{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T16:08:37Z","timestamp":1783613317380,"version":"3.55.0"},"reference-count":68,"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:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"Ministry of Education Humanities and Social Science Research Planning","award":["23YJAZH079"],"award-info":[{"award-number":["23YJAZH079"]}]},{"DOI":"10.13039\/501100005046","name":"Natural Science Foundation of Heilongjiang Province","doi-asserted-by":"publisher","award":["LH2021F015"],"award-info":[{"award-number":["LH2021F015"]}],"id":[{"id":"10.13039\/501100005046","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/jstars.2024.3419035","type":"journal-article","created":{"date-parts":[[2024,6,25]],"date-time":"2024-06-25T20:10:32Z","timestamp":1719346232000},"page":"16799-16814","source":"Crossref","is-referenced-by-count":12,"title":["RSMoDM: Multimodal Momentum Distillation Model for Remote Sensing Visual Question Answering"],"prefix":"10.1109","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-4234-1579","authenticated-orcid":false,"given":"Pengfei","family":"Li","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, Harbin Engineering University, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7032-8429","authenticated-orcid":false,"given":"Gang","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Harbin Engineering University, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-8891-554X","authenticated-orcid":false,"given":"Jinlong","family":"He","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Harbin Engineering University, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9842-4044","authenticated-orcid":false,"given":"Xiangxu","family":"Meng","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Harbin Engineering University, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6542-649X","authenticated-orcid":false,"given":"Shenjun","family":"Zhong","sequence":"additional","affiliation":[{"name":"Monash Biomedical Imaging, Monash University, Clayton, VIC, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4922-8116","authenticated-orcid":false,"given":"Xun","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MGRS.2023.3316438"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2016.2612821"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2017.2783902"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2020.3030990"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2021.3072488"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2016.2601622"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2021.3119852"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3296757"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/MGRS.2024.3383473"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3102590"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3132095"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3070383"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2021.3070872"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3163706"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3124252"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.2988782"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3079918"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3173811"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3192460"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3237606"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.jag.2023.103427"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3275156"},{"key":"ref24","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Li","year":"2021"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref26","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS47720.2021.9553307"},{"key":"ref28","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. 3rd Int. Conf.Learn. Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings,","author":"Simonyan","year":"2015"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref30","first-page":"1","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. 9th Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2022.3176603"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/jstars.2021.3070368"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2015.7298594"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/d14-1179"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d16-1044"},{"key":"ref37","first-page":"1","article-title":"Hadamard product for low-rank bilinear pooling","volume-title":"Proc. 5th Int. Conf. Learn. Representations","author":"Kim","year":"2017"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2017.202"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.10"},{"key":"ref40","first-page":"1571","article-title":"Bilinear attention networks","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Kim","year":"2018"},{"key":"ref41","first-page":"6077","article-title":"Bottom-up and top-down attention for image captioning and visual question answering","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Anderson","year":"2018"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350925"},{"key":"ref43","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2023"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/isbi53787.2023.10230743"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43907-0_36"},{"key":"ref46","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Vaswani","year":"2017"},{"key":"ref47","first-page":"1","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","volume-title":"Proc. 12th Int. Conf. Learn. Representations, ICLR 2024, Vienna, Austria, May 7-11","author":"Zhu","year":"2024"},{"key":"ref48","article-title":"Pefomed: Parameter efficient fine-tuning on multimodal large language models for medical visual question answering","author":"He","year":"2024"},{"key":"ref49","article-title":"Llava-plus: Learning to use tools for creating multimodal agents","author":"Liu","year":"2023"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1117\/12.2636276"},{"key":"ref51","article-title":"VisualBERT: A simple and performant baseline for vision and language","author":"Li","year":"2019"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS52108.2023.10281674"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.jag.2023.103641"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"ref55","first-page":"2765","article-title":"Paraphrasing complex network: Network compression via factor transfer","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Kim","year":"2018"},{"key":"ref56","article-title":"Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer","volume-title":"Proc. 5th Int. Conf. Learn. Representations","author":"Zagoruyko","year":"2017"},{"key":"ref57","first-page":"3967","article-title":"Relational knowledge distillation","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Park","year":"2019"},{"key":"ref58","first-page":"1","article-title":"Contrastive representation distillation","volume-title":"Proc. 8th Int. Conf. Learn. Representations","author":"Tian","year":"2020"},{"key":"ref59","article-title":"Distilling the knowledge in a neural network","volume-title":"Proc. NIPS Deep Learn. Representation Learn. Workshop","author":"Hinton","year":"2015"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5746"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00381"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref63","article-title":"Googles neural machine translation system: Bridging the gap between human and machine translation","author":"Wu","year":"2016"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/igarss.2019.8900532"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref66","article-title":"Decoupled weight decay regularization","volume-title":"Proc. 7th Int. Conf. Learn. Representations, ICLR 2019, New Orleans, LA, USA, May 6-9,","author":"Loshchilov","year":"2019"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw56347.2022.00143"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01228-7"}],"container-title":["IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/4609443\/10330207\/10571375.pdf?arnumber=10571375","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,17]],"date-time":"2025-03-17T17:40:05Z","timestamp":1742233205000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10571375\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":68,"URL":"https:\/\/doi.org\/10.1109\/jstars.2024.3419035","relation":{},"ISSN":["1939-1404","2151-1535"],"issn-type":[{"value":"1939-1404","type":"print"},{"value":"2151-1535","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}