{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T06:43:31Z","timestamp":1774680211053,"version":"3.50.1"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T00:00:00Z","timestamp":1770076800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T00:00:00Z","timestamp":1770076800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,2,3]]},"DOI":"10.1109\/icce67443.2026.11449737","type":"proceedings-article","created":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T19:47:50Z","timestamp":1774640870000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Edge-Driven Semantic Fusion for Real-Time Image Captioning in IoT Environments"],"prefix":"10.1109","author":[{"given":"Deema Abdal","family":"Hafeth","sequence":"first","affiliation":[{"name":"University of Lincoln,School of Engineering and Physical Sciences,Lincoln,UK"}]},{"given":"Mohammed","family":"Al-Khafajiy","sequence":"additional","affiliation":[{"name":"University of Lincoln,School of Engineering and Physical Sciences,Lincoln,UK"}]},{"given":"Thar","family":"Baker","sequence":"additional","affiliation":[{"name":"University of Khorfakkan,College of Computing and Intelligent Systems,Sharjah,UAE"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.5398"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3109481"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2019.10.006"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/jiot.2024.3492066"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3390\/s24061796"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3390\/app13105948"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.32604\/csse.2023.035529"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3243725"},{"issue":"1","key":"ref9","first-page":"1","volume-title":"Cisco annual internet report (2018\u20132023) white paper","volume":"10","author":"Cisco","year":"2020"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/EDGE60047.2023.00062"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2019.05.015"},{"key":"ref12","volume-title":"A Fog Computing Approach for Cognitive, Reliable and Trusted Distributed Systems","author":"Al-Khafajiy","year":"2020"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/2789168.2790123"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/SEC.2018.00016"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0243243"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-016-1750-7"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01098"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref19","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","volume":"28","author":"Ren","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.107075"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.694"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICIVC55077.2022.9886239"},{"key":"ref23","article-title":"Clipcap: Clip prefix for image captioning","author":"Mokady","year":"2021"},{"key":"ref24","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref25","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning","author":"Li"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3268744"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11164"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3994"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CCAI61966.2024.10602893"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-024-18150-x"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-023-00693-9"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/DeSE60595.2023.10468995"}],"event":{"name":"2026 IEEE International Conference on Consumer Electronics (ICCE)","location":"Dubai, United Arab Emirates","start":{"date-parts":[[2026,2,3]]},"end":{"date-parts":[[2026,2,5]]}},"container-title":["2026 IEEE International Conference on Consumer Electronics (ICCE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11449575\/11449585\/11449737.pdf?arnumber=11449737","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T05:18:11Z","timestamp":1774675091000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11449737\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,3]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icce67443.2026.11449737","relation":{},"subject":[],"published":{"date-parts":[[2026,2,3]]}}}