{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T16:14:02Z","timestamp":1778084042626,"version":"3.51.4"},"reference-count":57,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021202","name":"Digital Research Alliance of Canada","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100021202","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004489","name":"MITACS","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004489","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00210","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"2172-2182","source":"Crossref","is-referenced-by-count":1,"title":["Visual Modality Prompt for Adapting Vision-Language Object Detectors"],"prefix":"10.1109","author":[{"given":"Heitor R.","family":"Medeiros","sequence":"first","affiliation":[{"name":"LIVIA, ETS Montreal, Canada International Laboratory on Learning Systems (ILLS),Dept. of Systems Engineering"}]},{"given":"Atif","family":"Belal","sequence":"additional","affiliation":[{"name":"LIVIA, ETS Montreal, Canada International Laboratory on Learning Systems (ILLS),Dept. of Systems Engineering"}]},{"given":"Srikanth","family":"Muralidharan","sequence":"additional","affiliation":[{"name":"LIVIA, ETS Montreal, Canada International Laboratory on Learning Systems (ILLS),Dept. of Systems Engineering"}]},{"given":"Eric","family":"Granger","sequence":"additional","affiliation":[{"name":"LIVIA, ETS Montreal, Canada International Laboratory on Learning Systems (ILLS),Dept. of Systems Engineering"}]},{"given":"Marco","family":"Pedersoli","sequence":"additional","affiliation":[{"name":"LIVIA, ETS Montreal, Canada International Laboratory on Learning Systems (ILLS),Dept. of Systems Engineering"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Exploring visual prompts for adapting largescale models","author":"Bahng","year":"2022","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_24"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00426"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126804"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00046"},{"key":"ref6","article-title":"MMDetection: Open mmlab detection toolbox and benchmark","author":"Chen","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01599"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01899"},{"key":"ref9","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25072-9_46"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7353446"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref14","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","volume-title":"International Conference on Learning Representations","author":"Gu","year":"2022"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1117\/12.2304400"},{"key":"ref17","article-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/METROI4.2018.8428330"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref21","volume-title":"Ultralytics yolov8","author":"Jocher","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00180"},{"key":"ref23","author":"Kingma","year":"2022","journal-title":"Auto-encoding variational bayes"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3120870"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25233"},{"key":"ref28","article-title":"Learning object-language alignments for open-vocabulary object detection","volume-title":"The Eleventh International Conference on Learning Representations","author":"Lin","year":"2023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1405.0312"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73024-5_4"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00147"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00874"},{"key":"ref35","article-title":"Benchmarking robustness in object detection: Autonomous driving when winter is coming","author":"Michaelis","journal-title":"arXiv preprint"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2022.01.026"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3109419"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1080\/01691864.2017.1365009"},{"key":"ref39","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijcce.2021.11.005"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00852"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1177\/0306312717741687"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.3390\/rs14092020"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.07.026"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0145"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01049"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_7"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9191080"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2614"},{"key":"ref52","article-title":"Dino: Detr with improved denoising anchor boxes for end-to-end object detection","volume-title":"The Eleventh International Conference on Learning Representations","author":"Zhang","year":"2023"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2023.3238524"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444326.pdf?arnumber=11444326","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:07:38Z","timestamp":1777612058000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444326\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00210","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}