{"id":"https://openalex.org/W7141383362","doi":"https://doi.org/10.1109/icce67443.2026.11449737","title":"Edge-Driven Semantic Fusion for Real-Time Image Captioning in IoT Environments","display_name":"Edge-Driven Semantic Fusion for Real-Time Image Captioning in IoT Environments","publication_year":2026,"publication_date":"2026-02-03","ids":{"openalex":"https://openalex.org/W7141383362","doi":"https://doi.org/10.1109/icce67443.2026.11449737"},"language":null,"primary_location":{"id":"doi:10.1109/icce67443.2026.11449737","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icce67443.2026.11449737","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE International Conference on Consumer Electronics (ICCE)","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/A5083952165","display_name":"Deema Abdal Hafeth","orcid":"https://orcid.org/0009-0009-6514-6426"},"institutions":[{"id":"https://openalex.org/I51532219","display_name":"University of Lincoln","ror":"https://ror.org/03yeq9x20","country_code":"GB","type":"education","lineage":["https://openalex.org/I51532219"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Deema Abdal Hafeth","raw_affiliation_strings":["University of Lincoln,School of Engineering and Physical Sciences,Lincoln,UK"],"affiliations":[{"raw_affiliation_string":"University of Lincoln,School of Engineering and Physical Sciences,Lincoln,UK","institution_ids":["https://openalex.org/I51532219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012570064","display_name":"Mohammed Al-Khafajiy","orcid":"https://orcid.org/0000-0001-6561-0414"},"institutions":[{"id":"https://openalex.org/I51532219","display_name":"University of Lincoln","ror":"https://ror.org/03yeq9x20","country_code":"GB","type":"education","lineage":["https://openalex.org/I51532219"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mohammed Al-Khafajiy","raw_affiliation_strings":["University of Lincoln,School of Engineering and Physical Sciences,Lincoln,UK"],"affiliations":[{"raw_affiliation_string":"University of Lincoln,School of Engineering and Physical Sciences,Lincoln,UK","institution_ids":["https://openalex.org/I51532219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006740551","display_name":"thar intisar baker","orcid":null},"institutions":[{"id":"https://openalex.org/I29891158","display_name":"University of Sharjah","ror":"https://ror.org/00engpz63","country_code":"AE","type":"education","lineage":["https://openalex.org/I29891158"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Thar Baker","raw_affiliation_strings":["University of Khorfakkan,College of Computing and Intelligent Systems,Sharjah,UAE"],"affiliations":[{"raw_affiliation_string":"University of Khorfakkan,College of Computing and Intelligent Systems,Sharjah,UAE","institution_ids":["https://openalex.org/I29891158"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5083952165"],"corresponding_institution_ids":["https://openalex.org/I51532219"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.94665365,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9743000268936157,"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":0.9743000268936157,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.011900000274181366,"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":0.003700000001117587,"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/closed-captioning","display_name":"Closed captioning","score":0.8673999905586243},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5023000240325928},{"id":"https://openalex.org/keywords/image-fusion","display_name":"Image fusion","score":0.42800000309944153},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4050999879837036},{"id":"https://openalex.org/keywords/internet-of-things","display_name":"Internet of Things","score":0.37310001254081726},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.3001999855041504}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8673999905586243},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6890000104904175},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5023000240325928},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46549999713897705},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4343999922275543},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.42800000309944153},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4050999879837036},{"id":"https://openalex.org/C81860439","wikidata":"https://www.wikidata.org/wiki/Q251212","display_name":"Internet of Things","level":2,"score":0.37310001254081726},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.3001999855041504},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.2948000133037567},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.28850001096725464},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.2815000116825104},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2768999934196472},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2750999927520752},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.27160000801086426}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icce67443.2026.11449737","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icce67443.2026.11449737","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE International Conference on Consumer Electronics (ICCE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W68733909","https://openalex.org/W2086402015","https://openalex.org/W2194775991","https://openalex.org/W2404750506","https://openalex.org/W2561529111","https://openalex.org/W2896225285","https://openalex.org/W2945179442","https://openalex.org/W2952132475","https://openalex.org/W2979739834","https://openalex.org/W2985451806","https://openalex.org/W3035284526","https://openalex.org/W3083395297","https://openalex.org/W3201095160","https://openalex.org/W4296340333","https://openalex.org/W4319594886","https://openalex.org/W4319659860","https://openalex.org/W4319777846","https://openalex.org/W4366721356","https://openalex.org/W4381325171","https://openalex.org/W4385572123","https://openalex.org/W4386361551","https://openalex.org/W4391108232","https://openalex.org/W4392649810","https://openalex.org/W4393035527","https://openalex.org/W4401164032","https://openalex.org/W4404056934"],"related_works":[],"abstract_inverted_index":{"Edge":[0],"computing":[1],"greatly":[2],"enhances":[3],"image":[4,11,50,73,85,141],"processing":[5],"in":[6,13,96,143],"IoT":[7,144],"applications,":[8],"particularly":[9],"for":[10,32,100,139],"captioning":[12],"smart":[14],"monitoring":[15],"systems.":[16],"While":[17],"encoder-decoder":[18],"and":[19,52,64,70,87,92,107,125,134],"attention-based":[20],"models":[21],"have":[22],"improved":[23],"caption":[24],"quality,":[25],"they":[26],"often":[27],"neglect":[28],"semantic":[29,45,53,65,93,140],"representations":[30],"crucial":[31],"deeper":[33],"visual":[34,63,90],"understanding.":[35],"To":[36],"address":[37],"this":[38],"gap,":[39],"we":[40],"propose":[41],"EdgeEye,":[42],"an":[43],"Edge-driven":[44],"fusion":[46],"framework":[47],"that":[48],"performs":[49],"analysis":[51],"feature":[54,102],"extraction":[55],"directly":[56],"at":[57],"the":[58,113],"data":[59],"source.":[60],"EdgeEye":[61,104],"combines":[62],"features":[66,83],"to":[67,79],"generate":[68],"richer":[69,106],"more":[71,108],"accurate":[72,109],"captions.":[74,110],"Its":[75],"architecture":[76],"is":[77],"designed":[78],"i)":[80],"learn":[81],"distinctive":[82],"from":[84],"regions":[86],"ii)":[88],"embed":[89],"attention":[91],"attributes":[94],"together":[95],"a":[97,120,126],"shared":[98],"space":[99],"effective":[101],"fusion.":[103],"generates":[105],"Experiments":[111],"on":[112],"Flickr8k":[114],"dataset":[115],"show":[116],"notable":[117],"gains,":[118],"achieving":[119],"CIDEr":[121],"score":[122,128],"of":[123,129],"44.6%":[124],"ROUGE-L":[127],"46.9%,":[130],"demonstrating":[131],"its":[132],"effectiveness":[133],"competitiveness":[135],"with":[136],"state-of-the-":[137],"art":[138],"understanding":[142],"environments.":[145]},"counts_by_year":[],"updated_date":"2026-03-29T06:01:01.467347","created_date":"2026-03-28T00:00:00"}