{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T22:00:46Z","timestamp":1757628046183,"version":"3.44.0"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,8,11]],"date-time":"2025-08-11T00:00:00Z","timestamp":1754870400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,11]],"date-time":"2025-08-11T00:00:00Z","timestamp":1754870400000},"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":[[2025,8,11]]},"DOI":"10.1109\/avss65446.2025.11149918","type":"proceedings-article","created":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T17:30:18Z","timestamp":1757439018000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Zero-Shot Scene Understanding for Automatic Target Recognition Using Large Vision-Language Models"],"prefix":"10.1109","author":[{"given":"Yasiru","family":"Ranasinghe","sequence":"first","affiliation":[{"name":"Johns Hopkins University,Baltimore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vibashan","family":"VS","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Baltimore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"James","family":"Uplinger","sequence":"additional","affiliation":[{"name":"DEVCOM Army Research Laboratory,Adelphi"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Celso","family":"De Melo","sequence":"additional","affiliation":[{"name":"DEVCOM Army Research Laboratory,Adelphi"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vishal M.","family":"Patel","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Baltimore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298799"},{"key":"ref2","article-title":"Applications of Large Language Models for Robot Navigation and Scene Understanding","volume-title":"PhD thesis","author":"Chen","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01599"},{"key":"ref4","article-title":"Self-supervised features improve open-world learning","author":"Dhamija","year":"2021"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00459"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00902"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/s43586-021-00018-1"},{"key":"ref8","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3335602"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00577"},{"key":"ref11","first-page":"5583","article-title":"Vilt: Vision-and-language transformer without convolution or region supervision","volume-title":"International conference on machine learning","author":"Kim"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-016-6903-6"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3452437"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.14778\/1920841.1920886"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.14778\/3574245.3574258"},{"key":"ref17","article-title":"Pivot: Iterative visual prompting elicits actionable knowledge for vlms","author":"Nasiriany","year":"2024"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2010.5652306"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1117\/1.3601879"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095843"},{"key":"ref21","article-title":"Artificial intelligence for national security: the predictability problem","author":"Taddeo","year":"2022","journal-title":"Centre for Digital Ethics (CEDE) Research Paper No. Forthcoming"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2502579"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2024.1385778"}],"event":{"name":"2025 IEEE International Conference on Advanced Visual and Signal-Based Systems (AVSS)","location":"Tainan, Taiwan","start":{"date-parts":[[2025,8,11]]},"end":{"date-parts":[[2025,8,13]]}},"container-title":["2025 IEEE International Conference on Advanced Visual and Signal-Based Systems (AVSS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11149666\/11149641\/11149918.pdf?arnumber=11149918","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T05:50:07Z","timestamp":1757483407000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11149918\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,11]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/avss65446.2025.11149918","relation":{},"subject":[],"published":{"date-parts":[[2025,8,11]]}}}