{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:01:38Z","timestamp":1776888098126,"version":"3.51.2"},"reference-count":59,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"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":[[2024,10,14]]},"DOI":"10.1109\/iros58592.2024.10802074","type":"proceedings-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T19:17:39Z","timestamp":1735154259000},"page":"10967-10974","source":"Crossref","is-referenced-by-count":3,"title":["SCP: Soft Conditional Prompt Learning for Aerial Video Action Recognition"],"prefix":"10.1109","author":[{"given":"Xijun","family":"Wang","sequence":"first","affiliation":[{"name":"University of Maryland,Dept. of Computer Science,College Park,MD,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruiqi","family":"Xian","sequence":"additional","affiliation":[{"name":"University of Maryland,Dept. of Electrical and Computer Engineering,College Park,MD,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianrui","family":"Guan","sequence":"additional","affiliation":[{"name":"University of Maryland,Dept. of Computer Science,College Park,MD,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fuxiao","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Maryland,Dept. of Computer Science,College Park,MD,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dinesh","family":"Manocha","sequence":"additional","affiliation":[{"name":"University of Maryland,Dept. of Computer Science,College Park,MD,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.267"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093511"},{"key":"ref3","first-page":"5842","article-title":"The","volume-title":"something something\" video database for learning and evaluating visual common sense,\" in Proceedings of the IEEE international Conference on computer vision","author":"Goyal"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"ref5","article-title":"Two-stream convolutional networks for action recognition in videos","volume":"27","author":"Simonyan","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299059"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0636-x"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.368"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.337"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_31"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_17"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00747"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160564"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/wacv57701.2024.00683"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/wacv57701.2024.00649"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_37"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1250"},{"key":"ref24","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00324"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acllong.353"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_16"},{"key":"ref28","article-title":"Towards understanding in-context learning with contrastive demonstrations and saliency maps","author":"Li","year":"2023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.71"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.346"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2022.11.003"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.398"},{"key":"ref34","article-title":"Vima: General robot manipulation with multimodal prompts","author":"Jiang","year":"2022"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161317"},{"key":"ref36","first-page":"20","article-title":"Chatgpt for robotics: Design principles and model abilities","volume":"2","author":"Vemprala","year":"2023","journal-title":"Microsoft Auton. Syst. Robot. Res"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28374"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00081"},{"key":"ref39","article-title":"Vlap: Efficient video-language alignment via frame prompting and distilling for video question answering","author":"Wang","year":"2023"},{"key":"ref40","article-title":"Vila: Efficient video-language alignment for video question answering","volume-title":"ECCV 2024","author":"Wang","year":"2024"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01755"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_7"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref44","article-title":"Aligning large multi-modal model with robust instruction tuning","author":"Liu","year":"2023"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.70"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2924188"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9190864"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_43"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1544\/1\/012030"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2022.12.005"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_10"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00099"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01576"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"}],"event":{"name":"2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Abu Dhabi, United Arab Emirates","start":{"date-parts":[[2024,10,14]]},"end":{"date-parts":[[2024,10,18]]}},"container-title":["2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10801246\/10801290\/10802074.pdf?arnumber=10802074","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,15]],"date-time":"2025-01-15T19:29:05Z","timestamp":1736969345000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10802074\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,14]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/iros58592.2024.10802074","relation":{},"subject":[],"published":{"date-parts":[[2024,10,14]]}}}