{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T10:19:33Z","timestamp":1773137973427,"version":"3.50.1"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U21A20444"],"award-info":[{"award-number":["U21A20444"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62301335"],"award-info":[{"award-number":["62301335"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62371408"],"award-info":[{"award-number":["62371408"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Fundamental Research Funds for the Central UniversitiesGrant","award":["20720250036"],"award-info":[{"award-number":["20720250036"]}]},{"name":"Fundamental Research Funds for the Central UniversitiesGrant","award":["20720250170"],"award-info":[{"award-number":["20720250170"]}]},{"name":"National Key Research and Development Program of China","award":["2023YFB3107603"],"award-info":[{"award-number":["2023YFB3107603"]}]},{"name":"Postdoctoral Fellowship Program of CPSF","award":["GZC20252299"],"award-info":[{"award-number":["GZC20252299"]}]},{"name":"Fujian Provincial Natural Science Foundation of China","award":["2024J09002"],"award-info":[{"award-number":["2024J09002"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Mobile Comput."],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1109\/tmc.2025.3627276","type":"journal-article","created":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T17:14:13Z","timestamp":1761930853000},"page":"5016-5031","source":"Crossref","is-referenced-by-count":0,"title":["Reinforcement Learning-Based Edge-Assisted Inference With Multimodal Data"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-0367-2844","authenticated-orcid":false,"given":"Yu","family":"Liu","sequence":"first","affiliation":[{"name":"Institute of Artificial Intelligence, Xiamen University, Xiamen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2402-611X","authenticated-orcid":false,"given":"Liang","family":"Xiao","sequence":"additional","affiliation":[{"name":"Department of Informatics and Communication Engineering, Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Xiamen University, Xiamen, China"}]},{"given":"Chuxuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence, Xiamen University, Xiamen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3880-5069","authenticated-orcid":false,"given":"Zefang","family":"Lv","sequence":"additional","affiliation":[{"name":"Institute of Space Internet, Fudan University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2089-6938","authenticated-orcid":false,"given":"Yiwen","family":"Zhan","sequence":"additional","affiliation":[{"name":"Department of Informatics and Communication Engineering, Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Xiamen University, Xiamen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0717-7488","authenticated-orcid":false,"given":"Yilin","family":"Xiao","sequence":"additional","affiliation":[{"name":"Peng Cheng Laboratory, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9697-7470","authenticated-orcid":false,"given":"Helin","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Informatics and Communication Engineering, Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Xiamen University, Xiamen, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00430"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref4","first-page":"3927","article-title":"Is someone speaking? Exploring long-term temporal features for audio-visual active speaker detection","volume-title":"Proc. ACM Int. Conf. Multimedia","author":"Tao","year":"2021"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3241539.3241559"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3447993.3483249"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3037697.3037698"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2022.3229033"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2019.2947893"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3372224.3419215"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3372224.3419194"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2022.3177782"},{"key":"ref14","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Mach. Learn. Res. (ICML)","author":"Radford","year":"2021"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2023.3303350"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3183112"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3485730.3485944"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3550298"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/2906388.2906396"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539183"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2022.3189186"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM41043.2020.9155435"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2021.3125949"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3118403"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2023.3238342"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796896"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2022.3177569"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2021.3122279"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3431379.3460648"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2022.3172402"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCC57788.2023.10233276"},{"key":"ref32","first-page":"1","article-title":"An image is worth 16 x 16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations (ICLR)","author":"Dosovitskiy","year":"2021"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref34","first-page":"1157","article-title":"DISTMM: Accelerating distributed multimodal model training","volume-title":"Proc. USENIX Symp. Netw. Syst. Des. Implement. (NSDI)","author":"Huang","year":"2024"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.3017573"},{"key":"ref36","first-page":"1","article-title":"A unified approach to interpreting model predictions","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Lundberg","year":"2017"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2021.3070974"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2014.2322262"},{"key":"ref39","first-page":"1","article-title":"Is Q-learning provably efficient?","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Jin","year":"2018"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2003.809401"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053900"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"}],"container-title":["IEEE Transactions on Mobile Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7755\/11423852\/11223761.pdf?arnumber=11223761","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T20:01:16Z","timestamp":1773086476000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11223761\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":42,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tmc.2025.3627276","relation":{},"ISSN":["1536-1233","1558-0660","2161-9875"],"issn-type":[{"value":"1536-1233","type":"print"},{"value":"1558-0660","type":"electronic"},{"value":"2161-9875","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4]]}}}