{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,15]],"date-time":"2025-08-15T00:59:32Z","timestamp":1755219572457,"version":"3.43.0"},"reference-count":59,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,26]],"date-time":"2025-05-26T00:00:00Z","timestamp":1748217600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,26]],"date-time":"2025-05-26T00:00:00Z","timestamp":1748217600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100016311","name":"Arm","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100016311","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,5,26]]},"DOI":"10.1109\/fg61629.2025.11099250","type":"proceedings-article","created":{"date-parts":[[2025,8,6]],"date-time":"2025-08-06T17:55:00Z","timestamp":1754502900000},"page":"1-10","source":"Crossref","is-referenced-by-count":0,"title":["AeroGen: Ground-to-Air Generalization for Action Recognition"],"prefix":"10.1109","author":[{"given":"Ketul","family":"Shah","sequence":"first","affiliation":[{"name":"Johns Hopkins University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anshul","family":"Shah","sequence":"additional","affiliation":[{"name":"Johns Hopkins University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arun","family":"Reddy","sequence":"additional","affiliation":[{"name":"Johns Hopkins University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aniket","family":"Roy","sequence":"additional","affiliation":[{"name":"Johns Hopkins University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Celso M. de","family":"Melo","sequence":"additional","affiliation":[{"name":"DEVCOM U.S. Army Research Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rama","family":"Chellappa","sequence":"additional","affiliation":[{"name":"Johns Hopkins University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.01311"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093511"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00432"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00229"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00553"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.278"},{"volume-title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In International Conference on Learning Representations (ICLR)","author":"Dosovitskiy","key":"ref8"},{"key":"ref9","article-title":"Masked autoencoders as spatiotemporal learners","author":"Feichtenhofer","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01238"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108043"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01128"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/access.2021.3051842"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240675"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00699"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"volume-title":"The kinetics human action video dataset","year":"2017","author":"Kay","key":"ref20"},{"volume-title":"The Kinetics Human Action Video Dataset","year":"2017","author":"Kay","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW54805.2022.00056"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00530"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01094"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01594-9"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01594-9"},{"article-title":"Ddgen: A directed graph convolutional network for action recognition","volume-title":"The European Conference on Computer Vision (ECCV)","author":"Korban","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_37"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00029"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01600"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01192-2"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2916873"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01855"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00022"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818013"},{"article-title":"Decoupled Weight Decay Regularization","volume-title":"International Conference on Learning Representations (ICLR)","author":"Loshchilov","key":"ref36"},{"key":"ref37","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2021","journal-title":"arXiv preprint arXiv:2112.10741"},{"key":"ref38","article-title":"PyTorch: An Imperative Style, HighPerformance Deep Learning Library","author":"Paszke","year":"2019","journal-title":"NeurIPS"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3184598"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794443"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00886"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160416"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01042"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00338"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.115"},{"key":"ref46","article-title":"Two-stream convolutional networks for action recognition in videos","author":"Simonyan","year":"2014","journal-title":"Advances in neural information processing systems, 27"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2021.103186"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2021.103186"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref50","article-title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","author":"Tong","year":"2022","journal-title":"NeurIPS"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01467-7"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.492"},{"key":"ref53","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58583-9_26"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.339"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160564"},{"volume-title":"Robust category-level 3d pose estimation from synthetic data","year":"2023","author":"Yang","key":"ref57"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3116945"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7003"}],"event":{"name":"2025 IEEE 19th International Conference on Automatic Face and Gesture Recognition (FG)","start":{"date-parts":[[2025,5,26]]},"location":"Tampa\/Clearwater, FL, USA","end":{"date-parts":[[2025,5,30]]}},"container-title":["2025 IEEE 19th International Conference on Automatic Face and Gesture Recognition (FG)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11099084\/11099070\/11099250.pdf?arnumber=11099250","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T05:00:28Z","timestamp":1754542828000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11099250\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,26]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/fg61629.2025.11099250","relation":{},"subject":[],"published":{"date-parts":[[2025,5,26]]}}}