{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,10]],"date-time":"2026-11-10T20:46:57Z","timestamp":1794343617042,"version":"4.9.0"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/tdmrep.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1109\/wacvw68408.2026.00159","type":"proceedings-article","created":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T19:09:24Z","timestamp":1785870564000},"page":"1475-1483","source":"Crossref","is-referenced-by-count":0,"title":["Steering Instruction-Tuned Vision-Language Models for Multi-Label Landcover Classification"],"prefix":"10.1109","author":[{"given":"Weijia","family":"Wang","sequence":"first","affiliation":[{"name":"Northern Illinois University","place":["DeKalb, IL, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jichao","family":"Fang","sequence":"additional","affiliation":[{"name":"Northern Illinois University","place":["DeKalb, IL, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Luo","sequence":"additional","affiliation":[{"name":"Northern Illinois University","place":["DeKalb, IL, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Qwen-VL: A versatile vision-language model for understanding, localization, text reading, and beyond","volume":"1","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01538"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/igarss55030.2025.11242834"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0015"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0441"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.rse.2011.11.026"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02613"},{"key":"ref8","article-title":"LoRA: Low-rank adaptation of large language models","volume":"1, 3, 7","author":"Hu","year":"2022","journal-title":"ICLR"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2025.03.028"},{"key":"ref10","article-title":"Editing models with task arithmetic","volume":"1, 2, 3, 7","author":"Ilharco","year":"2022","journal-title":"arXiv preprint"},{"key":"ref11","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume":"1","author":"Li","year":"2023","journal-title":"ICML"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/MGRS.2025.3598283"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3390838"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref15","article-title":"Remote sensing vision-language foundation models without annotations via ground-remote alignment","volume":"2, 7","author":"Mall","year":"2024","journal-title":"ICLR"},{"key":"ref16","volume":"1, 2, 3, 4, 5, 7","author":"Mallya","year":"2025","journal-title":"Zero-shot multi-spectral learning: Reimagining a generalist multimodal Gemini 2.5 model for remote sensing applications"},{"key":"ref17","volume-title":"Qwen3-VL technical report","volume":"1, 2","year":"2025"},{"key":"ref18","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume":"1","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-24638-z"},{"key":"ref20","volume":"4","author":"Shen","year":"2023","journal-title":"Mixture-of-experts meets instruction tuning: A winning combination for large language models"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/icassp55912.2026.11462157"},{"key":"ref22","volume":"4","author":"Su","year":"2025","journal-title":"Rewiring experts on the fly: Continuous rerouting for better online adaptation in mixture-of-expert models"},{"issue":"8","key":"ref23","first-page":"6457","article-title":"BigEarthNet-MM: A large-scale, multimodal, multilabel benchmark archive for remote sensing image classification and retrieval","volume":"59","author":"Sumbul","year":"2021","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2025.3642610"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1452"},{"key":"ref26","article-title":"Qwen2-VL: Enhancing vision-language model\u2019s perception of the world at any resolution","volume":"1","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28393"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2026.3652099"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2025.06.019"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3449154"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11617369\/11617396\/11617529.pdf?arnumber=11617529","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,11,10]],"date-time":"2026-11-10T20:08:38Z","timestamp":1794341318000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11617529\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/wacvw68408.2026.00159","relation":{"has-part":[{"id-type":"doi","id":"https:\/\/doi.org\/10.1109\/wacvw68408.2026.00159\/mm1","asserted-by":"subject"}]},"subject":[],"published":{"date-parts":[[2026,3]]}}}