{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T15:53:58Z","timestamp":1784390038626,"version":"3.55.0"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,7,7]],"date-time":"2024-07-07T00:00:00Z","timestamp":1720310400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,7]],"date-time":"2024-07-07T00:00:00Z","timestamp":1720310400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,7,7]]},"DOI":"10.1109\/igarss53475.2024.10642424","type":"proceedings-article","created":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T17:56:13Z","timestamp":1725558973000},"page":"6953-6958","source":"Crossref","is-referenced-by-count":8,"title":["FUS-MAE: A Cross-Attention-Based Data Fusion Approach for Masked Autoencoders in Remote Sensing"],"prefix":"10.1109","author":[{"given":"Hugo","family":"Chan-To-Hing","sequence":"first","affiliation":[{"name":"National University of Singapore,Department of Electrical and Computer Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bharadwaj","family":"Veeravalli","sequence":"additional","affiliation":[{"name":"National University of Singapore,Department of Electrical and Computer Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"ref2","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref3","first-page":"10944","article-title":"What makes multi-modal learning better than single (provably)","volume":"34","author":"Huang","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3146246"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2019.2906412"},{"key":"ref6","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"key":"ref7","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref8","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"International conference on machine learning","author":"Chen"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/MGRS.2021.3089174"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.5194\/isprs-annals-IV-2-W7-153-2019"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/mgrs.2023.3281651"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3276853"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2022.3201489"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2023.3316193"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00123"},{"key":"ref17","first-page":"197","article-title":"SatMAE: Pre-training transformers for temporal and multi-spectral satellite imagery","volume":"35","author":"Cong","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2015.167"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.96"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TGRS.2020.3034752","article-title":"Self-supervised sar-optical data fusion of sentinel-1\/-2 images","volume":"60","author":"Chen","year":"2021","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2022.3195259"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS46834.2022.9883983"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3194732"},{"key":"ref26","article-title":"Large scale masked autoencoding for reducing label requirements on SAR data","author":"Allen","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_20"},{"key":"ref28","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"}],"event":{"name":"IGARSS 2024 - 2024 IEEE International Geoscience and Remote Sensing Symposium","location":"Athens, Greece","start":{"date-parts":[[2024,7,7]]},"end":{"date-parts":[[2024,7,12]]}},"container-title":["IGARSS 2024 - 2024 IEEE International Geoscience and Remote Sensing Symposium"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10640349\/10640352\/10642424.pdf?arnumber=10642424","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T06:10:31Z","timestamp":1725689431000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10642424\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,7]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/igarss53475.2024.10642424","relation":{},"subject":[],"published":{"date-parts":[[2024,7,7]]}}}