{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T06:26:57Z","timestamp":1774679217984,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":29,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819698622","type":"print"},{"value":"9789819698639","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-981-96-9863-9_26","type":"book-chapter","created":{"date-parts":[[2025,7,23]],"date-time":"2025-07-23T14:38:45Z","timestamp":1753281525000},"page":"304-315","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Curriculum-Learned Masked Pretraining Models for Remote Sensing Building Detection"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-8083-0124","authenticated-orcid":false,"given":"Yijing","family":"Zhai","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4409-3777","authenticated-orcid":false,"given":"Tao","family":"Xu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7696-4783","authenticated-orcid":false,"given":"Yuqian","family":"Zhang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3380-611X","authenticated-orcid":false,"given":"Baozhu","family":"Wan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,7,24]]},"reference":[{"key":"26_CR1","doi-asserted-by":"crossref","unstructured":"Zhang, X., Sun, Y., Shang, K., Zhang, L., Wang, S.: Crop classification based on feature band set construction and object-oriented approach using hyperspectral images. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 9(9), 4117\u20134128 (2016)","DOI":"10.1109\/JSTARS.2016.2577339"},{"issue":"10","key":"26_CR2","doi-asserted-by":"publisher","first-page":"7789","DOI":"10.1109\/JIOT.2020.3039359","volume":"8","author":"J Zhang","year":"2020","unstructured":"Zhang, J., Tao, D.: Empowering things with intelligence: a survey of the progress, challenges, and opportunities in artificial intelligence of things. IEEE Internet Things J. 8(10), 7789\u20137817 (2020)","journal-title":"IEEE Internet Things J."},{"issue":"5","key":"26_CR3","doi-asserted-by":"publisher","first-page":"2525","DOI":"10.1109\/TGRS.2016.2646420","volume":"55","author":"X Yang","year":"2017","unstructured":"Yang, X., Yu, Y.: Estimating soil salinity under various moisture conditions: an experimental study. IEEE Trans. Geosci. Remote Sens. 55(5), 2525\u20132533 (2017)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"26_CR4","doi-asserted-by":"publisher","unstructured":"Wang, D., et al.: An empirical study of remote sensing pretraining. IEEE Trans. Geosci. Remote Sens. 61, Art. 20 (2023). https:\/\/doi.org\/10.1109\/TGRS.2022.3176603","DOI":"10.1109\/TGRS.2022.3176603"},{"key":"26_CR5","doi-asserted-by":"crossref","unstructured":"Deng, J., et al.: ImageNet: a large-scale hierarchical image database. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Miami, FL, USA, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"26_CR6","doi-asserted-by":"crossref","unstructured":"Tong, X.-Y., et al.: Land-cover classification with high-resolution remote sensing images using transferable deep models. Remote Sens. Environ. 237, Article 111322 (2020)","DOI":"10.1016\/j.rse.2019.111322"},{"key":"26_CR7","doi-asserted-by":"crossref","unstructured":"Long, Y., et al.: On creating benchmark dataset for aerial image interpretation: Reviews, guidances, and million-aid. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 14, 4205\u20134230 (2021)","DOI":"10.1109\/JSTARS.2021.3070368"},{"key":"26_CR8","doi-asserted-by":"crossref","unstructured":"He, K., et al.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, pp. 770\u2013778. IEEE (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"26_CR9","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: IEEE International Conference on Computer Vision (ICCV), Montreal, Canada, pp. 10012\u201310022. IEEE (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"issue":"5","key":"26_CR10","doi-asserted-by":"publisher","first-page":"1141","DOI":"10.1007\/s11263-022-01739-w","volume":"131","author":"Q Zhang","year":"2023","unstructured":"Zhang, Q., et al.: ViTAEv2: vision transformer advanced by exploring inductive bias for image recognition and beyond. Int. J. Comput. Vis. 131(5), 1141\u20131162 (2023). https:\/\/doi.org\/10.1007\/s11263-022-01739-w","journal-title":"Int. J. Comput. Vis."},{"key":"26_CR11","unstructured":"Mikolov, T., et al.: Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781 [cs.CL] (2013)"},{"key":"26_CR12","doi-asserted-by":"crossref","unstructured":"Jean, N., et al.: Tile2vec: unsupervised representation learning for spatially distributed data. In: 33rd AAAI Conference on Artificial Intelligence (AAAI), Honolulu, HI, USA, pp. 3967\u20133974. AAAI Press (2019)","DOI":"10.1609\/aaai.v33i01.33013967"},{"key":"26_CR13","unstructured":"Chen, T., et al.: A simple framework for contrastive learning of visual representations. In: 37th International Conference on Machine Learning (ICML), Vienna, Austria, pp. 1597\u20131607. PMLR (2020)"},{"key":"26_CR14","first-page":"1","volume":"19","author":"H Jung","year":"2021","unstructured":"Jung, H., Oh, Y., Jeong, S., Lee, C., Jeon, T.: Contrastive self-supervised learning with smoothed representation for remote sensing. IEEE Geosci. Remote Sens. Lett. 19, 1\u20135 (2021)","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"26_CR15","doi-asserted-by":"crossref","unstructured":"Manas, O., et al.: Seasonal contrast: unsupervised pretraining from uncurated remote sensing data. In: IEEE International Conference on Computer Vision (ICCV), Montreal, Canada, pp. 9414\u20139423. IEEE (2021)","DOI":"10.1109\/ICCV48922.2021.00928"},{"key":"26_CR16","doi-asserted-by":"crossref","unstructured":"Scheibenreif, L., et al.: Self-supervised vision transformers for land-cover segmentation and classification. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA, pp. 1422\u20131431. IEEE (2022)","DOI":"10.1109\/CVPRW56347.2022.00148"},{"key":"26_CR17","doi-asserted-by":"crossref","unstructured":"Madan, N., Ristea, N.C., Nasrollahi, K., Moeslund, T.B., Ionescu, R.T.: CL-MAE: curriculum-learned masked autoencoders. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 2492\u20132502 (2024)","DOI":"10.1109\/WACV57701.2024.00248"},{"key":"26_CR18","doi-asserted-by":"crossref","unstructured":"Lu, Z., et al.: 5m-building: a large-scale high-resolution building dataset with CNN based detection analysis. In: IEEE International Conference on Tools with Artificial Intelligence (ICTAI), Portland, OR, USA, pp. 1385\u20131389. IEEE (2019)","DOI":"10.1109\/ICTAI.2019.00194"},{"key":"26_CR19","doi-asserted-by":"publisher","first-page":"296","DOI":"10.1016\/j.isprsjprs.2020.01.023","volume":"159","author":"K Li","year":"2020","unstructured":"Li, K., Wan, G., Cheng, G., Meng, L., Han, J.: Object detection in optical remote sensing images: a survey and a new benchmark. ISPRS J. Photogramm. Remote Sens. 159, 296\u2013307 (2020). https:\/\/doi.org\/10.1016\/j.isprsjprs.2020.01.023","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"26_CR20","doi-asserted-by":"crossref","unstructured":"Tian, Z., et al.: FCOS: fully convolutional one-stage object detection. In: IEEE International Conference on Computer Vision (ICCV), Seoul, South Korea, pp. 9626\u20139635. IEEE (2019)","DOI":"10.1109\/ICCV.2019.00972"},{"key":"26_CR21","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., et al.: Focal loss for dense object detection. In: IEEE International Conference on Computer Vision (ICCV), Venice, Italy, pp. 2980\u20132988. IEEE (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"26_CR22","doi-asserted-by":"crossref","unstructured":"Cai, Z., Vasconcelos, N.: Cascade R-CNN: delving into high quality object detection. In:\u00a0Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6154\u20136162. Springer, Cham (2018)","DOI":"10.1109\/CVPR.2018.00644"},{"key":"26_CR23","doi-asserted-by":"crossref","unstructured":"Sun, P., et al.: Sparse R-CNN: end-to-end object detection with learnable proposals. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Virtual Event, pp. 14454\u201314463. IEEE (2021)","DOI":"10.1109\/CVPR46437.2021.01422"},{"key":"26_CR24","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: Dynamic R-CNN: towards high quality object detection via dynamic training. In: 16th European Conference on Computer Vision (ECCV), Glasgow, UK, pp. 260\u2013275. Springer (2020)","DOI":"10.1007\/978-3-030-58555-6_16"},{"key":"26_CR25","doi-asserted-by":"crossref","unstructured":"Lu, X., et al.: Grid R-CNN. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA, pp. 7363\u20137372. IEEE (2019)","DOI":"10.1109\/CVPR.2019.00754"},{"key":"26_CR26","unstructured":"Ren, S., et al.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems (NeurIPS), Montreal, Canada, vol. 28, pp. 1\u201313. MIT Press (2015)"},{"key":"26_CR27","doi-asserted-by":"crossref","unstructured":"Wu, Y., et al.: Rethinking classification and localization for object detection. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA, pp. 10186\u201310195. IEEE (2020)","DOI":"10.1109\/CVPR42600.2020.01020"},{"key":"26_CR28","doi-asserted-by":"crossref","unstructured":"He, K., et al.: Mask R-CNN. In: IEEE International Conference on Computer Vision (ICCV), Venice, Italy, pp. 2961\u20132969. IEEE (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"26_CR29","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (ICLR), Virtual Event, pp. 1\u201321. OpenReview.net (2021)"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-9863-9_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T04:12:13Z","timestamp":1774671133000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-9863-9_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819698622","9789819698639"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-9863-9_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"24 July 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors declare no competing interests relevant to this work.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ningbo","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/icg\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}