{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T15:50:35Z","timestamp":1783698635420,"version":"3.55.0"},"reference-count":64,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62122060"],"award-info":[{"award-number":["62122060"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62431020"],"award-info":[{"award-number":["62431020"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Geosci. Remote Sensing"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tgrs.2024.3497976","type":"journal-article","created":{"date-parts":[[2024,11,14]],"date-time":"2024-11-14T18:37:35Z","timestamp":1731609455000},"page":"1-13","source":"Crossref","is-referenced-by-count":5,"title":["MGIMM: Multi-Granularity Instruction Multimodal Model for Attribute-Guided Remote Sensing Image Detailed Description"],"prefix":"10.1109","volume":"62","author":[{"given":"Cong","family":"Yang","sequence":"first","affiliation":[{"name":"National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0436-8446","authenticated-orcid":false,"given":"Zuchao","family":"Li","sequence":"additional","affiliation":[{"name":"National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0542-2280","authenticated-orcid":false,"given":"Lefei","family":"Zhang","sequence":"additional","affiliation":[{"name":"National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MGRS.2016.2540798"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2022.3167830"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MGRS.2022.3145854"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3279834"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102408"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2677464"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3044054"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MGRS.2024.3383473"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3401576"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16423"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3362475"},{"key":"ref12","first-page":"1","article-title":"Learn to explain: Multimodal reasoning via thought chains for science question answering","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Lu"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00503"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25445"},{"key":"ref15","article-title":"Kosmos-2: Grounding multimodal large language models to the world","author":"Peng","year":"2023","journal-title":"arXiv:2306.14824"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.876"},{"key":"ref17","article-title":"GPT4RoI: Instruction tuning large language model on region-of-interest","author":"Zhang","year":"2023","journal-title":"arXiv:2307.03601"},{"key":"ref18","first-page":"1","article-title":"Visual clues: Bridging vision and language foundations for image paragraph captioning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Xie"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2954750"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3211467"},{"key":"ref21","article-title":"Improved baselines with visual instruction tuning","author":"Liu","year":"2023","journal-title":"arXiv:2310.03744"},{"key":"ref22","article-title":"InstructBLIP: Towards general-purpose vision-language models with instruction tuning","author":"Dai","year":"2023","journal-title":"arXiv:2305.06500"},{"key":"ref23","article-title":"LLaMA-adapter V2: Parameter-efficient visual instruction model","author":"Gao","year":"2023","journal-title":"arXiv:2304.15010"},{"key":"ref24","article-title":"MiniGPT-V2: Large language model as a unified interface for vision-language multi-task learning","author":"Chen","year":"2023","journal-title":"arXiv:2310.09478"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3183022"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612374"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548316"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3070383"},{"key":"ref29","article-title":"GeoChat: Grounded large vision-language model for remote sensing","author":"Kuckreja","year":"2023","journal-title":"arXiv:2311.15826"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3603628"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2024.3471625"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3425815"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2024.3404604"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3102590"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3222606"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3132095"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.3026673"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3195692"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3218921"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3321752"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3250471"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3614949"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.352"},{"key":"ref44","volume-title":"Introducing ChatGPT","year":"2023"},{"key":"ref45","article-title":"OPT: Open pre-trained transformer language models","author":"Zhang","year":"2022","journal-title":"arXiv:2205.01068"},{"key":"ref46","first-page":"1","article-title":"Training language models to follow instructions with human feedback","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Ouyang"},{"key":"ref47","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv:2302.13971"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612470"},{"key":"ref49","first-page":"22631","article-title":"The flan collection: Designing data and methods for effective instruction tuning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Longpre"},{"key":"ref50","first-page":"1","article-title":"On the exploitability of instruction tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Shu"},{"key":"ref51","first-page":"1","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Alayrac"},{"key":"ref52","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. 40th Int. Conf. Mach. Learn. (ICML)","volume":"202","author":"Li"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref54","article-title":"VisionLLM: Large language model is also an open-ended decoder for vision-centric tasks","author":"Wang","year":"2023","journal-title":"arXiv:2305.11175"},{"key":"ref55","article-title":"LoRa: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Hu"},{"key":"ref56","article-title":"Scaling instruction-finetuned language models","author":"Won Chung","year":"2022","journal-title":"arXiv:2210.11416"},{"key":"ref57","volume-title":"Vicuna: An Open-Source Chatbot Impressing GPT-4 With 90%* ChatGPT Quality","author":"Chiang","year":"2023"},{"key":"ref58","article-title":"Foundation transformers","author":"Wang","year":"2022","journal-title":"arXiv:2210.06423"},{"key":"ref59","article-title":"ViP-LLaVA: Making large multimodal models understand arbitrary visual prompts","author":"Cai","year":"2023","journal-title":"arXiv:2312.00784"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref61","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proc. ACL Workshop Intrinsic Extrinsic Eval. Measures Mach. Transl. Summarization","author":"Banerjee"},{"key":"ref62","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Text Summarization Branches Out","author":"Lin","year":"2004"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"}],"container-title":["IEEE Transactions on Geoscience and Remote Sensing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/36\/10354519\/10752973.pdf?arnumber=10752973","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,15]],"date-time":"2025-01-15T19:54:59Z","timestamp":1736970899000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10752973\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/tgrs.2024.3497976","relation":{},"ISSN":["0196-2892","1558-0644"],"issn-type":[{"value":"0196-2892","type":"print"},{"value":"1558-0644","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}