{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,12,19]],"date-time":"2024-12-19T05:16:07Z","timestamp":1734585367867,"version":"3.30.2"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,17]],"date-time":"2024-10-17T00:00:00Z","timestamp":1729123200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,17]],"date-time":"2024-10-17T00:00:00Z","timestamp":1729123200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,10,17]]},"DOI":"10.1109\/iccp63557.2024.10793014","type":"proceedings-article","created":{"date-parts":[[2024,12,17]],"date-time":"2024-12-17T19:09:09Z","timestamp":1734462549000},"page":"1-9","source":"Crossref","is-referenced-by-count":0,"title":["Training-Free Open-Vocabulary Segmentation of Aerial Drone Images Using Foundation Models"],"prefix":"10.1109","author":[{"given":"Oana","family":"Morar","sequence":"first","affiliation":[{"name":"Technical University of Cluj-Napoca,Romania"}]},{"given":"Andra","family":"Petrovai","sequence":"additional","affiliation":[{"name":"Technical University of Cluj-Napoca,Romania"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP46576.2022.9897990"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00132"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2020.05.009"},{"key":"ref4","article-title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","author":"Liu","year":"2023","journal-title":"arXiv"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.685"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01525"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref8","first-page":"8748","article-title":"Learning Transferable Visual Models From Natural Language Super-vision","volume-title":"International conference on machine learning. PMLR","author":"Radford"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01249"},{"key":"ref11","article-title":"Yolov9: Learning what you want to learn using programmable gradient information","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"ref13","first-page":"1","article-title":"On seeing stuff: The perception of materials by humans and machines","volume-title":"SPIE proceedings series","author":"Adelson"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-88682-2_4"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299025"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.122"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0733-5"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/wacv.2019.00083"},{"key":"ref20","article-title":"The cityscapes dataset for semantic urban scene under-standing","author":"Cordts","year":"2016","journal-title":"CVPR"},{"key":"ref21","article-title":"The cityscapes dataset for semantic urban scene under-standing","author":"Cordts","year":"2016","journal-title":"CVPR"},{"key":"ref22","article-title":"Highway driving dataset for semantic video segmentation","author":"Kim","year":"2018","journal-title":"BMVC"},{"key":"ref23","first-page":"2847","volume-title":"VisDrone-DET2021: The Vision Meets Drone Object detection Challenge Results","author":"Yaru","year":"2021"},{"key":"ref24","article-title":"Zero Shot Context-Based Object Segmentation using SLIP (SAM+CLIP)","author":"Gundavarapu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref25","article-title":"Open-Vocabulary SAM: Segment and Recognize Twenty-thousand Classes Interactively","author":"Haobo","year":"2024","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00179"},{"key":"ref27","article-title":"Grounded language-image pre-training","author":"Li","year":"2021","journal-title":"arXiv preprint"},{"key":"ref28","first-page":"213","article-title":"Endto-end object detection with transformers","volume-title":"European Conference on Computer Vision","author":"Carion"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01525"},{"key":"ref30","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.3390\/rs16122077"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01540"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2022.06.008"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.3390\/rs13163065"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00113"},{"key":"ref38","article-title":"Fast-scnn: Fast semantic seg-mentation network","author":"Poudel","year":"2019","journal-title":"arXiv preprint"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_20"},{"key":"ref40","article-title":"Deeperlab: Single-shot image parser","author":"Yang","year":"2019","journal-title":"arXiv"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00073"}],"event":{"name":"2024 IEEE 20th International Conference on Intelligent Computer Communication and Processing (ICCP)","start":{"date-parts":[[2024,10,17]]},"location":"Cluj-Napoca, Romania","end":{"date-parts":[[2024,10,19]]}},"container-title":["2024 IEEE 20th International Conference on Intelligent Computer Communication and Processing (ICCP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10792975\/10792923\/10793014.pdf?arnumber=10793014","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,18]],"date-time":"2024-12-18T07:17:43Z","timestamp":1734506263000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10793014\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,17]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/iccp63557.2024.10793014","relation":{},"subject":[],"published":{"date-parts":[[2024,10,17]]}}}