{"id":"https://openalex.org/W4413912213","doi":"https://doi.org/10.1007/s00521-025-11521-x","title":"Multimodal object detection: an architecture using feature-level fusion and deep learning","display_name":"Multimodal object detection: an architecture using feature-level fusion and deep learning","publication_year":2025,"publication_date":"2025-09-02","ids":{"openalex":"https://openalex.org/W4413912213","doi":"https://doi.org/10.1007/s00521-025-11521-x"},"language":"en","primary_location":{"id":"doi:10.1007/s00521-025-11521-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-025-11521-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-025-11521-x.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"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":"Neural Computing 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/s00521-025-11521-x.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082550019","display_name":"Rui Silva","orcid":"https://orcid.org/0000-0001-6928-6770"},"institutions":[{"id":"https://openalex.org/I155381812","display_name":"University of Tr\u00e1s-os-Montes and Alto Douro","ror":"https://ror.org/03qc8vh97","country_code":"PT","type":"education","lineage":["https://openalex.org/I155381812"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Rui Silva","raw_affiliation_strings":["CITAB, Universidade de Tr\u00e1s-os-Montes e Alto Douro, 5000-801, Vila Real, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CITAB, Universidade de Tr\u00e1s-os-Montes e Alto Douro, 5000-801, Vila Real, Portugal","institution_ids":["https://openalex.org/I155381812"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042348182","display_name":"Eduardo Coelho","orcid":"https://orcid.org/0009-0006-9568-854X"},"institutions":[{"id":"https://openalex.org/I99682543","display_name":"University of Minho","ror":"https://ror.org/037wpkx04","country_code":"PT","type":"education","lineage":["https://openalex.org/I99682543"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Eduardo Coelho","raw_affiliation_strings":["ALGORITMI Research Centre/LASI, University of Minho, 4800-058, Guimar\u00e3es, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ALGORITMI Research Centre/LASI, University of Minho, 4800-058, Guimar\u00e3es, Portugal","institution_ids":["https://openalex.org/I99682543"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021564927","display_name":"Nuno Pimenta","orcid":"https://orcid.org/0000-0001-8232-6466"},"institutions":[{"id":"https://openalex.org/I99682543","display_name":"University of Minho","ror":"https://ror.org/037wpkx04","country_code":"PT","type":"education","lineage":["https://openalex.org/I99682543"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Nuno Pimenta","raw_affiliation_strings":["ALGORITMI Research Centre/LASI, University of Minho, 4800-058, Guimar\u00e3es, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ALGORITMI Research Centre/LASI, University of Minho, 4800-058, Guimar\u00e3es, Portugal","institution_ids":["https://openalex.org/I99682543"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054879737","display_name":"Dalila Dur\u00e3es","orcid":"https://orcid.org/0000-0002-8313-7023"},"institutions":[{"id":"https://openalex.org/I99682543","display_name":"University of Minho","ror":"https://ror.org/037wpkx04","country_code":"PT","type":"education","lineage":["https://openalex.org/I99682543"]}],"countries":["PT"],"is_corresponding":true,"raw_author_name":"Dalila Dur\u00e3es","raw_affiliation_strings":["ALGORITMI Research Centre/LASI, University of Minho, 4800-058, Guimar\u00e3es, Portugal"],"raw_orcid":"https://orcid.org/0000-0002-8313-7023","affiliations":[{"raw_affiliation_string":"ALGORITMI Research Centre/LASI, University of Minho, 4800-058, Guimar\u00e3es, Portugal","institution_ids":["https://openalex.org/I99682543"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016100261","display_name":"Victor Alves","orcid":"https://orcid.org/0000-0003-1819-7051"},"institutions":[{"id":"https://openalex.org/I99682543","display_name":"University of Minho","ror":"https://ror.org/037wpkx04","country_code":"PT","type":"education","lineage":["https://openalex.org/I99682543"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Victor Alves","raw_affiliation_strings":["ALGORITMI Research Centre/LASI, University of Minho, 4800-058, Guimar\u00e3es, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ALGORITMI Research Centre/LASI, University of Minho, 4800-058, Guimar\u00e3es, Portugal","institution_ids":["https://openalex.org/I99682543"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026706868","display_name":"L. Bandeira","orcid":"https://orcid.org/0000-0002-4432-8513"},"institutions":[{"id":"https://openalex.org/I4210122709","display_name":"Hospital de Santa Cruz","ror":"https://ror.org/02r581p42","country_code":"PT","type":"healthcare","lineage":["https://openalex.org/I4210122709"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Louren\u00e7o Bandeira","raw_affiliation_strings":["Schr\u00e9der Hyperion, Carnaxide, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Schr\u00e9der Hyperion, Carnaxide, Portugal","institution_ids":["https://openalex.org/I4210122709"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011826531","display_name":"Jos\u00e9 Machado","orcid":"https://orcid.org/0000-0003-4121-6169"},"institutions":[{"id":"https://openalex.org/I99682543","display_name":"University of Minho","ror":"https://ror.org/037wpkx04","country_code":"PT","type":"education","lineage":["https://openalex.org/I99682543"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Jos\u00e9 Machado","raw_affiliation_strings":["ALGORITMI Research Centre/LASI, University of Minho, 4800-058, Guimar\u00e3es, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ALGORITMI Research Centre/LASI, University of Minho, 4800-058, Guimar\u00e3es, Portugal","institution_ids":["https://openalex.org/I99682543"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048119697","display_name":"Paulo Nov\u00e1is","orcid":"https://orcid.org/0000-0002-3549-0754"},"institutions":[{"id":"https://openalex.org/I99682543","display_name":"University of Minho","ror":"https://ror.org/037wpkx04","country_code":"PT","type":"education","lineage":["https://openalex.org/I99682543"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Paulo Novais","raw_affiliation_strings":["ALGORITMI Research Centre/LASI, University of Minho, 4800-058, Guimar\u00e3es, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ALGORITMI Research Centre/LASI, University of Minho, 4800-058, Guimar\u00e3es, Portugal","institution_ids":["https://openalex.org/I99682543"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031794649","display_name":"Pedro Melo\u2010Pinto","orcid":"https://orcid.org/0000-0001-8257-0143"},"institutions":[{"id":"https://openalex.org/I155381812","display_name":"University of Tr\u00e1s-os-Montes and Alto Douro","ror":"https://ror.org/03qc8vh97","country_code":"PT","type":"education","lineage":["https://openalex.org/I155381812"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Pedro Melo-Pinto","raw_affiliation_strings":["CITAB, Universidade de Tr\u00e1s-os-Montes e Alto Douro, 5000-801, Vila Real, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CITAB, Universidade de Tr\u00e1s-os-Montes e Alto Douro, 5000-801, Vila Real, Portugal","institution_ids":["https://openalex.org/I155381812"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5054879737"],"corresponding_institution_ids":["https://openalex.org/I99682543"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":{"value":2990,"currency":"USD","value_usd":2990},"fwci":2.729,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.91322877,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"37","issue":"29","first_page":"23799","last_page":"23810"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9991999864578247,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9991999864578247,"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":0.9988999962806702,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9970999956130981,"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/computational-science-and-engineering","display_name":"Computational Science and Engineering","score":0.8707500696182251},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7444517016410828},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.731643557548523},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6682976484298706},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.654847264289856},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5160927176475525},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5083860754966736},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5055210590362549},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.4957629144191742},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4673483967781067},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43049243092536926},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.42316073179244995},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4163004159927368}],"concepts":[{"id":"https://openalex.org/C68597687","wikidata":"https://www.wikidata.org/wiki/Q362601","display_name":"Computational Science and Engineering","level":2,"score":0.8707500696182251},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7444517016410828},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.731643557548523},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6682976484298706},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.654847264289856},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5160927176475525},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5083860754966736},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5055210590362549},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4957629144191742},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4673483967781067},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43049243092536926},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.42316073179244995},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4163004159927368},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s00521-025-11521-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-025-11521-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-025-11521-x.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"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":"Neural Computing and Applications","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s00521-025-11521-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-025-11521-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-025-11521-x.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"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":"Neural Computing and Applications","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7949088935","display_name":"ALGORITMI Research Center","funder_award_id":"UIDB/00319/2020","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"}],"funders":[{"id":"https://openalex.org/F4320325399","display_name":"Universidade do Minho","ror":null},{"id":"https://openalex.org/F4320334779","display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","ror":"https://ror.org/00snfqn58"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4413912213.pdf","grobid_xml":"https://content.openalex.org/works/W4413912213.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W1689977300","https://openalex.org/W1861492603","https://openalex.org/W2031489346","https://openalex.org/W2102605133","https://openalex.org/W2151103935","https://openalex.org/W2164598857","https://openalex.org/W2229637417","https://openalex.org/W2619383789","https://openalex.org/W2763148304","https://openalex.org/W2916052001","https://openalex.org/W2963516811","https://openalex.org/W2980698950","https://openalex.org/W4281996560","https://openalex.org/W4317496152","https://openalex.org/W4381251438","https://openalex.org/W4386076325","https://openalex.org/W4386230809"],"related_works":["https://openalex.org/W4375867731","https://openalex.org/W4393232657","https://openalex.org/W2949096641","https://openalex.org/W2970686063","https://openalex.org/W4320729701","https://openalex.org/W4254103348","https://openalex.org/W3210378990","https://openalex.org/W3034745255","https://openalex.org/W3048601286","https://openalex.org/W2965925734"],"abstract_inverted_index":{"Abstract":[0],"Object":[1],"detection":[2,109,171],"is":[3],"one":[4],"of":[5,36,59,68,81,86,93],"the":[6,13,34,69,79,82,156],"most":[7],"fundamental":[8],"problems":[9],"to":[10,54,64],"tackle":[11],"in":[12,20,33,173],"computer":[14],"vision":[15],"research":[16],"area.":[17],"Recent":[18],"advances":[19],"multimodal":[21,37,75,169],"data":[22],"streams":[23],"and":[24,56,62,91,118,127,136],"deep":[25],"learning":[26,76],"architectures":[27],"have":[28],"prompted":[29],"a":[30,74,103,148,163],"fast":[31],"growth":[32],"field":[35],"learning,":[38],"which":[39],"brings":[40],"several":[41,167],"advantages":[42],"over":[43],"single-modality":[44],"approaches":[45],"for":[46,107,166],"object":[47,108,170],"detection,":[48],"such":[49,94],"as":[50,162],"improved":[51],"accuracy,":[52],"robustness":[53],"noise":[55],"ambiguity,":[57],"handling":[58],"complex":[60],"scenarios":[61],"adaptability":[63],"diverse":[65],"data.":[66],"Some":[67],"biggest":[70],"challenges":[71],"when":[72],"implementing":[73],"approach":[77],"are":[78,141],"selection":[80],"fusion":[83,105],"strategy,":[84],"design":[85],"processing":[87],"architecture,":[88],"modality":[89],"alignment/synchronization":[90],"interpretability":[92],"high-dimensional":[95],"representations.":[96],"To":[97],"address":[98],"this":[99],"challenge,":[100],"we":[101],"propose":[102],"feature-level":[104],"architecture":[106,158],"based":[110],"on":[111],"extracting":[112],"YOLO":[113],"features":[114,120],"from":[115,121,130],"images,":[116],"spectral":[117],"rhythm":[119],"sound":[122],"using":[123],"Mel-frequency":[124],"cepstral":[125],"coefficients,":[126],"general":[128],"descriptors":[129],"radar":[131],"modalities":[132],"that,":[133],"after":[134],"timestamp":[135],"homography":[137],"transformation":[138],"matrix":[139],"alignment,":[140],"combined":[142],"with":[143],"an":[144],"attention":[145],"mechanism":[146],"into":[147],"single":[149],"classification":[150],"network.":[151],"Preliminary":[152],"experiments":[153],"indicate":[154],"that":[155],"proposed":[157],"can":[159],"constitute":[160],"itself":[161],"base":[164],"pipeline":[165],"different":[168],"tasks":[172],"real-world":[174],"applications.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":5}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}
