{"id":"https://openalex.org/W4313492027","doi":"https://doi.org/10.1145/3570991.3571010","title":"Designing a Vision Transformer based Enhanced Text Extractor for Product Images","display_name":"Designing a Vision Transformer based Enhanced Text Extractor for Product Images","publication_year":2023,"publication_date":"2023-01-04","ids":{"openalex":"https://openalex.org/W4313492027","doi":"https://doi.org/10.1145/3570991.3571010"},"language":"en","primary_location":{"id":"doi:10.1145/3570991.3571010","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3570991.3571010","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th Joint International Conference on Data Science & Management of Data (10th ACM IKDD CODS and 28th COMAD)","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/A5083639618","display_name":"Saptarshi Misra","orcid":"https://orcid.org/0000-0001-5125-6311"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Saptarshi Misra","raw_affiliation_strings":["Walmart Global Tech, India"],"affiliations":[{"raw_affiliation_string":"Walmart Global Tech, India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006056405","display_name":"Pranay Dugar","orcid":"https://orcid.org/0000-0002-5598-7872"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pranay Dugar","raw_affiliation_strings":["Walmart Global Tech, India"],"affiliations":[{"raw_affiliation_string":"Walmart Global Tech, India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075247915","display_name":"Anirban Chatterjee","orcid":"https://orcid.org/0000-0003-2513-6433"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anirban Chatterjee","raw_affiliation_strings":["Walmart Global Tech, India"],"affiliations":[{"raw_affiliation_string":"Walmart Global Tech, India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006129471","display_name":"Lalitdutt Parsai","orcid":"https://orcid.org/0000-0002-5327-203X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lalitdutt Parsai","raw_affiliation_strings":["Walmart Global Tech, India"],"affiliations":[{"raw_affiliation_string":"Walmart Global Tech, India","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023588595","display_name":"Kunal Banerjee","orcid":"https://orcid.org/0000-0002-0605-630X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kunal Banerjee","raw_affiliation_strings":["Walmart Global Tech, India"],"affiliations":[{"raw_affiliation_string":"Walmart Global Tech, India","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5083639618"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00223611,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"208","last_page":"212"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9998999834060669,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9998999834060669,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9897000193595886,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.9883999824523926,"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":0.7311112880706787},{"id":"https://openalex.org/keywords/extractor","display_name":"Extractor","score":0.568343997001648},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5235078930854797},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5213602781295776},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.47687798738479614},{"id":"https://openalex.org/keywords/resolver","display_name":"Resolver","score":0.4615635275840759},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.4434622526168823},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.44211846590042114},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4387504458427429},{"id":"https://openalex.org/keywords/indexation","display_name":"Indexation","score":0.419389009475708},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.4106642007827759},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.34969624876976013},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32350990176200867},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1957363784313202}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7311112880706787},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.568343997001648},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5235078930854797},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5213602781295776},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.47687798738479614},{"id":"https://openalex.org/C80156102","wikidata":"https://www.wikidata.org/wiki/Q788036","display_name":"Resolver","level":3,"score":0.4615635275840759},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4434622526168823},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.44211846590042114},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4387504458427429},{"id":"https://openalex.org/C186311912","wikidata":"https://www.wikidata.org/wiki/Q2038409","display_name":"Indexation","level":3,"score":0.419389009475708},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.4106642007827759},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34969624876976013},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32350990176200867},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1957363784313202},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C126285488","wikidata":"https://www.wikidata.org/wiki/Q178476","display_name":"Monetary policy","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C21880701","wikidata":"https://www.wikidata.org/wiki/Q2144042","display_name":"Process engineering","level":1,"score":0.0},{"id":"https://openalex.org/C556758197","wikidata":"https://www.wikidata.org/wiki/Q580018","display_name":"Monetary economics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C165005293","wikidata":"https://www.wikidata.org/wiki/Q1074500","display_name":"Chip","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3570991.3571010","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3570991.3571010","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th Joint International Conference on Data Science & Management of Data (10th ACM IKDD CODS and 28th COMAD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1922126009","https://openalex.org/W2194187530","https://openalex.org/W2788069964","https://openalex.org/W2963517393","https://openalex.org/W2967615747","https://openalex.org/W3004846386","https://openalex.org/W3211160260","https://openalex.org/W4212960994"],"related_works":["https://openalex.org/W2121484818","https://openalex.org/W2804343227","https://openalex.org/W2142531896","https://openalex.org/W1526923327","https://openalex.org/W2158159993","https://openalex.org/W2369328568","https://openalex.org/W2377847262","https://openalex.org/W4210337026","https://openalex.org/W2588537960","https://openalex.org/W4380356635"],"abstract_inverted_index":{"Product":[0],"images,":[1],"such":[2,137],"as":[3],"those":[4,184],"which":[5],"appear":[6,128,144],"in":[7,18,45,56,105,112,145,198],"e-commerce":[8],"sites,":[9],"exhibit":[10],"unique":[11],"characteristics":[12],"that":[13,158],"are":[14,82,102,122],"typically":[15],"not":[16,143],"present":[17,151],"natural":[19],"images.":[20],"The":[21],"primary":[22],"distinguishing":[23],"characteristic":[24],"is":[25,89],"the":[26,46,61,80,93,139,161],"presence":[27],"of":[28,48,134,185,200],"text":[29,50,62,94,156,180,189],"(e.g.,":[30],"brand":[31,140],"names,":[32,141],"price,":[33],"constituents)":[34],"along":[35],"with":[36,96,183],"high":[37],"local":[38],"entropy":[39],"(i.e.,":[40],"too":[41],"much":[42],"visual":[43],"information":[44],"form":[47],"both":[49,197],"and":[51,77,85,99,168,187,193,202],"brightly":[52],"coloured":[53],"pictures":[54],"condensed":[55],"a":[57,113,116,152],"small":[58],"region).":[59],"Extracting":[60],"from":[63],"these":[64,100,135],"images":[65,81,166],"may":[66],"have":[67],"multiple":[68],"benefits:":[69],"catalogue":[70],"enrichment,":[71],"product":[72,165],"matching,":[73],"offensive":[74],"content":[75],"identification,":[76],"more.":[78],"However,":[79],"sometimes":[83],"unclear":[84],"blurry":[86],"where":[87],"it":[88],"difficult":[90],"to":[91],"recognise":[92],"even":[95],"human":[97],"perception,":[98],"texts":[101],"often":[103],"written":[104],"non-standard":[106],"fonts":[107],"(at":[108],"times":[109],"each":[110],"character":[111],"word":[114],"has":[115],"different":[117],"colour":[118],"and/or":[119],"style),":[120],"or":[121,127],"oriented":[123],"at":[124],"odd":[125],"angles":[126],"on":[129],"curved":[130],"surfaces;":[131],"moreover,":[132],"many":[133],"words":[136],"as,":[138],"do":[142],"dictionaries.":[146],"In":[147],"this":[148],"work,":[149],"we":[150],"vision":[153],"transformer":[154],"based":[155],"extractor":[157],"can":[159],"handle":[160],"aforementioned":[162],"challenges":[163],"for":[164],"effectively,":[167],"outperforms":[169],"our":[170,177],"earlier":[171],"model":[172],"considerably.":[173],"We":[174],"further":[175],"compare":[176],"new":[178],"end-to-end":[179],"extraction":[181,190],"solution":[182],"Google":[186],"Azure":[188],"cloud":[191],"offerings,":[192],"showcase":[194],"its":[195],"efficacy":[196],"terms":[199],"accuracy":[201],"latency.":[203]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}