{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T08:07:04Z","timestamp":1761898024545,"version":"3.28.0"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,7,15]]},"DOI":"10.1109\/icme57554.2024.10687493","type":"proceedings-article","created":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T17:24:16Z","timestamp":1727717056000},"page":"1-6","source":"Crossref","is-referenced-by-count":1,"title":["MISTA: A Large-Scale Dataset for Multi-Modal Instruction Tuning on Aerial Images"],"prefix":"10.1109","author":[{"given":"Hao","family":"Wu","sequence":"first","affiliation":[{"name":"University of Chinese Academy of Sciences,School of Engineering Science,Beijing,China,100049"}]},{"given":"Ke","family":"Lu","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,School of Engineering Science,Beijing,China,100049"}]},{"given":"Yuqiu","family":"Li","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,School of Engineering Science,Beijing,China,100049"}]},{"given":"Junhao","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,School of Engineering Science,Beijing,China,100049"}]},{"given":"Jian","family":"Xue","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,School of Engineering Science,Beijing,China,100049"}]}],"member":"263","reference":[{"article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","year":"2018","author":"Devlin","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11023-020-09548-1"},{"year":"2023","key":"ref3","article-title":"Gpt-4 technical report"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.33540\/2168"},{"key":"ref5","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Instructblip: Towards general-purpose vision-language models with instruction tuning","year":"2023","author":"Dai","key":"ref6"},{"article-title":"Svit: Scaling up visual instruction tuning","year":"2023","author":"Zhao","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02484"},{"article-title":"Sharegpt4v: Improving large multi-modal models with better captions","year":"2023","author":"Chen","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3117983"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3078451"},{"article-title":"Rsvg: Exploring data and models for visual grounding on remote sensing data","year":"2022","author":"Zhan","key":"ref12"},{"article-title":"Skyscript: A large and semantically diverse vision-language dataset for remote sensing","year":"2023","author":"Wang","key":"ref13"},{"article-title":"Rs5m: A large scale vision-language dataset for remote sensing vision-language foundation model","year":"2023","author":"Zhang","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.2988782"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3079918"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3203314"},{"key":"ref18","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","year":"2023","author":"Zhu","key":"ref19"},{"article-title":"Llava-med: Training a large language-and-vision assistant for biomedicine in one day","year":"2023","author":"Li","key":"ref20"},{"article-title":"Lamm: Language-assisted multi-modal instruction-tuning dataset, framework, and benchmark","year":"2023","author":"Yin","key":"ref21"},{"article-title":"Blip2: Bootstrapping language-image pre-training with frozen image encoders and large language models","year":"2023","author":"Li","key":"ref22"},{"article-title":"Minigpt-v2: large language model as a unified interface for vision-language multi-task learning","year":"2023","author":"Chen","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"article-title":"Visual instruction tuning with polite flamingo","year":"2023","author":"Chen","key":"ref25"},{"article-title":"M3it: A large-scale dataset towards multi-modal multilingual instruction tuning","year":"2023","author":"Li","key":"ref26"},{"year":"2023","key":"ref27","article-title":"Openai platform documentation: Vision"},{"year":"2023","key":"ref28","article-title":"New models and developer products announced at devday"}],"event":{"name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2024,7,15]]},"location":"Niagara Falls, ON, Canada","end":{"date-parts":[[2024,7,19]]}},"container-title":["2024 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10685847\/10687354\/10687493.pdf?arnumber=10687493","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T05:56:18Z","timestamp":1727762178000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10687493\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,15]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icme57554.2024.10687493","relation":{},"subject":[],"published":{"date-parts":[[2024,7,15]]}}}