{"id":"https://openalex.org/W4399432865","doi":"https://doi.org/10.1007/s00138-024-01549-9","title":"Multimodal fine-grained grocery product recognition using image and OCR text","display_name":"Multimodal fine-grained grocery product recognition using image and OCR text","publication_year":2024,"publication_date":"2024-06-07","ids":{"openalex":"https://openalex.org/W4399432865","doi":"https://doi.org/10.1007/s00138-024-01549-9"},"language":"en","primary_location":{"id":"doi:10.1007/s00138-024-01549-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00138-024-01549-9","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00138-024-01549-9.pdf","source":{"id":"https://openalex.org/S27728525","display_name":"Machine Vision and Applications","issn_l":"0932-8092","issn":["0932-8092","1432-1769"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Vision and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s00138-024-01549-9.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002154629","display_name":"Tobias Pettersson","orcid":"https://orcid.org/0000-0001-8880-7965"},"institutions":[{"id":"https://openalex.org/I205158640","display_name":"University of Sk\u00f6vde","ror":"https://ror.org/051mrsz47","country_code":"SE","type":"education","lineage":["https://openalex.org/I205158640"]},{"id":"https://openalex.org/I94616838","display_name":"J\u00f6nk\u00f6ping University","ror":"https://ror.org/03t54am93","country_code":"SE","type":"education","lineage":["https://openalex.org/I94616838"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Tobias Pettersson","raw_affiliation_strings":["ITAB Shop Products AB, University of Sk\u00f6vde, J\u00f6nk\u00f6ping University, J\u00f6nk\u00f6ping, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ITAB Shop Products AB, University of Sk\u00f6vde, J\u00f6nk\u00f6ping University, J\u00f6nk\u00f6ping, Sweden","institution_ids":["https://openalex.org/I94616838","https://openalex.org/I205158640"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041841729","display_name":"Maria Riveiro","orcid":"https://orcid.org/0000-0003-2900-9335"},"institutions":[{"id":"https://openalex.org/I94616838","display_name":"J\u00f6nk\u00f6ping University","ror":"https://ror.org/03t54am93","country_code":"SE","type":"education","lineage":["https://openalex.org/I94616838"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Maria Riveiro","raw_affiliation_strings":["Department of Computer Science and Informatics, J\u00f6nk\u00f6ping University, J\u00f6nk\u00f6ping, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Informatics, J\u00f6nk\u00f6ping University, J\u00f6nk\u00f6ping, Sweden","institution_ids":["https://openalex.org/I94616838"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073489496","display_name":"Tuve L\u00f6fstr\u00f6m","orcid":"https://orcid.org/0000-0003-0274-9026"},"institutions":[{"id":"https://openalex.org/I94616838","display_name":"J\u00f6nk\u00f6ping University","ror":"https://ror.org/03t54am93","country_code":"SE","type":"education","lineage":["https://openalex.org/I94616838"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Tuwe L\u00f6fstr\u00f6m","raw_affiliation_strings":["Department of Computing, J\u00f6nk\u00f6ping University, J\u00f6nk\u00f6ping, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing, J\u00f6nk\u00f6ping University, J\u00f6nk\u00f6ping, Sweden","institution_ids":["https://openalex.org/I94616838"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5002154629"],"corresponding_institution_ids":["https://openalex.org/I205158640","https://openalex.org/I94616838"],"apc_list":{"value":2490,"currency":"EUR","value_usd":3090},"apc_paid":{"value":2490,"currency":"EUR","value_usd":3090},"fwci":2.6476,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.90731451,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"35","issue":"4","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12707","display_name":"Vehicle License Plate Recognition","score":0.989799976348877,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12707","display_name":"Vehicle License Plate Recognition","score":0.989799976348877,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"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":0.9894000291824341,"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":0.9886000156402588,"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/computer-science","display_name":"Computer science","score":0.5569096207618713},{"id":"https://openalex.org/keywords/product","display_name":"Product (mathematics)","score":0.5227368474006653},{"id":"https://openalex.org/keywords/grocery-store","display_name":"Grocery store","score":0.46793195605278015},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.45501959323883057},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43046367168426514},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3659853935241699},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.34237420558929443},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.25546789169311523},{"id":"https://openalex.org/keywords/advertising","display_name":"Advertising","score":0.24294909834861755},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12116312980651855}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5569096207618713},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.5227368474006653},{"id":"https://openalex.org/C2992627081","wikidata":"https://www.wikidata.org/wiki/Q1295201","display_name":"Grocery store","level":2,"score":0.46793195605278015},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.45501959323883057},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43046367168426514},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3659853935241699},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34237420558929443},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.25546789169311523},{"id":"https://openalex.org/C112698675","wikidata":"https://www.wikidata.org/wiki/Q37038","display_name":"Advertising","level":1,"score":0.24294909834861755},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12116312980651855},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s00138-024-01549-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00138-024-01549-9","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00138-024-01549-9.pdf","source":{"id":"https://openalex.org/S27728525","display_name":"Machine Vision and Applications","issn_l":"0932-8092","issn":["0932-8092","1432-1769"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Vision and Applications","raw_type":"journal-article"},{"id":"pmh:oai:DiVA.org:his-23933","is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:his:diva-23933","pdf_url":null,"source":{"id":"https://openalex.org/S4306401029","display_name":"University Library of Sk\u00f6vde (University of Sk\u00f6vde)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205158640","host_organization_name":"University of Sk\u00f6vde","host_organization_lineage":["https://openalex.org/I205158640"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1007/s00138-024-01549-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00138-024-01549-9","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00138-024-01549-9.pdf","source":{"id":"https://openalex.org/S27728525","display_name":"Machine Vision and Applications","issn_l":"0932-8092","issn":["0932-8092","1432-1769"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Vision and Applications","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth","score":0.7400000095367432}],"awards":[{"id":"https://openalex.org/G1364868472","display_name":null,"funder_award_id":"2018-05973","funder_id":"https://openalex.org/F4320322581","funder_display_name":"Vetenskapsr\u00e5det"},{"id":"https://openalex.org/G3321450376","display_name":null,"funder_award_id":"05973","funder_id":"https://openalex.org/F4320322581","funder_display_name":"Vetenskapsr\u00e5det"},{"id":"https://openalex.org/G4572525476","display_name":null,"funder_award_id":"grant agreement no. 2018-05973","funder_id":"https://openalex.org/F4320322581","funder_display_name":"Vetenskapsr\u00e5det"},{"id":"https://openalex.org/G712881263","display_name":null,"funder_award_id":"2018-","funder_id":"https://openalex.org/F4320322581","funder_display_name":"Vetenskapsr\u00e5det"}],"funders":[{"id":"https://openalex.org/F4320322581","display_name":"Vetenskapsr\u00e5det","ror":"https://ror.org/03zttf063"},{"id":"https://openalex.org/F4320328657","display_name":"H\u00f6gskolan i Sk\u00f6vde","ror":"https://ror.org/051mrsz47"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399432865.pdf"},"referenced_works_count":81,"referenced_works":["https://openalex.org/W16066671","https://openalex.org/W2127095579","https://openalex.org/W2151103935","https://openalex.org/W2194775991","https://openalex.org/W2203189730","https://openalex.org/W2250539671","https://openalex.org/W2504485264","https://openalex.org/W2579318141","https://openalex.org/W2602178251","https://openalex.org/W2619383789","https://openalex.org/W2767929243","https://openalex.org/W2784163702","https://openalex.org/W2787873795","https://openalex.org/W2894676449","https://openalex.org/W2897842311","https://openalex.org/W2900753462","https://openalex.org/W2905005563","https://openalex.org/W2911663386","https://openalex.org/W2921056832","https://openalex.org/W2936150952","https://openalex.org/W2951755742","https://openalex.org/W2961018736","https://openalex.org/W2962724251","https://openalex.org/W2963539956","https://openalex.org/W2963626623","https://openalex.org/W2963686633","https://openalex.org/W2971900262","https://openalex.org/W2980708516","https://openalex.org/W2981976713","https://openalex.org/W2982083293","https://openalex.org/W2996041315","https://openalex.org/W3010622391","https://openalex.org/W3011640627","https://openalex.org/W3013022628","https://openalex.org/W3024152176","https://openalex.org/W3034457371","https://openalex.org/W3034993937","https://openalex.org/W3036444709","https://openalex.org/W3042175414","https://openalex.org/W3088337003","https://openalex.org/W3093029279","https://openalex.org/W3093526239","https://openalex.org/W3094609756","https://openalex.org/W3103152812","https://openalex.org/W3105335547","https://openalex.org/W3105354225","https://openalex.org/W3106146634","https://openalex.org/W3111114947","https://openalex.org/W3118152356","https://openalex.org/W3118547708","https://openalex.org/W3120139496","https://openalex.org/W3120545528","https://openalex.org/W3126336475","https://openalex.org/W3128046581","https://openalex.org/W3130422318","https://openalex.org/W3130423852","https://openalex.org/W3133204170","https://openalex.org/W3138516171","https://openalex.org/W3177275514","https://openalex.org/W3183098974","https://openalex.org/W3183819948","https://openalex.org/W3187289500","https://openalex.org/W3191404950","https://openalex.org/W3194454787","https://openalex.org/W3194487089","https://openalex.org/W3199015608","https://openalex.org/W3199729485","https://openalex.org/W3204450916","https://openalex.org/W3205471129","https://openalex.org/W3213192039","https://openalex.org/W3217661900","https://openalex.org/W4205335327","https://openalex.org/W4206237889","https://openalex.org/W4210316772","https://openalex.org/W4225541601","https://openalex.org/W4226549712","https://openalex.org/W4281751435","https://openalex.org/W4312241447","https://openalex.org/W4312443924","https://openalex.org/W4321789735","https://openalex.org/W6601572732"],"related_works":["https://openalex.org/W2529447859","https://openalex.org/W4309761369","https://openalex.org/W3116344863","https://openalex.org/W2611900230","https://openalex.org/W2890416085","https://openalex.org/W2755342338","https://openalex.org/W2775347418","https://openalex.org/W2785060783","https://openalex.org/W4206594571","https://openalex.org/W2603253675"],"abstract_inverted_index":{"Abstract":[0],"Automatic":[1],"recognition":[2,23,55,81,96,139,165,171],"of":[3,38,52,97,116,148],"grocery":[4,64,98],"products":[5,39,67],"can":[6,175],"be":[7,176],"used":[8,167],"to":[9,34,93,168],"improve":[10,94,170],"customer":[11],"flow":[12],"at":[13,178],"checkouts":[14],"and":[15,19,40,104,108,124,133],"reduce":[16],"labor":[17],"costs":[18],"store":[20,65],"losses.":[21],"Product":[22],"is,":[24],"however,":[25],"a":[26,59,63,78,135],"challenging":[27],"task":[28],"for":[29,158],"machine":[30],"learning-based":[31],"solutions":[32],"due":[33],"the":[35,50,146],"large":[36,60],"number":[37,147],"their":[41],"variations":[42],"in":[43,130,162],"appearance.":[44],"In":[45],"this":[46,154],"work,":[47],"we":[48,76],"tackle":[49],"challenge":[51],"fine-grained":[53,95],"product":[54,80,85,164],"by":[56,72],"first":[57],"extracting":[58],"dataset":[61,174],"from":[62,91],"containing":[66],"that":[68,83,122],"are":[69],"only":[70],"differentiable":[71],"subtle":[73],"details.":[74],"Then,":[75],"propose":[77],"multimodal":[79,114,131],"approach":[82,155],"uses":[84],"images":[86],"with":[87,137],"extracted":[88],"OCR":[89],"text":[90,105],"packages":[92],"products.":[99],"We":[100],"evaluate":[101],"several":[102],"image":[103,123],"models":[106,115,132],"separately":[107],"then":[109],"combine":[110],"them":[111],"using":[112],"different":[113,160],"varying":[117],"complexities.":[118],"The":[119,173],"results":[120],"show":[121],"textual":[125],"information":[126],"complement":[127],"each":[128],"other":[129],"enable":[134],"classifier":[136],"greater":[138],"performance":[140],"than":[141],"unimodal":[142],"models,":[143],"especially":[144],"when":[145],"training":[149],"samples":[150],"is":[151,156,166],"limited.":[152],"Therefore,":[153],"suitable":[157],"many":[159],"scenarios":[161],"which":[163],"further":[169],"performance.":[172],"found":[177],"https://github.com/Tubbias/finegrainocr":[179],".":[180]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}