{"id":"https://openalex.org/W4200331212","doi":"https://doi.org/10.3233/jifs-219230","title":"Searching for memory-lighter architectures for OCR-augmented image captioning","display_name":"Searching for memory-lighter architectures for OCR-augmented image captioning","publication_year":2021,"publication_date":"2021-12-15","ids":{"openalex":"https://openalex.org/W4200331212","doi":"https://doi.org/10.3233/jifs-219230"},"language":"en","primary_location":{"id":"doi:10.3233/jifs-219230","is_oa":false,"landing_page_url":"https://doi.org/10.3233/jifs-219230","pdf_url":null,"source":{"id":"https://openalex.org/S179157397","display_name":"Journal of Intelligent & Fuzzy Systems","issn_l":"1064-1246","issn":["1064-1246","1875-8967"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Intelligent & Fuzzy Systems","raw_type":"journal-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/A5102437193","display_name":"Rafael Gallardo-Garc\u00eda","orcid":null},"institutions":[{"id":"https://openalex.org/I721619","display_name":"Benem\u00e9rita Universidad Aut\u00f3noma de Puebla","ror":"https://ror.org/03p2z7827","country_code":"MX","type":"education","lineage":["https://openalex.org/I721619"]}],"countries":["MX"],"is_corresponding":true,"raw_author_name":"Rafael Gallardo-Garc\u00eda","raw_affiliation_strings":["Language and Knowledge Engineering Laboratory, Benem\u00e9rita Universidad Aut\u00f3noma de Puebla, Puebla, Mexico"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language and Knowledge Engineering Laboratory, Benem\u00e9rita Universidad Aut\u00f3noma de Puebla, Puebla, Mexico","institution_ids":["https://openalex.org/I721619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012040249","display_name":"Beatr\u00edz Beltr\u00e1n","orcid":"https://orcid.org/0000-0003-4528-4222"},"institutions":[{"id":"https://openalex.org/I721619","display_name":"Benem\u00e9rita Universidad Aut\u00f3noma de Puebla","ror":"https://ror.org/03p2z7827","country_code":"MX","type":"education","lineage":["https://openalex.org/I721619"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Beatriz Beltr\u00e1n-Mart\u00ednez","raw_affiliation_strings":["Language and Knowledge Engineering Laboratory, Benem\u00e9rita Universidad Aut\u00f3noma de Puebla, Puebla, Mexico"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language and Knowledge Engineering Laboratory, Benem\u00e9rita Universidad Aut\u00f3noma de Puebla, Puebla, Mexico","institution_ids":["https://openalex.org/I721619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101597326","display_name":"Carlos Hern\u00e1ndez","orcid":"https://orcid.org/0000-0003-0267-6306"},"institutions":[{"id":"https://openalex.org/I721619","display_name":"Benem\u00e9rita Universidad Aut\u00f3noma de Puebla","ror":"https://ror.org/03p2z7827","country_code":"MX","type":"education","lineage":["https://openalex.org/I721619"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Carlos Hern\u00e1ndez-Gracidas","raw_affiliation_strings":["Faculty of Physical and Mathematical Sciences, Benem\u00e9rita Universidad Aut\u00f3noma de Puebla, Puebla, Mexico"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Physical and Mathematical Sciences, Benem\u00e9rita Universidad Aut\u00f3noma de Puebla, Puebla, Mexico","institution_ids":["https://openalex.org/I721619"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091785066","display_name":"Darnes Vilari\u00f1o Ayala","orcid":"https://orcid.org/0000-0002-3539-2783"},"institutions":[{"id":"https://openalex.org/I721619","display_name":"Benem\u00e9rita Universidad Aut\u00f3noma de Puebla","ror":"https://ror.org/03p2z7827","country_code":"MX","type":"education","lineage":["https://openalex.org/I721619"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Darnes Vilari\u00f1o-Ayala","raw_affiliation_strings":["Language and Knowledge Engineering Laboratory, Benem\u00e9rita Universidad Aut\u00f3noma de Puebla, Puebla, Mexico"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language and Knowledge Engineering Laboratory, Benem\u00e9rita Universidad Aut\u00f3noma de Puebla, Puebla, Mexico","institution_ids":["https://openalex.org/I721619"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5102437193"],"corresponding_institution_ids":["https://openalex.org/I721619"],"apc_list":null,"apc_paid":null,"fwci":0.0942,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.41634429,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"42","issue":"5","first_page":"4399","last_page":"4410"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9965999722480774,"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/T11439","display_name":"Video Analysis and Summarization","score":0.984000027179718,"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":0.8557306528091431},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.773715615272522},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6899533271789551},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5915176868438721},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5447753667831421},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5255643129348755},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4762953817844391},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.41848224401474},{"id":"https://openalex.org/keywords/usability","display_name":"Usability","score":0.4125227630138397},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.35786354541778564},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33806347846984863},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3357212543487549},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.14331600069999695},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12987792491912842}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8557306528091431},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.773715615272522},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6899533271789551},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5915176868438721},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5447753667831421},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5255643129348755},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4762953817844391},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.41848224401474},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.4125227630138397},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.35786354541778564},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33806347846984863},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3357212543487549},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.14331600069999695},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12987792491912842},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/jifs-219230","is_oa":false,"landing_page_url":"https://doi.org/10.3233/jifs-219230","pdf_url":null,"source":{"id":"https://openalex.org/S179157397","display_name":"Journal of Intelligent & Fuzzy Systems","issn_l":"1064-1246","issn":["1064-1246","1875-8967"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Intelligent & Fuzzy Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Responsible consumption and production","id":"https://metadata.un.org/sdg/12","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2133459682","https://openalex.org/W2250539671","https://openalex.org/W2506483933","https://openalex.org/W2613718673","https://openalex.org/W2809273748","https://openalex.org/W2896348597","https://openalex.org/W2963908984","https://openalex.org/W2967615747","https://openalex.org/W2979382951","https://openalex.org/W3034336960","https://openalex.org/W3034792612","https://openalex.org/W3093272873","https://openalex.org/W3106859150","https://openalex.org/W3110661548","https://openalex.org/W3112075608","https://openalex.org/W3174012740","https://openalex.org/W3177430964","https://openalex.org/W3181159501"],"related_works":["https://openalex.org/W2795359650","https://openalex.org/W3107474891","https://openalex.org/W3008515501","https://openalex.org/W2923366293","https://openalex.org/W2945836425","https://openalex.org/W4285428748","https://openalex.org/W4284710034","https://openalex.org/W2435130738","https://openalex.org/W2577085889","https://openalex.org/W2523937091"],"abstract_inverted_index":{"Current":[0],"State-of-the-Art":[1],"image":[2],"captioning":[3],"systems":[4],"that":[5],"can":[6,142],"read":[7,10],"and":[8,20,27,36,48,175],"integrate":[9],"text":[11],"into":[12],"the":[13,25,30,54,71,86,91,105,108,119,122,144,148,158,166,170,173,190,198],"generated":[14],"descriptions":[15],"need":[16],"high":[17],"processing":[18],"power":[19],"memory":[21,145],"usage,":[22],"which":[23,57,193],"limits":[24],"sustainability":[26],"usability":[28],"of":[29,50,97,107,136,157,169,187],"models":[31,84,160],"(as":[32],"they":[33],"require":[34],"expensive":[35],"very":[37],"specialized":[38],"hardware).":[39],"The":[40],"present":[41],"work":[42,164],"introduces":[43],"two":[44],"alternative":[45],"versions":[46],"(L-M4C":[47],"L-CNMT)":[49],"top":[51],"architectures":[52,128],"(on":[53],"TextCaps":[55],"challenge),":[56],"were":[58],"mainly":[59,76],"adapted":[60],"to":[61,70,103,152],"achieve":[62],"near-State-of-The-Art":[63],"performance":[64],"while":[65],"being":[66],"memory-lighter":[67],"when":[68],"compared":[69],"original":[72],"architectures,":[73],"this":[74,141,163],"is":[75,194],"achieved":[77],"by":[78,131,147],"using":[79,137],"distilled":[80,95,112],"or":[81],"smaller":[82],"pre-trained":[83,139],"on":[85,118,126,172,189],"text-and-OCR":[87],"embedding":[88],"modules.":[89],"On":[90],"one":[92],"hand,":[93,121],"a":[94,153,184],"version":[96],"BERT":[98],"was":[99,129],"used":[100,146],"in":[101,162],"order":[102],"reduce":[104,143],"size":[106],"text-embedding":[109],"module":[110,150],"(the":[111],"model":[113],"has":[114],"59%":[115],"fewer":[116],"parameters),":[117],"other":[120],"OCR":[123],"context":[124],"processor":[125],"both":[127],"replaced":[130],"Global":[132],"Vectors":[133],"(GloVe),":[134],"instead":[135],"FastText":[138],"vectors,":[140],"OCR-embedding":[149],"up":[151],"94%":[154],".":[155],"Two":[156],"three":[159],"presented":[161],"surpassed":[165],"baseline":[167,199],"(M4C-Captioner)":[168],"challenge":[171],"evaluation":[174],"test":[176,191],"sets,":[177],"also,":[178],"our":[179],"best":[180],"lighter":[181],"architecture":[182],"reached":[183],"CIDEr":[185],"score":[186],"88.24":[188],"set,":[192],"7.25":[195],"points":[196],"above":[197],"model.":[200]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}