{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T15:29:07Z","timestamp":1785511747404,"version":"3.56.0"},"reference-count":61,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Major Key Project of PCL","award":["PCL2023A06"],"award-info":[{"award-number":["PCL2023A06"]}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022YFB3105000"],"award-info":[{"award-number":["2022YFB3105000"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Key Lab of Software Defined Networking","award":["ZDSYS20140509172959989"],"award-info":[{"award-number":["ZDSYS20140509172959989"]}]},{"name":"Research Ireland","award":["21\/FFP-P\/10244 (FRADIS)"],"award-info":[{"award-number":["21\/FFP-P\/10244 (FRADIS)"]}]},{"name":"Research Ireland","award":["12\/RC\/2289_P2 (INSIGHT)"],"award-info":[{"award-number":["12\/RC\/2289_P2 (INSIGHT)"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Broadcast."],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1109\/tbc.2025.3549983","type":"journal-article","created":{"date-parts":[[2025,4,2]],"date-time":"2025-04-02T21:36:21Z","timestamp":1743629781000},"page":"529-541","source":"Crossref","is-referenced-by-count":9,"title":["VaVLM: Toward Efficient Edge-Cloud Video Analytics With Vision-Language Models"],"prefix":"10.1109","volume":"71","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-5847-9615","authenticated-orcid":false,"given":"Yang","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Optoelectronic Engineering, Xi’an Technological University, Xi’an, Shaanxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8463-5211","authenticated-orcid":false,"given":"Hanling","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Advanced Interdisciplinary Research, Pengcheng Laboratory, Shenzhen, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qing","family":"Bai","sequence":"additional","affiliation":[{"name":"Department of Quality Safety, Northern Optoelectronics Company Ltd. (NORTHEO), Xi’an, Shaanxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7088-250X","authenticated-orcid":false,"given":"Haifeng","family":"Liang","sequence":"additional","affiliation":[{"name":"School of Optoelectronic Engineering, Xi’an Technological University, Xi’an, Shaanxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8389-1093","authenticated-orcid":false,"given":"Peican","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Optics and Electronics, NWPU, Xi’an, Shaanxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9332-4770","authenticated-orcid":false,"given":"Gabriel-Miro","family":"Muntean","sequence":"additional","affiliation":[{"name":"School of Electronic Engineering, Dublin City University, Dublin 9, Ireland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6071-473X","authenticated-orcid":false,"given":"Qing","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Advanced Interdisciplinary Research, Pengcheng Laboratory, Shenzhen, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TBC.2024.3391051"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TBC.2022.3171131"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TBC.2008.2006252"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TBC.2023.3254165"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TBC.2020.2983298"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-019-07793-w"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-15628-2_15"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.3035044"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3300061.3300116"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2022.3181986"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MCG.2024.3381450"},{"key":"ref12","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3438155"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3570361.3592529"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2022.3221995"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3387514.3405887"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3447993.3483274"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3465434"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3385678"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2021.3125359"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2023.3281598"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TBC.2023.3345646"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/2809695.2809711"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3387514.3405874"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3447993.3448628"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_31"},{"key":"ref28","first-page":"34892","article-title":"Visual instruction tuning","volume-title":"Proc. 37th Conf. Neural Inf. Process. Syst.","volume":"36","author":"Liu"},{"key":"ref29","volume-title":"YOLOv8-ultralytics YOLO docs","year":"2024"},{"key":"ref30","article-title":"Comprehensive study on performance evaluation and optimization of model compression: Bridging traditional deep learning and large language models","author":"Saxena","year":"2024","journal-title":"arXiv:2407.15904"},{"key":"ref31","first-page":"37524","article-title":"Understanding INT4 quantization for language models: Latency speedup, composability, and failure cases","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wu"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72933-1_22"},{"key":"ref33","volume-title":"Hello GPT-4o","year":"2024"},{"key":"ref34","first-page":"1","article-title":"Image-to-word transformation based on dividing and vector quantizing images with words","volume-title":"Proc. 1st Int. Workshop Multimedia Intell. Storage Retrieval Manag.","author":"Mori"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383173"},{"key":"ref36","first-page":"2222","article-title":"Multimodal learning with deep Boltzmann machines","volume-title":"Proc. 26th Conf. Neural Inf. Process. Syst.","author":"Srivastava"},{"key":"ref37","first-page":"1","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref38","first-page":"13","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref39","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv:2302.13971"},{"key":"ref40","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv:2304.10592"},{"key":"ref41","article-title":"Instructblip: Towards general-purpose vision-language models with instruction tuning","author":"Dai","year":"2023","journal-title":"arXiv:2305.06500"},{"key":"ref42","article-title":"PandaGPT: One model to instruction-follow them all","author":"Su","year":"2023","journal-title":"arXiv:2305.16355"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM52122.2024.10621074"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3016485"},{"key":"ref45","first-page":"450","article-title":"AccMPEG: Optimizing video encoding for accurate video analytics","volume-title":"Proc. Mach. Learn. Syst.","author":"Du"},{"key":"ref46","first-page":"1","article-title":"Scaling video analytics on constrained edge nodes","volume-title":"Proc. Mach. Learn. Syst.","author":"Canel"},{"key":"ref47","first-page":"1","article-title":"Mainstream: Dynamic stem-sharing for multi-tenant video processing","volume-title":"Proc. USENIX Conf. Usenix Annu. Tech. Conf.","author":"Jiang"},{"key":"ref48","article-title":"Darts: Differentiable architecture search","author":"Liu","year":"2018","journal-title":"arXiv:1806.09055"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2024.3365949"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3230543.3230554"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3230543.3230574"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3372224.3380881"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796875"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-012-9338-y"},{"key":"ref55","volume-title":"iperf-the TCP, UDP and SCTP network bandwidth measurement tool","year":"2024"},{"key":"ref56","volume-title":"Socket low-level networking interface Python 3.13.0 documentation","year":"2024"},{"key":"ref57","first-page":"1","article-title":"Advancing video anomaly detection: A concise review and a new dataset","volume-title":"Proc. 8th Conf. Neural Inf. Process. Syst. Datasets Benchmarks Track","author":"Zhu"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00493"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM41043.2020.9155524"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3376769"},{"key":"ref61","volume-title":"Becayesoft\/guns-detection-yolov8: A computer vision model that detects guns using YOLOv8","year":"2024"}],"container-title":["IEEE Transactions on Broadcasting"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11\/11027897\/10947590.pdf?arnumber=10947590","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,10]],"date-time":"2025-06-10T05:11:10Z","timestamp":1749532270000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10947590\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":61,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tbc.2025.3549983","relation":{},"ISSN":["0018-9316","1557-9611"],"issn-type":[{"value":"0018-9316","type":"print"},{"value":"1557-9611","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6]]}}}