{"id":"https://openalex.org/W3114065210","doi":"https://doi.org/10.1145/3430984.3431030","title":"On-Device Document Classification using multimodal features","display_name":"On-Device Document Classification using multimodal features","publication_year":2020,"publication_date":"2020-12-28","ids":{"openalex":"https://openalex.org/W3114065210","doi":"https://doi.org/10.1145/3430984.3431030","mag":"3114065210"},"language":"en","primary_location":{"id":"doi:10.1145/3430984.3431030","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3430984.3431030","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd ACM India Joint International Conference on Data Science & Management of Data (8th ACM IKDD CODS & 26th COMAD)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2101.01880","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041264187","display_name":"Sugam Garg","orcid":null},"institutions":[{"id":"https://openalex.org/I4210139030","display_name":"Samsung (India)","ror":"https://ror.org/04cpx2569","country_code":"IN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210139030"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sugam Garg","raw_affiliation_strings":["Samsung R&D Institute Bangalore, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung R&D Institute Bangalore, India","institution_ids":["https://openalex.org/I4210139030"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029306575","display_name":"Harichandana SS","orcid":null},"institutions":[{"id":"https://openalex.org/I4210139030","display_name":"Samsung (India)","ror":"https://ror.org/04cpx2569","country_code":"IN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210139030"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Harichandana SS","raw_affiliation_strings":["Samsung R&D Institute Bangalore, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung R&D Institute Bangalore, India","institution_ids":["https://openalex.org/I4210139030"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005088304","display_name":"Sumit Kumar","orcid":"https://orcid.org/0000-0001-5441-1671"},"institutions":[{"id":"https://openalex.org/I4210139030","display_name":"Samsung (India)","ror":"https://ror.org/04cpx2569","country_code":"IN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210139030"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sumit Kumar","raw_affiliation_strings":["Samsung R&D Institute Bangalore, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung R&D Institute Bangalore, India","institution_ids":["https://openalex.org/I4210139030"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210139030"],"apc_list":null,"apc_paid":null,"fwci":0.0957,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.4221539,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"203","last_page":"207"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9987999796867371,"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/T11309","display_name":"Music and Audio Processing","score":0.9979000091552734,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.8494504690170288},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7314825057983398},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6092435717582703},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5996170043945312},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5869004726409912},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.5292013883590698},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5238590240478516},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.48829197883605957},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.42018458247184753},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4059428870677948}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8494504690170288},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7314825057983398},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6092435717582703},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5996170043945312},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5869004726409912},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.5292013883590698},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5238590240478516},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.48829197883605957},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.42018458247184753},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4059428870677948},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3430984.3431030","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3430984.3431030","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd ACM India Joint International Conference on Data Science & Management of Data (8th ACM IKDD CODS & 26th COMAD)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2101.01880","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2101.01880","pdf_url":"https://arxiv.org/pdf/2101.01880","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2101.01880","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2101.01880","pdf_url":"https://arxiv.org/pdf/2101.01880","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2062227835","https://openalex.org/W2095705004","https://openalex.org/W2143017621","https://openalex.org/W2194775991","https://openalex.org/W2296448531","https://openalex.org/W2470673105","https://openalex.org/W2612445135","https://openalex.org/W2619383789","https://openalex.org/W2784121710","https://openalex.org/W2787873795","https://openalex.org/W2896457183","https://openalex.org/W2914913241","https://openalex.org/W2939507640","https://openalex.org/W2945542139","https://openalex.org/W2949117887","https://openalex.org/W2949495788","https://openalex.org/W2963026768","https://openalex.org/W2963823840","https://openalex.org/W2999803534","https://openalex.org/W3000141935","https://openalex.org/W3013022628","https://openalex.org/W3103398325"],"related_works":["https://openalex.org/W2292997772","https://openalex.org/W3037187668","https://openalex.org/W2055243143","https://openalex.org/W2370205415","https://openalex.org/W4387493491","https://openalex.org/W2055970094","https://openalex.org/W2904225411","https://openalex.org/W4234772502","https://openalex.org/W4388331409","https://openalex.org/W4377970376"],"abstract_inverted_index":{"From":[0],"small":[1],"screenshots":[2],"to":[3,83,94],"large":[4],"videos,":[5],"documents":[6,36,47,85],"take":[7],"up":[8],"a":[9,14,19,40,63,71,80,123,135],"bulk":[10],"of":[11,32,35,148],"space":[12],"in":[13,18,39,62,114],"modern":[15],"smartphone.":[16],"Documents":[17],"phone":[20],"can":[21],"accumulate":[22],"from":[23],"various":[24],"sources,":[25],"and":[26,78,109,140],"with":[27,134,144,151],"the":[28,115,119,145,149],"high":[29],"storage":[30],"capacity":[31],"mobiles,":[33],"hundreds":[34],"are":[37],"accumulated":[38],"short":[41],"period.":[42],"However,":[43],"searching":[44],"or":[45,59],"managing":[46],"remains":[48],"an":[49,101],"onerous":[50],"task,":[51,98],"since":[52],"most":[53],"search":[54],"methods":[55],"depend":[56],"on":[57],"meta-information":[58],"only":[60],"text":[61],"document.":[64],"In":[65],"this":[66,97],"paper,":[67],"we":[68,99],"showcase":[69,141],"that":[70],"single":[72],"modality":[73],"is":[74],"insufficient":[75],"for":[76,104,121,126],"classification":[77,132],"present":[79],"novel":[81,111],"pipeline":[82],"classify":[84],"on-device,":[86],"thus":[87],"preventing":[88],"any":[89],"private":[90],"user":[91],"data":[92],"transfer":[93],"server.":[95],"For":[96],"integrate":[100],"open-source":[102],"library":[103],"Optical":[105],"Character":[106],"Recognition":[107],"(OCR)":[108],"our":[110,131],"model":[112,120,133,153],"architecture":[113],"pipeline.":[116],"We":[117,129],"optimise":[118],"size,":[122],"necessary":[124],"metric":[125],"on-device":[127],"inference.":[128],"benchmark":[130],"standard":[136],"multimodal":[137],"dataset":[138],"FOOD-101":[139],"competitive":[142],"results":[143],"previous":[146],"State":[147],"Art":[150],"30%":[152],"compression.":[154]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-10T00:00:00"}