{"id":"https://openalex.org/W2894676449","doi":"https://doi.org/10.1109/dicta.2018.8615789","title":"Image and Encoded Text Fusion for Multi-Modal Classification","display_name":"Image and Encoded Text Fusion for Multi-Modal Classification","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2894676449","doi":"https://doi.org/10.1109/dicta.2018.8615789","mag":"2894676449"},"language":"en","primary_location":{"id":"doi:10.1109/dicta.2018.8615789","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dicta.2018.8615789","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Digital Image Computing: Techniques and Applications (DICTA)","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/A5054778549","display_name":"Ignazio Gallo","orcid":"https://orcid.org/0000-0002-7076-8328"},"institutions":[{"id":"https://openalex.org/I115752224","display_name":"University of Insubria","ror":"https://ror.org/00s409261","country_code":"IT","type":"education","lineage":["https://openalex.org/I115752224"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"I. Gallo","raw_affiliation_strings":["Dep. of Theoretical and Applied Science, University of Insubria, Varese, Italy"],"affiliations":[{"raw_affiliation_string":"Dep. of Theoretical and Applied Science, University of Insubria, Varese, Italy","institution_ids":["https://openalex.org/I115752224"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087859719","display_name":"Alessandro Calefati","orcid":"https://orcid.org/0000-0003-3860-4785"},"institutions":[{"id":"https://openalex.org/I115752224","display_name":"University of Insubria","ror":"https://ror.org/00s409261","country_code":"IT","type":"education","lineage":["https://openalex.org/I115752224"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"A. Calefati","raw_affiliation_strings":["Dep. of Theoretical and Applied Science, University of Insubria, Varese, Italy"],"affiliations":[{"raw_affiliation_string":"Dep. of Theoretical and Applied Science, University of Insubria, Varese, Italy","institution_ids":["https://openalex.org/I115752224"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016485532","display_name":"Shah Nawaz","orcid":"https://orcid.org/0000-0002-7715-4409"},"institutions":[{"id":"https://openalex.org/I115752224","display_name":"University of Insubria","ror":"https://ror.org/00s409261","country_code":"IT","type":"education","lineage":["https://openalex.org/I115752224"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"S. Nawaz","raw_affiliation_strings":["Dep. of Theoretical and Applied Science, University of Insubria, Varese, Italy"],"affiliations":[{"raw_affiliation_string":"Dep. of Theoretical and Applied Science, University of Insubria, Varese, Italy","institution_ids":["https://openalex.org/I115752224"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003149553","display_name":"Muhammad Kamran Janjua","orcid":"https://orcid.org/0000-0002-5666-1700"},"institutions":[{"id":"https://openalex.org/I929597975","display_name":"National University of Sciences and Technology","ror":"https://ror.org/03w2j5y17","country_code":"PK","type":"education","lineage":["https://openalex.org/I929597975"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"M. K. Janjua","raw_affiliation_strings":["National University of Sciences and Technology, Islamabad, Pakistan"],"affiliations":[{"raw_affiliation_string":"National University of Sciences and Technology, Islamabad, Pakistan","institution_ids":["https://openalex.org/I929597975"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5054778549"],"corresponding_institution_ids":["https://openalex.org/I115752224"],"apc_list":null,"apc_paid":null,"fwci":1.8802,"has_fulltext":false,"cited_by_count":53,"citation_normalized_percentile":{"value":0.8989115,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9984999895095825,"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":0.9984999895095825,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9908999800682068,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7780417203903198},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7712842226028442},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.7306529879570007},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6916051506996155},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6073884963989258},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6060912013053894},{"id":"https://openalex.org/keywords/image-fusion","display_name":"Image fusion","score":0.5255393385887146},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.5033079981803894},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4872845411300659},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.4695855975151062},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.46433863043785095},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.45906808972358704},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3550408184528351}],"concepts":[{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7780417203903198},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7712842226028442},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7306529879570007},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6916051506996155},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6073884963989258},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6060912013053894},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.5255393385887146},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.5033079981803894},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4872845411300659},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.4695855975151062},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.46433863043785095},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.45906808972358704},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3550408184528351},{"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},{"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/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/dicta.2018.8615789","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dicta.2018.8615789","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Digital Image Computing: Techniques and Applications (DICTA)","raw_type":"proceedings-article"},{"id":"pmh:oai:irinsubria.uninsubria.it:11383/2083804","is_oa":false,"landing_page_url":"http://hdl.handle.net/11383/2083804","pdf_url":null,"source":{"id":"https://openalex.org/S4377196351","display_name":"IrInSubria (University of Insubria)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I115752224","host_organization_name":"University of Insubria","host_organization_lineage":["https://openalex.org/I115752224"],"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":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5799999833106995,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W155596317","https://openalex.org/W1614298861","https://openalex.org/W1832693441","https://openalex.org/W1981613567","https://openalex.org/W2026012689","https://openalex.org/W2053101950","https://openalex.org/W2095569536","https://openalex.org/W2097117768","https://openalex.org/W2126274282","https://openalex.org/W2145056192","https://openalex.org/W2155806188","https://openalex.org/W2163605009","https://openalex.org/W2164587673","https://openalex.org/W2177113878","https://openalex.org/W2184188583","https://openalex.org/W2251394420","https://openalex.org/W2296448531","https://openalex.org/W2470413457","https://openalex.org/W2619383789","https://openalex.org/W2786495300","https://openalex.org/W2786797739","https://openalex.org/W2787873795","https://openalex.org/W2963389687","https://openalex.org/W2963823840","https://openalex.org/W2963887950","https://openalex.org/W6606244218","https://openalex.org/W6606327593","https://openalex.org/W6636510571","https://openalex.org/W6678924111","https://openalex.org/W6684191040","https://openalex.org/W6685422269","https://openalex.org/W6686207219","https://openalex.org/W6697395949","https://openalex.org/W6738199216","https://openalex.org/W6748680937"],"related_works":["https://openalex.org/W2788731446","https://openalex.org/W2204403038","https://openalex.org/W3152170969","https://openalex.org/W2379054866","https://openalex.org/W2549658594","https://openalex.org/W2370195708","https://openalex.org/W1490651872","https://openalex.org/W2139242969","https://openalex.org/W2284201331","https://openalex.org/W2095903272"],"abstract_inverted_index":{"Multi-modal":[0],"approaches":[1],"employ":[2],"data":[3],"from":[4],"multiple":[5],"input":[6],"streams":[7],"such":[8],"as":[9],"textual":[10],"and":[11,36,129],"visual":[12],"domains.":[13],"Deep":[14],"neural":[15],"networks":[16],"have":[17],"been":[18],"successfully":[19],"employed":[20,76],"for":[21,77],"these":[22],"approaches.":[23],"In":[24],"this":[25],"paper,":[26],"we":[27,117],"present":[28],"a":[29,83],"novel":[30,95],"multi-modal":[31,41,109,124],"approach":[32,49,101,120],"that":[33],"fuses":[34],"images":[35],"text":[37,53],"descriptions":[38],"to":[39,57,90],"improve":[40],"classification":[42,78,110],"performance":[43],"in":[44],"real-world":[45],"scenarios.":[46],"The":[47],"proposed":[48],"embeds":[50],"an":[51,55,59],"encoded":[52],"onto":[54],"image":[56],"obtain":[58],"information":[60],"enriched":[61],"image.":[62],"To":[63],"learn":[64,91],"feature":[65],"representations":[66,92],"of":[67,93],"resulting":[68],"images,":[69],"standard":[70],"Convolutional":[71],"Neural":[72],"Networks":[73],"(CNNs)":[74],"is":[75],"task.":[79],"We":[80,98],"demonstrate":[81],"how":[82],"CNN":[84],"based":[85],"pipeline":[86],"can":[87],"be":[88],"used":[89],"the":[94],"fusion":[96,128],"approach.":[97],"compare":[99],"our":[100,119],"with":[102],"individual":[103],"sources":[104],"on":[105],"two":[106,122],"large":[107],"scale":[108],"datasets":[111],"while":[112],"obtaining":[113],"encouraging":[114],"results.":[115],"Furthermore,":[116],"evaluate":[118],"against":[121],"famous":[123],"strategies":[125],"namely":[126],"early":[127],"late":[130],"fusion.":[131]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}