{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:31:23Z","timestamp":1776889883533,"version":"3.51.2"},"publisher-location":"Singapore","reference-count":31,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819609659","type":"print"},{"value":"9789819609666","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T00:00:00Z","timestamp":1733529600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T00:00:00Z","timestamp":1733529600000},"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\/978-981-96-0966-6_17","type":"book-chapter","created":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T08:41:17Z","timestamp":1733474477000},"page":"280-296","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["RS-SAM: Integrating Multi-scale Information for\u00a0Enhanced Remote Sensing Image Segmentation"],"prefix":"10.1007","author":[{"given":"Enkai","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Jingjing","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Anda","family":"Cao","sequence":"additional","affiliation":[]},{"given":"Zhen","family":"Sun","sequence":"additional","affiliation":[]},{"given":"Haofei","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Huiqiong","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Li","family":"Sun","sequence":"additional","affiliation":[]},{"given":"Mingli","family":"Song","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,12,7]]},"reference":[{"key":"17_CR1","doi-asserted-by":"publisher","unstructured":"Badrinarayanan, V., Kendall, A., Cipolla, R.: SegNet: a deep convolutional encoder-decoder architecture for image segmentation (2017). https:\/\/doi.org\/10.17863\/CAM.17966","DOI":"10.17863\/CAM.17966"},{"key":"17_CR2","unstructured":"Chen, J., et al.: TransUNet: transformers make strong encoders for medical image segmentation. arXiv preprint arXiv:2102.04306 (2021)"},{"key":"17_CR3","doi-asserted-by":"publisher","unstructured":"Chen, K., et al.: RSPrompter: learning to prompt for remote sensing instance segmentation based on visual foundation model. IEEE Trans. Geosci. Remote Sens. 62, 1\u201317 (2024). https:\/\/doi.org\/10.1109\/TGRS.2024.3356074","DOI":"10.1109\/TGRS.2024.3356074"},{"key":"17_CR4","doi-asserted-by":"crossref","unstructured":"Demir, I., et al.: DeepGlobe 2018: a challenge to parse the earth through satellite images. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, June 2018","DOI":"10.1109\/CVPRW.2018.00031"},{"key":"17_CR5","unstructured":"Hu, E.J., et al.: LoRA: low-rank adaptation of large language models. In: International Conference on Learning Representations (2022). https:\/\/openreview.net\/forum?id=nZeVKeeFYf9"},{"key":"17_CR6","doi-asserted-by":"publisher","unstructured":"Huang, L., Jiang, B., Lv, S., Liu, Y., Fu, Y.: Deep-learning-based semantic segmentation of remote sensing images: a survey. IEEE J. Sel. Top. Appl. Earth Observ. Remote Sens. PP, 1\u201328 (2023). https:\/\/doi.org\/10.1109\/JSTARS.2023.3335891","DOI":"10.1109\/JSTARS.2023.3335891"},{"issue":"1","key":"17_CR7","doi-asserted-by":"publisher","first-page":"574","DOI":"10.1109\/TGRS.2018.2858817","volume":"57","author":"S Ji","year":"2019","unstructured":"Ji, S., Wei, S., Lu, M.: Fully convolutional networks for multisource building extraction from an open aerial and satellite imagery data set. IEEE Trans. Geosci. Remote Sens. 57(1), 574\u2013586 (2019). https:\/\/doi.org\/10.1109\/TGRS.2018.2858817","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"17_CR8","unstructured":"Kaidong, Z., Dong, L.: Customized segment anything model for medical image segmentation. arXiv preprint arXiv:2304.13785 (2023)"},{"key":"17_CR9","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et al.: Segment anything. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 4015\u20134026 (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"17_CR10","unstructured":"Kolesnikov, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale (2021)"},{"key":"17_CR11","doi-asserted-by":"publisher","unstructured":"Li, R., Wang, L., Zhang, C., Duan, C., Zheng, S.: A2-FPN for semantic segmentation of fine-resolution remotely sensed images. Int. J. Remote Sens. 43(3), 1131\u20131155 (2022). https:\/\/doi.org\/10.1080\/01431161.2022.2030071","DOI":"10.1080\/01431161.2022.2030071"},{"key":"17_CR12","doi-asserted-by":"publisher","unstructured":"Li, R., et al.: Multiattention network for semantic segmentation of fine-resolution remote sensing images. IEEE Trans. Geosci. Remote Sens. 60, 1\u201313 (2022). https:\/\/doi.org\/10.1109\/TGRS.2021.3093977","DOI":"10.1109\/TGRS.2021.3093977"},{"key":"17_CR13","doi-asserted-by":"publisher","unstructured":"Li, R., Zheng, S., Zhang, C., Duan, C., Wang, L., Atkinson, P.M.: ABCNet: attentive bilateral contextual network for efficient semantic segmentation of fine-resolution remotely sensed imagery. ISPRS J. Photogram. Remote Sens. 181, 84\u201398 (2021). https:\/\/doi.org\/10.1016\/j.isprsjprs.2021.09.005. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0924271621002379","DOI":"10.1016\/j.isprsjprs.2021.09.005"},{"key":"17_CR14","doi-asserted-by":"publisher","unstructured":"Li, S.: A review of remote sensing image classification techniques: the role of spatio-contextual information. Eur. J. Remote Sens. 47, 389\u2013411 (2014). https:\/\/doi.org\/10.5721\/EuJRS20144723","DOI":"10.5721\/EuJRS20144723"},{"key":"17_CR15","doi-asserted-by":"publisher","unstructured":"Li, Y., Mao, H., Girshick, R., He, K.: Exploring plain vision transformer backbones for object detection, pp. 280\u2013296 (2022). https:\/\/doi.org\/10.1007\/978-3-031-20077-9_17","DOI":"10.1007\/978-3-031-20077-9_17"},{"key":"17_CR16","doi-asserted-by":"publisher","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 936\u2013944 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.106","DOI":"10.1109\/CVPR.2017.106"},{"key":"17_CR17","doi-asserted-by":"crossref","unstructured":"Ma, X., Wu, Q., Zhao, X., Zhang, X., Pun, M.O., Huang, B.: SAM-assisted remote sensing imagery semantic segmentation with object and boundary constraints (2023)","DOI":"10.1109\/TGRS.2024.3443420"},{"key":"17_CR18","doi-asserted-by":"crossref","unstructured":"Osco, L., et al.: The segment anything model (SAM) for remote sensing applications: from zero to one shot (2023)","DOI":"10.1016\/j.jag.2023.103540"},{"key":"17_CR19","doi-asserted-by":"crossref","unstructured":"Qi, X., Wu, Y., Mao, Y., Zhang, W., Zhang, Y.: Self-guided few-shot semantic segmentation for remote sensing imagery based on large vision models (2023)","DOI":"10.1007\/978-3-031-71716-1_6"},{"key":"17_CR20","doi-asserted-by":"publisher","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation, vol.\u00a09351, pp. 234\u2013241 (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"17_CR21","doi-asserted-by":"publisher","unstructured":"Shao, Z., Yang, K., Zhou, W.: Performance evaluation of single-label and multi-label remote sensing image retrieval using a dense labeling dataset. Remote Sens. 10(6) (2018). https:\/\/doi.org\/10.3390\/rs10060964. https:\/\/www.mdpi.com\/2072-4292\/10\/6\/964","DOI":"10.3390\/rs10060964"},{"key":"17_CR22","doi-asserted-by":"crossref","unstructured":"Shao, Z., Zhou, W., Deng, X., Zhang, M., Cheng, Q.: Multilabel remote sensing image retrieval based on fully convolutional network. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 13, 318\u2013328 (2020). https:\/\/api.semanticscholar.org\/CorpusID:211208779","DOI":"10.1109\/JSTARS.2019.2961634"},{"issue":"4","key":"17_CR23","doi-asserted-by":"publisher","first-page":"640","DOI":"10.1109\/TPAMI.2016.2572683","volume":"39","author":"E Shelhamer","year":"2017","unstructured":"Shelhamer, E., Long, J., Darrell, T.: Fully convolutional networks for semantic segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 39(4), 640\u2013651 (2017). https:\/\/doi.org\/10.1109\/TPAMI.2016.2572683","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"17_CR24","unstructured":"Sultan, R.I., Li, C., Zhu, H., Khanduri, P., Brocanelli, M., Zhu, D.: GeoSAM: Fine-tuning SAM with sparse and dense visual prompting for automated segmentation of mobility infrastructure (2024)"},{"key":"17_CR25","doi-asserted-by":"crossref","unstructured":"Sun, K., Xiao, B., Liu, D., Wang, J.: Deep high-resolution representation learning for human pose estimation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00584"},{"key":"17_CR26","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Guyon, I., et al (eds.) Advances in Neural Information Processing Systems, vol.\u00a030. Curran Associates, Inc. (2017). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2017\/file\/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf"},{"issue":"9","key":"17_CR27","doi-asserted-by":"publisher","first-page":"2221","DOI":"10.1109\/TMM.2019.2954752","volume":"22","author":"B Wang","year":"2020","unstructured":"Wang, B., Zhao, Y., Chen, C.L.P.: Moving cast shadows segmentation using illumination invariant feature. IEEE Trans. Multimedia 22(9), 2221\u20132233 (2020). https:\/\/doi.org\/10.1109\/TMM.2019.2954752","journal-title":"IEEE Trans. Multimedia"},{"key":"17_CR28","doi-asserted-by":"publisher","unstructured":"Wang, L., Li, R., Duan, C., Zhang, C., Meng, X., Fang, S.: A novel transformer based semantic segmentation scheme for fine-resolution remote sensing images. IEEE Geosci. Remote Sens. Lett. 19, 1\u20135 (2022). https:\/\/doi.org\/10.1109\/LGRS.2022.3143368","DOI":"10.1109\/LGRS.2022.3143368"},{"key":"17_CR29","doi-asserted-by":"publisher","unstructured":"Wang, L., et al.: UNetFormer: a UNet-like transformer for efficient semantic segmentation of remote sensing urban scene imagery. ISPRS J. Photogram. Remote Sens. 190, 196\u2013214 (2022). https:\/\/doi.org\/10.1016\/j.isprsjprs.2022.06.008. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0924271622001654","DOI":"10.1016\/j.isprsjprs.2022.06.008"},{"key":"17_CR30","unstructured":"Zhang, J., Yang, X., Jiang, R., Shao, W., Zhang, L.: RSAM-Seg: a SAM-based approach with prior knowledge integration for remote sensing image semantic segmentation. ArXiv abs\/2402.19004 (2024). https:\/\/api.semanticscholar.org\/CorpusID:268063200"},{"key":"17_CR31","doi-asserted-by":"publisher","unstructured":"Zhang, X., Liu, Y., Lin, Y., Liao, Q., Li, Y.: UV-SAM: adapting segment anything model for urban village identification. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, no. 20, pp. 22520\u201322528 (2024). https:\/\/doi.org\/10.1609\/aaai.v38i20.30260. https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/30260","DOI":"10.1609\/aaai.v38i20.30260"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-0966-6_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T09:07:59Z","timestamp":1733476079000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-0966-6_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,7]]},"ISBN":["9789819609659","9789819609666"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-0966-6_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,7]]},"assertion":[{"value":"7 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hanoi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}