{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T05:54:14Z","timestamp":1764914054287,"version":"3.46.0"},"reference-count":16,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"School of Engineering and Digital Sciences at Nazarbayev University"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Geosci. Remote Sensing Lett."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/lgrs.2025.3636165","type":"journal-article","created":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T19:03:17Z","timestamp":1764010997000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Federated Aerial Video Captioning With Effective Temporal Adaptation"],"prefix":"10.1109","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0650-8169","authenticated-orcid":false,"given":"Nguyen Anh","family":"Tu","sequence":"first","affiliation":[{"name":"School of Engineering and Digital Sciences, Nazarbayev University, Astana, Kazakhstan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7655-8391","authenticated-orcid":false,"given":"Nursultan","family":"Makhanov","sequence":"additional","affiliation":[{"name":"School of Engineering and Digital Sciences, Nazarbayev University, Astana, Kazakhstan"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3162-8910","authenticated-orcid":false,"given":"Kenzhebek","family":"Taniyev","sequence":"additional","affiliation":[{"name":"School of Engineering and Digital Sciences, Nazarbayev University, Astana, Kazakhstan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8605-2666","authenticated-orcid":false,"given":"Ton","family":"Duc Do","sequence":"additional","affiliation":[{"name":"School of Engineering and Digital Sciences, Nazarbayev University, Astana, Kazakhstan"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.1109\/TPAMI.2024.3522295","article-title":"A review of deep learning for video captioning","author":"Abdar","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3390\/rs15082139"},{"key":"ref3","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proc. Artif. Intell. Statist.","author":"McMahan"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MGRS.2024.3415391"},{"key":"ref5","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3331841"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref8","first-page":"429","article-title":"Federated optimization in heterogeneous networks","volume-title":"Proc. 3rd Mach. Learn. Syst. Conf.","author":"Li"},{"key":"ref9","first-page":"1","article-title":"Adaptive federated optimization","volume-title":"Proc. ICLR","author":"Reddi"},{"issue":"140","key":"ref10","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2019","journal-title":"J. Mach. Learn. Res."},{"key":"ref11","first-page":"1","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","volume-title":"Proc. 1st Conf. Lang. Model.","author":"Gu"},{"key":"ref12","article-title":"GIT: A generative image-to-text transformer for vision and language","author":"Wang","year":"2022","journal-title":"Trans. Mach. Learn. Res. (TMLR)"},{"key":"ref13","first-page":"1","article-title":"On the importance and applicability of pre-training for federated learning","volume-title":"Proc. ICLR","author":"Chen"},{"article-title":"Llava-next: A strong zero-shot video understanding model","year":"2024","author":"Zhang","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00313"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"}],"container-title":["IEEE Geoscience and Remote Sensing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8859\/11258609\/11265791.pdf?arnumber=11265791","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T05:50:33Z","timestamp":1764913833000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11265791\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":16,"URL":"https:\/\/doi.org\/10.1109\/lgrs.2025.3636165","relation":{},"ISSN":["1545-598X","1558-0571"],"issn-type":[{"type":"print","value":"1545-598X"},{"type":"electronic","value":"1558-0571"}],"subject":[],"published":{"date-parts":[[2026]]}}}