{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,7]],"date-time":"2026-11-07T11:42:39Z","timestamp":1794051759007,"version":"4.8.0"},"reference-count":188,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"16","license":[{"start":{"date-parts":[[2025,8,15]],"date-time":"2025-08-15T00:00:00Z","timestamp":1755216000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,8,15]],"date-time":"2025-08-15T00:00:00Z","timestamp":1755216000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,15]],"date-time":"2025-08-15T00:00:00Z","timestamp":1755216000000},"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":["IEEE Internet Things J."],"published-print":{"date-parts":[[2025,8,15]]},"DOI":"10.1109\/jiot.2025.3579032","type":"journal-article","created":{"date-parts":[[2025,6,12]],"date-time":"2025-06-12T13:43:51Z","timestamp":1749735831000},"page":"32701-32724","source":"Crossref","is-referenced-by-count":66,"title":["Vision-Language Models for Edge Networks: A Comprehensive Survey"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2280-5240","authenticated-orcid":false,"given":"Ahmed","family":"Sharshar","sequence":"first","affiliation":[{"name":"Computer Vision Department, Mohamed Bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7678-6949","authenticated-orcid":false,"given":"Latif U.","family":"Khan","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Information Technology, Abu Dhabi University, Abu Dhabi, UAE"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5191-9023","authenticated-orcid":false,"given":"Waseem","family":"Ullah","sequence":"additional","affiliation":[{"name":"Machine Learning Department, Mohamed Bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8972-8094","authenticated-orcid":false,"given":"Mohsen","family":"Guizani","sequence":"additional","affiliation":[{"name":"Machine Learning Department, Mohamed Bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","author":"Lu","year":"2019","journal-title":"arXiv:1908.02265"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref3","first-page":"5583","article-title":"VILT: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IOTM.001.2300078"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2946140"},{"key":"ref6","first-page":"1","article-title":"Lite transformer with long-short range attention","volume-title":"Proc. Int. Conf. Learn. Rep.","author":"Wu"},{"key":"ref7","volume-title":"Pushing large language models to the 6G edge: Vision, challenges, and opportunities.","author":"Lin","year":"2023"},{"key":"ref8","volume-title":"EfficientVLM: Fast and accurate vision-language models via knowledge distillation and modal-adaptive pruning.","author":"Wang","year":"2022"},{"key":"ref9","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding","author":"Han","year":"2016","journal-title":"arXiv:1510.00149"},{"key":"ref10","first-page":"2704","article-title":"Quantization and training of neural networks for efficient integer-arithmetic-only inference","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Jacob"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1503.02531"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2761740"},{"key":"ref13","article-title":"Edge TPU: State-of-the-art AI at the edge","author":"Reddi","year":"2020","journal-title":"arXiv:2005.04268"},{"issue":"1","key":"ref14","first-page":"291","article-title":"Deep learning for autonomous driving: Techniques and applications","volume":"21","author":"Chen","year":"2019","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"12","key":"ref15","first-page":"3456","article-title":"Real-time human activity recognition with miniaturized wearable sensors using deep learning","volume":"20","author":"Wang","year":"2020","journal-title":"Sensors"},{"key":"ref16","article-title":"EfficientNetV2: Smaller models and faster training","author":"Tan","year":"2021","journal-title":"arXiv:2104.00298"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/2699343.2699349"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"ref19","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Brown"},{"key":"ref20","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"issue":"5","key":"ref21","first-page":"8972389","article-title":"Internet of Things (IoT) for next-generation smart systems: A review of current challenges, future trends and prospects for emerging 5G-IoT scenarios","volume":"7","author":"Zanella","year":"2020","journal-title":"IEEE Internet Things J."},{"key":"ref22","first-page":"82554","article-title":"Hardware acceleration for machine learning inference on edge devices: A review","volume":"8","author":"Zhang","year":"2020","journal-title":"IEEE Access"},{"issue":"5","key":"ref23","first-page":"1719","article-title":"Cloud and edge computing for deep learning applications","volume":"32","author":"Chen","year":"2021","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00293"},{"key":"ref25","article-title":"Slimmable neural networks","author":"Yu","year":"2019","journal-title":"arXiv:1812.08928"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref27","first-page":"160543","article-title":"Transformer-based model for text classification and question answering","volume":"8","author":"Chen","year":"2020","journal-title":"IEEE Access"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1038\/nature21056"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-018-0300-7"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.l007\/978-3-319-46448-0_2"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/762"},{"key":"ref35","volume-title":"Vision-language intelligence: Tasks, representation learning, and large models.","author":"Li","year":"2022"},{"key":"ref36","doi-asserted-by":"crossref","DOI":"10.1016\/j.cag.2024.01.012","article-title":"A survey of efficient fine-tuning methods for vision-language models\u2014A prompt and adapter","volume":"119","author":"Xing","year":"2024","journal-title":"Comput. Graph."},{"key":"ref37","volume-title":"Exploring the frontier of vision-language models: A survey of current methodologies and future directions.","author":"Ghosh","year":"2024"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00106"},{"key":"ref40","doi-asserted-by":"crossref","DOI":"10.1093\/nsr\/nwae403","volume-title":"A survey on multimodal large language models.","author":"Yin","year":"2024"},{"key":"ref41","article-title":"Efficient multimodal large language models: A survey","author":"Jin","year":"2024","journal-title":"arXiv:2405.10739"},{"key":"ref42","article-title":"Artificial intelligence market by offering, technology, end-user industry and geography\u2014Global forecast to 2026","volume-title":"MarketsandMarkets","year":"2021"},{"key":"ref43","volume-title":"Design choices for vision language models in 2024.","author":"Gigant","year":"2024"},{"key":"ref44","volume-title":"Edge ai hardware market by device type, processor type, end user, and application: Global opportunity analysis and industry forecast, 2018\u20132025.","year":"2024"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref46","article-title":"VisualBert: A simple and performant baseline for vision and language","author":"Li","year":"2019","journal-title":"arXiv:1908.03557"},{"key":"ref47","article-title":"VL-bert: Pre-training of generic visual-linguistic representations","author":"Su","year":"2019","journal-title":"arXiv:1908.08530"},{"key":"ref48","article-title":"MobileVLM V2: Faster and stronger baseline for vision language model","author":"Liu","year":"2024","journal-title":"arXiv:2402.03766"},{"key":"ref49","volume-title":"Unified-IO: A unified model for vision, language, and multi-modal tasks.","author":"Lu","year":"2022"},{"key":"ref50","first-page":"1","article-title":"LightVLP: A lightweight vision-language pre-training via gated interactive masked autoencoders","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Xu"},{"key":"ref51","article-title":"XModel-VLM: A simple baseline for multimodal vision language model","author":"Li","year":"2024","journal-title":"arXiv:2405.09215"},{"key":"ref52","article-title":"EM-VLM4AD: Multi-frame, lightweight & efficient vision-language models for question answering in autonomous driving","author":"Wu","year":"2024","journal-title":"arXiv:2403.19838"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01231"},{"key":"ref54","volume-title":"Driving with language: Introducing Wayve\u2019s multimodal driving model lingo-2.","author":"AI","year":"2024"},{"key":"ref55","volume-title":"InstructBLIP: Towards general-purpose vision-language models with instruction tuning.","author":"Dai","year":"2024"},{"key":"ref56","article-title":"Raven: Multitask retrieval augmented vision-language learning","author":"Kumar","year":"2024","journal-title":"arXiv:2406.19150"},{"key":"ref57","article-title":"ScreenAI: A vision-language model for UI and infographics understanding","author":"AI","year":"2024","journal-title":"arXiv:2405.09215"},{"key":"ref58","volume-title":"Allava: Harnessing GPT4V-synthesized data for lite vision-language models.","author":"Chen","year":"2024"},{"key":"ref59","article-title":"MiniVLM: A smaller and faster vision-language model","author":"Wang","year":"2020","journal-title":"arXiv:2012.06946"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.629"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref65","article-title":"P-tuning V2: Prompt tuning can be comparable to fine-tuning universally across scales and tasks","author":"Liu","year":"2021","journal-title":"arXiv:2110.07602"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01755"},{"key":"ref67","article-title":"PRODA: Prompt distribution learning for efficient and effective fine-tuning of pre-trained models","author":"Wang","year":"2021","journal-title":"arXiv:2111.12434"},{"key":"ref68","article-title":"Parameter-efficient transfer learning for NLP","author":"Houlsby","year":"2019","journal-title":"arXiv:1902.00751"},{"key":"ref69","article-title":"LoRa: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv:2106.09685"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.39"},{"key":"ref71","article-title":"VL-adapter: Parameter-efficient transfer learning for vision-and-language tasks","author":"Sung","year":"2021","journal-title":"arXiv:2106.01558"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73390-1_18"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICC51166.2024.10623069"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.3390\/fi13050118"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2015.10.005"},{"key":"ref77","volume-title":"Applications of Security, Mobile, Analytic and Cloud (SMAC) Technologies for Effective Information Processing and Management","author":"Karthikeyan","year":"2019"},{"issue":"2","key":"ref78","first-page":"77","article-title":"Edge cloud computing technologies for Internet of Things: A primer","volume":"4","author":"Shiyun","year":"2021","journal-title":"Digit. Commun. Netw."},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2990292"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2019.2918437"},{"key":"ref81","doi-asserted-by":"crossref","DOI":"10.1109\/JIOT.2024.3470210","volume-title":"Efficient prompting for LLM-based generative Internet of Things.","author":"Xiao","year":"2024"},{"key":"ref82","volume-title":"LLMIND: Orchestrating AI and IoT with LLM for complex task execution.","author":"Cui","year":"2024"},{"key":"ref83","volume-title":"Tiny VLMs bring AI text plus image vision to the edge.","year":"2024"},{"key":"ref84","volume-title":"VILA: On pre-training for visual language models.","author":"Lin","year":"2024"},{"key":"ref85","article-title":"Edge-LLM: Enabling efficient large language model adaptation on edge devices","author":"Yu","year":"2024","journal-title":"arXiv:2406.15758"},{"key":"ref86","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52688.2022.01185","volume-title":"Patch slimming for efficient vision transformers.","author":"Tang","year":"2022"},{"key":"ref87","volume-title":"Data selection for efficient model update in federated learning.","author":"Shi","year":"2021"},{"issue":"16","key":"ref88","doi-asserted-by":"crossref","first-page":"3157","DOI":"10.3390\/electronics13163157","article-title":"A systematic literature review on the use of federated learning and bioinspired computing","volume":"13","author":"de Souza","year":"2024","journal-title":"Electronics"},{"issue":"11","key":"ref89","doi-asserted-by":"crossref","first-page":"2135","DOI":"10.3390\/electronics13112135","article-title":"Enhancing edge-assisted federated learning with asynchronous aggregation and cluster pairing","volume":"13","author":"Sha","year":"2024","journal-title":"Electronics"},{"issue":"16","key":"ref90","doi-asserted-by":"crossref","first-page":"3154","DOI":"10.3390\/electronics13163154","article-title":"A multi-dimensional reverse auction mechanism for volatile federated learning in the mobile edge computing systems","volume":"13","author":"Hong","year":"2024","journal-title":"Electronics"},{"key":"ref91","volume-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications.","author":"Howard","year":"2017"},{"key":"ref92","first-page":"4510","article-title":"MobileNetV2: Inverted residuals and linear bottlenecks","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Sandler"},{"key":"ref93","first-page":"770","article-title":"Deep residual learning for image recognition","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"He"},{"key":"ref94","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. Conf. North Amer. Assoc. Comput. Linguist. (NAACL)","author":"Devlin"},{"issue":"55","key":"ref95","first-page":"1","article-title":"Neural architecture search: A survey","volume":"20","author":"Elsken","year":"2019","journal-title":"J. Mach. Learn. Res."},{"key":"ref96","volume-title":"Large batch training of convolutional networks.","author":"You","year":"2017"},{"key":"ref97","volume-title":"Expanding the reach of federated learning by reducing client resource requirements.","author":"Caldas","year":"2018"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.62836\/jitp.v1i1.156"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.107"},{"key":"ref100","article-title":"Combining compressions for multiplicative size scaling on natural language tasks","author":"Movva","year":"2022","journal-title":"arXiv:2208.09684"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-short.22"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1561\/2200000083"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1145\/3298981"},{"key":"ref104","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proc. 20th Int. Conf. Artif. Intell. Stat. (AISTATS)","author":"McMahan"},{"issue":"9","key":"ref105","doi-asserted-by":"crossref","first-page":"3400","DOI":"10.1109\/TNNLS.2019.2944481","article-title":"Robust and communication-efficient federated learning from non-IID data","volume":"31","author":"Sattler","year":"2020","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref106","first-page":"4427","article-title":"Federated multi-task learning","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Smith"},{"key":"ref107","first-page":"7252","article-title":"Bayesian nonparametric federated learning of neural networks","volume-title":"Proc. 36th Int. Conf. Mach. Learn. (ICML)","author":"Yurochkin"},{"key":"ref108","volume-title":"Federated optimization: Distributed machine learning for on-device intelligence.","author":"Konecn\u00fd","year":"2016"},{"key":"ref109","article-title":"LDP-FL: Practical private aggregation in federated learning with local differential privacy","author":"Truex","year":"2020","journal-title":"arXiv:2005.13129"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1145\/3133956.3133982"},{"key":"ref111","volume-title":"OpenFHE: Open-source fully homomorphic encryption library.","author":"Team","year":"2022"},{"issue":"2","key":"ref112","first-page":"1751","article-title":"Towards edge-based federated learning: A systematic survey","volume":"19","author":"Yao","year":"2022","journal-title":"IEEE Trans. Netw. Service Manag."},{"issue":"4","key":"ref113","first-page":"247","article-title":"Edge-based continual learning: Achieving privacy-preserving, fast, and accurate model adaptation","volume":"35","author":"Wang","year":"2021","journal-title":"IEEE Netw."},{"key":"ref114","first-page":"10132","article-title":"Federated meta-learning: Concept and applications","volume-title":"Proc. 35th Int. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Li"},{"issue":"3","key":"ref115","first-page":"1457","article-title":"Federated evaluation: A unified framework for privacy-preserving model evaluation","volume":"19","author":"Xu","year":"2022","journal-title":"IEEE Trans. Depend. Secure Comput."},{"issue":"11","key":"ref116","first-page":"5234","article-title":"Federated hyperparameter tuning with Bayesian optimization","volume":"51","author":"Zhang","year":"2021","journal-title":"IEEE Trans. Cybern."},{"issue":"2","key":"ref117","first-page":"312","article-title":"Continuous federated learning with dynamic client participation","volume":"35","author":"Liu","year":"2024","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"3","key":"ref118","first-page":"478","article-title":"Sparse federated learning: Reducing communication overhead for edge computing","volume":"35","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"issue":"1","key":"ref119","first-page":"112","article-title":"Orchestrated edge deployment for federated learning in heterogeneous environments","volume":"23","author":"Wang","year":"2024","journal-title":"IEEE Trans. Mobile Comput."},{"issue":"5","key":"ref120","first-page":"2789","article-title":"Adaptive federated learning in resource-constrained environments","volume":"11","author":"Chen","year":"2024","journal-title":"IEEE Internet Things J."},{"key":"ref121","first-page":"12","article-title":"KubeFL: A kubernetes-based federated learning framework for scalable edge computing","volume":"167","author":"Xu","year":"2023","journal-title":"J. Parallel Distrib. Comput."},{"issue":"2","key":"ref122","first-page":"324","article-title":"Federated continual learning: Advances and challenges","volume":"9","author":"Yao","year":"2024","journal-title":"IEEE Trans. Emerg. Topics Comput."},{"key":"ref123","first-page":"1123","article-title":"Reinforcement learning in federated learning systems: A survey","volume":"12","author":"Zhu","year":"2024","journal-title":"IEEE Access"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3315673"},{"key":"ref125","doi-asserted-by":"crossref","DOI":"10.1561\/9781638281337","volume-title":"Vision-language pre-training: Basics, recent advances, and future trends.","author":"Gan","year":"2022"},{"key":"ref126","volume-title":"Bimedix: Bilingual medical mixture of experts LLM.","author":"Pieri","year":"2024"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-demo.3"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-96-0908-6_6"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.32604\/cmc.2021.018671"},{"key":"ref130","article-title":"Customizing general-purpose foundation models for medical report generation","volume-title":"arxiv.abs\/2306.05642","author":"Yang","year":"2023"},{"key":"ref131","volume-title":"Geollava: Efficient fine-tuned vision-language models for temporal change detection in remote sensing.","author":"Elgendy","year":"2024"},{"key":"ref132","volume-title":"Satin: A multi-task metadataset for classifying satellite imagery using vision-language models.","author":"Roberts","year":"2023"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01411"},{"key":"ref134","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1016\/j.isprsjprs.2024.01.004","article-title":"Changeclip: Remote sensing change detection with multimodal vision-language representation learning","volume":"208","author":"Dong","year":"2024","journal-title":"ISPRS J. Photogrammetry Remote Sens."},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3192460"},{"key":"ref136","article-title":"Vision language models in autonomous driving and intelligent transportation systems","author":"Zhou","year":"2023","journal-title":"arxiv.abs\/2310.14414"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i8.32902"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.3233\/SCS-220010"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3276172"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1145\/3486611.3491133"},{"key":"ref141","article-title":"Vision-language models in remote sensing: Current progress and future trends","author":"Wen","year":"2023","journal-title":"arxiv.abs\/2305.05726"},{"key":"ref142","article-title":"Vision-language models as success detectors","author":"Du","year":"2023","journal-title":"arxiv.abs\/2303.07280"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01040"},{"key":"ref144","volume-title":"MoonDream2: A tiny vision-language model for edge devices.","author":"Vikhyat","year":"2024"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAE59995.2024.10569285"},{"key":"ref146","volume-title":"Visual Language Intelligence and Edge AI 2.0","author":"Lu","year":"2024"},{"key":"ref147","volume-title":"Mobile edge intelligence for large language models: A contemporary survey.","author":"Qu","year":"2024"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1109\/IWCMC61514.2024.10592339"},{"key":"ref149","volume-title":"Towards edge general intelligence via large language models: Opportunities and challenges.","author":"Chen","year":"2024"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-024-01312-0"},{"key":"ref151","volume-title":"DIME-FM: Distilling multimodal and efficient foundation models.","author":"Sun","year":"2023"},{"key":"ref152","volume-title":"EdgeVL: Self-adapting large visual-language models to edge devices.","year":"2024"},{"key":"ref153","volume-title":"Adapting vision-language models for edge devices.","author":"Science","year":"2024"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2025.3579032"},{"key":"ref155","article-title":"Federated prompt learning for vision-language models","author":"Luo","year":"2024","journal-title":"arXiv:2410.10114"},{"key":"ref156","article-title":"Mixture of experts made personalized: Federated prompt learning for vision-language models","author":"Luo","year":"2024","journal-title":"arXiv:2410.10114"},{"key":"ref157","article-title":"FLORA: Enhancing vision-language models with parameter-efficient federated learning","author":"Nguyen","year":"2024","journal-title":"arXiv:2404.15182"},{"key":"ref158","article-title":"Federated learning from vision-language foundation models","author":"Pan","year":"2024","journal-title":"arXiv:2409.19610"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72633-0_13"},{"key":"ref160","volume-title":"Multi-frame, lightweight & efficient vision-language models for question answering in autonomous driving.","author":"Gopalkrishnan","year":"2024"},{"key":"ref161","first-page":"1","article-title":"Litevila: A lightweight vision-language model for scene understanding in autonomous driving","volume-title":"Proc. ECCV Workshop W-CODA","author":"Cheng"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.3390\/drones7020114"},{"issue":"2","key":"ref163","first-page":"22","article-title":"Edge-assisted object segmentation using multimodal feature fusion","volume":"19","author":"Liu","year":"2023","journal-title":"ACM Trans Sensor Netw."},{"key":"ref164","volume-title":"DynAFuse: Dynamic fusion for resource efficient multi-modal machine learning inference.","author":"Alikhani","year":"2023"},{"issue":"4","key":"ref165","doi-asserted-by":"crossref","first-page":"804","DOI":"10.3390\/electronics14040804","article-title":"Few-shot learning with multimodal fusion for efficient cloud-edge collaborative mmWave beam selection","volume":"14","author":"Zhang","year":"2025","journal-title":"Electronics"},{"key":"ref166","article-title":"Unraveling cross-modality knowledge conflicts in large vision-language models","author":"Zhu","year":"2024","journal-title":"arXiv:2410.03659"},{"key":"ref167","first-page":"1","article-title":"Visual prompt multi-modal tracking","volume-title":"Proc. Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Cheng"},{"key":"ref168","volume-title":"Cross-modality fusion for depth prediction via RGB and thermal data.","author":"","year":"2023"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1145\/3592800"},{"key":"ref170","volume-title":"Boosting model inversion attacks with adversarial examples.","author":"Zhou","year":"2023"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547801"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1109\/CSR51186.2021.9527945"},{"key":"ref173","volume-title":"A formal model for secure multiparty computation.","author":"Rathore","year":"2023"},{"key":"ref174","volume-title":"Set-level guidance attack: Boosting adversarial transferability of vision-language pre-training models.","author":"Lu","year":"2023"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.3390\/app12020734"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.3390\/fi13040094"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.1109\/NaNA60121.2023.00084"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.47667\/ijpasr.v4i3.235"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.1109\/ICTC55196.2022.9952531"},{"key":"ref180","doi-asserted-by":"publisher","DOI":"10.1002\/int.22818"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/8380239"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1109\/PST58708.2023.10320195"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1002\/ett.4648"},{"key":"ref184","doi-asserted-by":"publisher","DOI":"10.14778\/3476249.3476302"},{"key":"ref185","volume-title":"Energy-efficient task adaptation for NLP edge inference leveraging heterogeneous memory architectures.","author":"Fu","year":"2023"},{"key":"ref186","volume-title":"Pipeline parallelism for inference on heterogeneous edge computing","author":"Hu","year":"2021"},{"key":"ref187","volume-title":"Devit: Decomposing vision transformers for collaborative inference in edge devices.","author":"Xu","year":"2023"},{"key":"ref188","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-45170-6_5","volume-title":"Search-time efficient device constraints-aware neural architecture search.","author":"Dutta","year":"2023"}],"container-title":["IEEE Internet of Things Journal"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6488907\/11121332\/11032085.pdf?arnumber=11032085","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,11]],"date-time":"2025-08-11T17:45:04Z","timestamp":1754934304000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11032085\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,15]]},"references-count":188,"journal-issue":{"issue":"16"},"URL":"https:\/\/doi.org\/10.1109\/jiot.2025.3579032","relation":{},"ISSN":["2327-4662","2372-2541"],"issn-type":[{"value":"2327-4662","type":"electronic"},{"value":"2372-2541","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,15]]}}}