],"combining":[144],"components,":[146],"our":[147],"outperforms":[150],"VLMs,":[151],"effectively":[152],"capturing":[153],"visual":[154,170],"cues":[155],"crucial":[156],"discrimination.":[160],"Additionally,":[161],"class":[165],"adaptation":[166],"method":[167],"utilizes":[169],"prototyping":[171],"limited":[173],"samples":[174],"scenarios":[176],"scarce":[178],"labeled":[179],"data,":[180],"addressing":[181],"critical":[183],"environments":[187],"where":[188],"variety":[190],"frequently":[191],"changes.":[192],"To":[193],"encourage":[194],"further":[195],"research":[196,216],"will":[206],"release":[207],"both":[208],"dataset":[211],"community.":[217],"Interested":[218],"researchers":[219],"can":[220],"contact":[221],"authors":[223],"details":[225],"terms":[228],"conditions":[230],"use.":[232],"code":[234],"available:":[236],"https://github.com/AnilOsmanTur/Zero-shot-Retail-Product-Classification.":[237]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}