{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:16:15Z","timestamp":1792786575917,"version":"4.5.0"},"reference-count":66,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"19","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Natural Science Foundation of China","award":["62476006"],"award-info":[{"award-number":["62476006"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"crossref"}]},{"name":"Postgraduate Innovation Fund Project of Anhui University of Science & Technology","award":["2024cx2189"],"award-info":[{"award-number":["2024cx2189"]}],"id":[{"id":"https:\/\/ror.org\/00q9atg80","id-type":"ROR","asserted-by":"crossref"}]},{"name":"Fundamental Research Funds of AUST","award":["2024JBZD0007"],"award-info":[{"award-number":["2024JBZD0007"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Internet Things J."],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1109\/jiot.2026.3718226","type":"journal-article","created":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T19:12:06Z","timestamp":1785352326000},"page":"44999-45017","source":"Crossref","is-referenced-by-count":0,"title":["A Multimodal Benchmark for Open-Pit Mine Remote Sensing Change Detection With Vision\u2013Language Guidance"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-2488-7853","authenticated-orcid":false,"given":"Wanyun","family":"Chen","sequence":"first","affiliation":[{"name":"Anhui University of Science & Technology","place":["Huainan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9222-0702","authenticated-orcid":false,"given":"Changhe","family":"Li","sequence":"additional","affiliation":[{"name":"Anhui University of Science & Technology","place":["Huainan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuchen","family":"Feng","sequence":"additional","affiliation":[{"name":"Anhui Normal University","place":["Wuhu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1848-9106","authenticated-orcid":false,"given":"Hongchen","family":"Tang","sequence":"additional","affiliation":[{"name":"Anhui Normal University","place":["Wuhu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongda","family":"Wang","sequence":"additional","affiliation":[{"name":"Anhui University of Science and Technology","place":["Huainan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6169-9666","authenticated-orcid":false,"given":"Jiarun","family":"Yang","sequence":"additional","affiliation":[{"name":"Anhui University of Science & Technology","place":["Huainan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1821-1094","authenticated-orcid":false,"given":"Yong","family":"Xu","sequence":"additional","affiliation":[{"name":"Anhui Normal University","place":["Wuhu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1338-6224","authenticated-orcid":false,"given":"Qun","family":"Fang","sequence":"additional","affiliation":[{"name":"Anhui Normal University","place":["Wuhu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1080\/0143116031000101675"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1126\/science.1111772"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.rse.2011.04.032"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1080\/01431168908903939"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1117\/12.919756"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3390\/rs13193930"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2024.3491715"},{"key":"ref8","article-title":"EuroMineNet: A multitemporal Sentinel-2 benchmark for spatiotemporal mining footprint analysis in the European union (2015\u20132024)","author":"Yu","year":"2025","journal-title":"arXiv:2510.14661"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3095166"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/igarss46834.2022.9883686"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2023.3277496"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2024.01.004"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.5194\/isprs-annals-x-g-2025-383-2025"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3390\/rs18040541"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2018.8451652"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3390\/rs15143482"},{"key":"ref17","article-title":"Show me what and where has changed? Question answering and grounding for remote sensing change detection","author":"Li","year":"2024","journal-title":"arXiv:2410.23828"},{"key":"ref18","article-title":"ViLaCD-r1: A vision\u2013language framework for semantic change detection in remote sensing","author":"Ma","year":"2025","journal-title":"arXiv:2512.23244"},{"key":"ref19","article-title":"ChangeChat: An interactive model for remote sensing change analysis via multimodal instruction tuning","author":"Deng","year":"2024","journal-title":"arXiv:2409.08582"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS55030.2025.11243524"},{"key":"ref21","article-title":"SkySense: A multi-modal remote sensing foundation model towards universal interpretation for Earth observation imagery","author":"Guo","year":"2023","journal-title":"arXiv:2312.10115"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2025.01.020"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2025.03.028"},{"key":"ref24","first-page":"1","article-title":"GeoPixel: Pixel grounding large multimodal model in remote sensing","volume-title":"Proc. ICML","author":"Shabbir"},{"key":"ref25","article-title":"GEOBench-VLM: Benchmarking vision\u2013language models for geospatial tasks","author":"Danish","year":"2024","journal-title":"arXiv:2411.19325"},{"key":"ref26","article-title":"CHOICE: Benchmarking the remote sensing capabilities of large vision\u2013language models","author":"An","year":"2024","journal-title":"arXiv:2411.18145"},{"key":"ref27","article-title":"ViCA: Efficient multimodal LLMs with vision-only cross-attention","author":"Liu","year":"2026","journal-title":"arXiv:2602.07574"},{"key":"ref28","article-title":"CASA: Cross-attention over self-attention for efficient vision\u2013language fusion","author":"B\u00f6hle","year":"2025","journal-title":"arXiv:2512.19535"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref30","article-title":"VLRM: Vision\u2013language models act as reward models for image captioning","author":"Dzabraev","year":"2024","journal-title":"arXiv:2404.01911"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.02149"},{"key":"ref32","article-title":"Enhancing image caption generation using reinforcement learning with human feedback","author":"Adarsh","year":"2024","journal-title":"arXiv:2403.06735"},{"key":"ref33","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref34","article-title":"Fluent and accurate image captioning with a self-trained reward model","author":"Moratelli","year":"2024","journal-title":"arXiv:2408.16827"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref36","first-page":"1","article-title":"An image is worth $16\\times 16$\n words: Transformers for image recognition at scale","volume-title":"Proc. ICLR","author":"Dosovitskiy"},{"key":"ref37","first-page":"1","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. ICML","author":"Radford"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2018.214"},{"key":"ref40","volume-title":"Information Retrieval","author":"van Rijsbergen","year":"1979"},{"key":"ref41","first-page":"547","article-title":"\u00c9tude comparative de la distribution florale dans une portion des Alpes et des Jura","volume":"7","author":"Jaccard","year":"1901","journal-title":"Bull. de la Soci\u00e9t\u00e9 Vaudoise des Sciences Naturelles"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1177\/001316446002000104"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.3115\/1626355.1626389"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref46","first-page":"1","article-title":"BERTScore: Evaluating text generation with BERT","volume-title":"Proc. ICLR","author":"Zhang"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-022-08122-3"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3241436"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2020.01.013"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2023.3300533"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3227098"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/lgrs.2018.2889307"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2020.06.003"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2023.3264802"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2023.3310208"},{"key":"ref57","volume-title":"GPT-4V(ision) System Card","year":"2023"},{"key":"ref58","article-title":"Qwen-VL: A versatile vision\u2013language model for understanding, localization, text reading, and beyond","author":"Bai","year":"2023","journal-title":"arXiv:2308.12966"},{"key":"ref59","article-title":"Gemma 3 technical report","author":"Team","year":"2025"},{"key":"ref60","article-title":"DeepSeek-VL2: Mixture-of-experts vision\u2013language models for advanced multimodal understanding","author":"Wu","year":"2024","journal-title":"arXiv:2412.10302"},{"key":"ref61","article-title":"Qwen3-VL technical report","volume-title":"arXiv:2511.21631","author":"Bai","year":"2025"},{"key":"ref62","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. ICML","author":"Li"},{"key":"ref63","article-title":"Kosmos-2: Grounding multimodal large language models to the world","author":"Peng","year":"2023","journal-title":"arXiv:2306.14824"},{"key":"ref64","article-title":"MiniGPT-v2: Large language model as a unified interface for vision\u2013language multi-task learning","author":"Chen","year":"2023","journal-title":"arXiv:2310.09478"},{"key":"ref65","article-title":"SAM 2: Segment anything in images and videos","author":"Ravi","year":"2024","journal-title":"arXiv:2408.00714"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/igarss55030.2025.11243118"}],"container-title":["IEEE Internet of Things Journal"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6488907\/11705432\/11627844.pdf?arnumber=11627844","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T19:15:55Z","timestamp":1790277355000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11627844\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":66,"journal-issue":{"issue":"19"},"URL":"https:\/\/doi.org\/10.1109\/jiot.2026.3718226","relation":{},"ISSN":["2327-4662"],"issn-type":[{"value":"2327-4662","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10]]}}}