{"id":"https://openalex.org/W7128547123","doi":"https://doi.org/10.1007/s11042-026-21192-y","title":"Multi-modal fusion for billboard categorization in video frames: A text and image-based approach","display_name":"Multi-modal fusion for billboard categorization in video frames: A text and image-based approach","publication_year":2026,"publication_date":"2026-02-09","ids":{"openalex":"https://openalex.org/W7128547123","doi":"https://doi.org/10.1007/s11042-026-21192-y"},"language":"en","primary_location":{"id":"doi:10.1007/s11042-026-21192-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11042-026-21192-y","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11042-026-21192-y.pdf","source":{"id":"https://openalex.org/S110206669","display_name":"Multimedia Tools and Applications","issn_l":"1380-7501","issn":["1380-7501","1573-7721"],"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":"Multimedia Tools 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/s11042-026-21192-y.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104633351","display_name":"Sukriti Dhang","orcid":"https://orcid.org/0000-0003-4025-5334"},"institutions":[{"id":"https://openalex.org/I100930933","display_name":"University College Dublin","ror":"https://ror.org/05m7pjf47","country_code":"IE","type":"education","lineage":["https://openalex.org/I100930933"]},{"id":"https://openalex.org/I168346926","display_name":"Science Foundation Ireland","ror":"https://ror.org/0271asj38","country_code":"IE","type":"nonprofit","lineage":["https://openalex.org/I168346926"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Sukriti Dhang","raw_affiliation_strings":["ADAPT SFI Research Centre, Dublin, Ireland","School of Computer Science, University College Dublin, Dublin, Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ADAPT SFI Research Centre, Dublin, Ireland","institution_ids":["https://openalex.org/I168346926"]},{"raw_affiliation_string":"School of Computer Science, University College Dublin, Dublin, Ireland","institution_ids":["https://openalex.org/I100930933"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125537811","display_name":"Jason Lok","orcid":null},"institutions":[{"id":"https://openalex.org/I100930933","display_name":"University College Dublin","ror":"https://ror.org/05m7pjf47","country_code":"IE","type":"education","lineage":["https://openalex.org/I100930933"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Jason Lok","raw_affiliation_strings":["School of Computer Science, University College Dublin, Dublin, Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, University College Dublin, Dublin, Ireland","institution_ids":["https://openalex.org/I100930933"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027322470","display_name":"Mimi Zhang","orcid":"https://orcid.org/0000-0002-3807-297X"},"institutions":[{"id":"https://openalex.org/I205274468","display_name":"Trinity College Dublin","ror":"https://ror.org/02tyrky19","country_code":"IE","type":"education","lineage":["https://openalex.org/I205274468"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Mimi Zhang","raw_affiliation_strings":["School of Computer Science and Statistics, Trinity College Dublin, Dublin, Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Statistics, Trinity College Dublin, Dublin, Ireland","institution_ids":["https://openalex.org/I205274468"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011772990","display_name":"Soumyabrata Dev","orcid":"https://orcid.org/0000-0002-0153-1095"},"institutions":[{"id":"https://openalex.org/I100930933","display_name":"University College Dublin","ror":"https://ror.org/05m7pjf47","country_code":"IE","type":"education","lineage":["https://openalex.org/I100930933"]},{"id":"https://openalex.org/I168346926","display_name":"Science Foundation Ireland","ror":"https://ror.org/0271asj38","country_code":"IE","type":"nonprofit","lineage":["https://openalex.org/I168346926"]},{"id":"https://openalex.org/I205274468","display_name":"Trinity College Dublin","ror":"https://ror.org/02tyrky19","country_code":"IE","type":"education","lineage":["https://openalex.org/I205274468"]}],"countries":["IE"],"is_corresponding":true,"raw_author_name":"Soumyabrata Dev","raw_affiliation_strings":["ADAPT SFI Research Centre, Dublin, Ireland","School of Computer Science and Statistics, Trinity College Dublin, Dublin, Ireland","School of Computer Science, University College Dublin, Dublin, Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ADAPT SFI Research Centre, Dublin, Ireland","institution_ids":["https://openalex.org/I168346926"]},{"raw_affiliation_string":"School of Computer Science and Statistics, Trinity College Dublin, Dublin, Ireland","institution_ids":["https://openalex.org/I205274468"]},{"raw_affiliation_string":"School of Computer Science, University College Dublin, Dublin, Ireland","institution_ids":["https://openalex.org/I100930933"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5011772990"],"corresponding_institution_ids":["https://openalex.org/I100930933","https://openalex.org/I168346926","https://openalex.org/I205274468"],"apc_list":{"value":2890,"currency":"USD","value_usd":2890},"apc_paid":{"value":2890,"currency":"USD","value_usd":2890},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16233733,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"85","issue":"2","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.28690001368522644,"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/T11439","display_name":"Video Analysis and Summarization","score":0.28690001368522644,"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":0.20800000429153442,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.09520000219345093,"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/categorization","display_name":"Categorization","score":0.7973999977111816},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6610999703407288},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4156999886035919},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.3986999988555908},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.39590001106262207},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.34779998660087585},{"id":"https://openalex.org/keywords/text-categorization","display_name":"Text categorization","score":0.32030001282691956}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9138000011444092},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.7973999977111816},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6610999703407288},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6424999833106995},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.43160000443458557},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4156999886035919},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4101000130176544},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.3986999988555908},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.39590001106262207},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.34779998660087585},{"id":"https://openalex.org/C2986744138","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Text categorization","level":3,"score":0.32030001282691956},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32010000944137573},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3075000047683716},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.3075000047683716},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.30480000376701355},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.30059999227523804},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2953999936580658},{"id":"https://openalex.org/C2982962833","wikidata":"https://www.wikidata.org/wiki/Q17092450","display_name":"Information fusion","level":2,"score":0.28870001435279846},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.26980000734329224},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s11042-026-21192-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11042-026-21192-y","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11042-026-21192-y.pdf","source":{"id":"https://openalex.org/S110206669","display_name":"Multimedia Tools and Applications","issn_l":"1380-7501","issn":["1380-7501","1573-7721"],"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":"Multimedia Tools and Applications","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s11042-026-21192-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11042-026-21192-y","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11042-026-21192-y.pdf","source":{"id":"https://openalex.org/S110206669","display_name":"Multimedia Tools and Applications","issn_l":"1380-7501","issn":["1380-7501","1573-7721"],"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":"Multimedia Tools and Applications","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320858","display_name":"University College Dublin","ror":"https://ror.org/05m7pjf47"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7128547123.pdf","grobid_xml":"https://content.openalex.org/works/W7128547123.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W2001642682","https://openalex.org/W2014545475","https://openalex.org/W2039203387","https://openalex.org/W2069539193","https://openalex.org/W2120452880","https://openalex.org/W2744024894","https://openalex.org/W2807036468","https://openalex.org/W2887955780","https://openalex.org/W2890416589","https://openalex.org/W2900875655","https://openalex.org/W2945551613","https://openalex.org/W2963037330","https://openalex.org/W2976072220","https://openalex.org/W3085804837","https://openalex.org/W4283711975","https://openalex.org/W4405318106","https://openalex.org/W4407826057"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Traditional":[1],"multimedia":[2],"classification":[3],"techniques":[4],"rely":[5],"on":[6],"analyzing":[7],"either":[8],"its":[9],"features":[10,34,55],"or":[11],"the":[12,40],"associated":[13],"annotated":[14],"textual":[15],"information.":[16],"In":[17],"this":[18],"paper,":[19],"we":[20],"introduce":[21],"a":[22,45,69],"technique":[23],"that":[24,50],"leverages":[25],"deep":[26],"learning":[27],"methodologies":[28],"to":[29,56],"extract":[30],"both":[31],"low-level":[32],"visual":[33],"and":[35,53,65,76,92],"high-level":[36],"semantic":[37],"information":[38],"from":[39],"billboard":[41],"images.":[42],"We":[43],"propose":[44],"multi-modal":[46],"hybrid":[47],"fusion":[48],"model":[49,82],"integrates":[51],"text":[52],"image":[54],"categorize":[57],"billboards":[58],"in":[59],"video":[60],"frames":[61],"into":[62],"food,":[63],"sports,":[64],"miscellaneous":[66],"categories.":[67],"Achieving":[68],"5%":[70],"accuracy":[71],"improvement":[72],"over":[73,78],"image-based":[74],"models":[75],"10%":[77],"text-based":[79],"models,":[80],"our":[81],"demonstrates":[83],"robust":[84],"generalization":[85],"across":[86],"diverse":[87],"datasets,":[88],"benefiting":[89],"advertising,":[90],"media,":[91],"content":[93],"creation":[94],"industries.":[95]},"counts_by_year":[],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2026-02-11T00:00:00"}