{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T05:44:39Z","timestamp":1782798279228,"version":"3.54.5"},"reference-count":46,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T00:00:00Z","timestamp":1779062400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T00:00:00Z","timestamp":1779062400000},"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":[[2026,5,18]]},"DOI":"10.1109\/infocom59046.2026.11571484","type":"proceedings-article","created":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T19:38:15Z","timestamp":1782761895000},"page":"1-10","source":"Crossref","is-referenced-by-count":0,"title":["MoVi: Real-Time Large Multimodal Model-Driven Interactive Video Analytics on Mobile Devices"],"prefix":"10.1109","author":[{"given":"Zekai","family":"Li","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoyi","family":"Fan","sequence":"additional","affiliation":[{"name":"Shenzhen MSU-BIT University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiping","family":"Hu","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yifei","family":"Zhu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2023.3323091"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3230543.3230574"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796875"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01742"},{"key":"ref6","article-title":"Advanced Voice Mode FAQ","year":"2024"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2017.3641638"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3754448"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3387514.3405874"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/jsac.2022.3221995"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM41043.2020.9155467"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3636534.3649359"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2024.3372046"},{"key":"ref14","article-title":"YouTube Recommended Upload Encoding Settings","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3230543.3230554"},{"key":"ref16","first-page":"450","article-title":"Accmpeg: Optimizing video encoding for accurate video analytics","volume-title":"Proceedings of Machine Learning and Systems","volume":"4","author":"Du"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3387514.3405887"},{"issue":"5","key":"ref18","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3706418","article-title":"Resource-efficient algorithms and systems of foundation models: A survey","volume":"57","author":"Xu","year":"2025","journal-title":"ACM Computing Surveys"},{"key":"ref19","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3376769"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3488"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2021.3087625"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2022.3161351"},{"key":"ref25","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref26","article-title":"Livevlm: Efficient online video understanding via streaming-oriented kv cache and retrieval","author":"Ning","year":"2025"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02239"},{"key":"ref28","article-title":"A simple but tough-to-beat baseline for sentence embeddings","volume-title":"International conference on learning representations","author":"Arora"},{"key":"ref29","article-title":"opencv-python: Python bindings for opencv"},{"key":"ref30","article-title":"ffmpeg-python: Python bindings for ffmpeg"},{"key":"ref31","article-title":"Termux: Terminal emulator and linux environment for android","year":"2023"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3538394.3546042"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1688"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref35","article-title":"Recommendation P.1203: Parametric bitstream-based quality assessment of progressive download and adaptive audiovisual streaming services over reliable transport","volume-title":"ITU-T, Tech. Rep","year":"2017"},{"key":"ref36","first-page":"377","article-title":"Live video analytics at scale with approximation and {Delay-Tolerance}","volume-title":"Proc. USENIX NSDI","author":"Zhang"},{"key":"ref37","first-page":"406","article-title":"Scaling video analytics on constrained edge nodes","volume":"1","author":"Canel","year":"2019","journal-title":"MLsys"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3300061.3300116"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/IWQoS61813.2024.10682870"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2025.3574591"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM55648.2025.11044626"},{"key":"ref42","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"ref43","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. PMLR ICML","author":"Radford"},{"key":"ref44","article-title":"Gemini: A family of highly capable multimodal models","volume":"1","author":"Anil","year":"2023"},{"key":"ref45","article-title":"Qwen-vl: A frontier large vision-language model with versatile abilities","author":"Bai","year":"2023"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73397-0_15"}],"event":{"name":"IEEE INFOCOM 2026 - IEEE Conference on Computer Communications","location":"Tokyo, Japan","start":{"date-parts":[[2026,5,18]]},"end":{"date-parts":[[2026,5,21]]}},"container-title":["IEEE INFOCOM 2026 - IEEE Conference on Computer Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11571071\/11571169\/11571484.pdf?arnumber=11571484","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T05:12:37Z","timestamp":1782796357000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11571484\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,18]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/infocom59046.2026.11571484","relation":{},"subject":[],"published":{"date-parts":[[2026,5,18]]}}}