{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T16:33:47Z","timestamp":1769186027051,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":28,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819555666","type":"print"},{"value":"9789819555673","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-981-95-5567-3_12","type":"book-chapter","created":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T21:13:55Z","timestamp":1769116435000},"page":"165-181","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["PMCFNet: Prompt-Guided Multi-scale Cross-Modal Fusion Network for\u00a0Referring Remote Sensing Image Segmentation"],"prefix":"10.1007","author":[{"given":"Yuqiu","family":"Kong","sequence":"first","affiliation":[]},{"given":"Wenjie","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Zijian","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Shenglan","family":"Liu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,1,23]]},"reference":[{"key":"12_CR1","unstructured":"Bar, A., Gandelsman, Y., Darrell, T., Globerson, A., Efros, A.A.: Visual prompting via image inpainting. In: Oh, A.H., Agarwal, A., Belgrave, D., Cho, K. (eds.) Advances in Neural Information Processing Systems (2022). https:\/\/openreview.net\/forum?id=o4uFFg9_TpV"},{"key":"12_CR2","doi-asserted-by":"crossref","unstructured":"Chng, Y.X., Zheng, H., Han, Y., Qiu, X., Huang, G.: Mask grounding for referring image segmentation. In: 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2024)","DOI":"10.1109\/CVPR52733.2024.02509"},{"key":"12_CR3","doi-asserted-by":"crossref","unstructured":"Cho, Y., Yu, H., Kang, S.J.: Cross-aware early fusion with stage-divided vision and language transformer encoders for referring image segmentation. IEEE Trans. Multimedia (2023)","DOI":"10.1109\/TMM.2023.3340062"},{"key":"12_CR4","doi-asserted-by":"publisher","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2009 (2009). https:\/\/doi.org\/10.1109\/cvpr.2009.5206848","DOI":"10.1109\/cvpr.2009.5206848"},{"key":"12_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1007\/978-3-319-46454-1_6","volume-title":"Computer Vision \u2013 ECCV 2016","author":"L Duan","year":"2016","unstructured":"Duan, L., Lafarge, F.: Towards large-scale city reconstruction from satellites. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9909, pp. 89\u2013104. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46454-1_6"},{"issue":"20","key":"12_CR6","doi-asserted-by":"publisher","first-page":"4035","DOI":"10.1080\/0143116031000103853","volume":"24","author":"GM Foody","year":"2003","unstructured":"Foody, G.M.: Remote sensing of tropical forest environments: towards the monitoring of environmental resources for sustainable development. Int. J. Remote Sens. 24(20), 4035\u20134046 (2003)","journal-title":"Int. J. Remote Sens."},{"key":"12_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1007\/978-3-319-46448-0_7","volume-title":"Computer Vision \u2013 ECCV 2016","author":"R Hu","year":"2016","unstructured":"Hu, R., Rohrbach, M., Darrell, T.: Segmentation from natural language expressions. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 108\u2013124. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_7"},{"key":"12_CR8","doi-asserted-by":"crossref","unstructured":"Hu, Y., et al.: Beyond one-to-one: rethinking the referring image segmentation. In: 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), October 2023, pp. 4067\u20134077 (2023)","DOI":"10.1109\/ICCV51070.2023.00376"},{"key":"12_CR9","doi-asserted-by":"publisher","unstructured":"Hu, Z., Feng, G., Sun, J., Zhang, L., Lu, H.: Bi-directional relationship inferring network for referring image segmentation. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2020 (2020). https:\/\/doi.org\/10.1109\/cvpr42600.2020.00448","DOI":"10.1109\/cvpr42600.2020.00448"},{"key":"12_CR10","doi-asserted-by":"crossref","unstructured":"Huang, S., et al.: Referring image segmentation via cross-modal progressive comprehension. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10488\u201310497 (2020)","DOI":"10.1109\/CVPR42600.2020.01050"},{"key":"12_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1007\/978-3-030-58607-2_4","volume-title":"Computer Vision \u2013 ECCV 2020","author":"T Hui","year":"2020","unstructured":"Hui, T., et al.: Linguistic structure guided context modeling for referring image segmentation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12355, pp. 59\u201375. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58607-2_4"},{"key":"12_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2024.3522293","volume":"63","author":"S Lei","year":"2025","unstructured":"Lei, S., Xiao, X., Zhang, T., Li, H.C., Shi, Z., Zhu, Q.: Exploring fine-grained image-text alignment for referring remote sensing image segmentation. IEEE Trans. Geosci. Remote Sens. 63, 1\u201311 (2025). https:\/\/doi.org\/10.1109\/TGRS.2024.3522293","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"12_CR13","doi-asserted-by":"crossref","unstructured":"Liu, C., Ding, H., Jiang, X.: GRES: generalized referring expression segmentation. In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.02259"},{"key":"12_CR14","doi-asserted-by":"publisher","unstructured":"Liu, C., Lin, Z., Shen, X., Yang, J., Lu, X., Yuille, A.: Recurrent multimodal interaction for referring image segmentation. In: 2017 IEEE\/CVF International Conference on Computer Vision (ICCV), October 2017 (2017). https:\/\/doi.org\/10.1109\/iccv.2017.143","DOI":"10.1109\/iccv.2017.143"},{"key":"12_CR15","doi-asserted-by":"publisher","unstructured":"Liu, S., et al.: Rotated multi-scale interaction network for referring remote sensing image segmentation. In: 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 26648\u201326658 (2024). https:\/\/doi.org\/10.1109\/CVPR52733.2024.02517","DOI":"10.1109\/CVPR52733.2024.02517"},{"key":"12_CR16","doi-asserted-by":"crossref","unstructured":"Liu, S.A., Zhang, Y., Qiu, Z., Xie, H., Zhang, Y., Yao, T.: CARIS: context-aware referring image segmentation. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 779\u2013788 (2023)","DOI":"10.1145\/3581783.3612117"},{"key":"12_CR17","doi-asserted-by":"publisher","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 9992\u201310002 (2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.00986","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"12_CR18","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: International Conference on Learning Representations (2017)"},{"key":"12_CR19","doi-asserted-by":"crossref","unstructured":"Margffoy-Tuay, E., P\u00e9rez, J.C., Botero, E., Arbel\u00e1ez, P.: Dynamic multimodal instance segmentation guided by natural language queries. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 630\u2013645 (2018)","DOI":"10.1007\/978-3-030-01252-6_39"},{"issue":"2","key":"12_CR20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3485128","volume":"55","author":"D Rolnick","year":"2022","unstructured":"Rolnick, D., et al.: Tackling climate change with machine learning. ACM Comput. Surv. 55(2), 1\u201396 (2022)","journal-title":"ACM Comput. Surv."},{"key":"12_CR21","unstructured":"Waswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems (2017)"},{"key":"12_CR22","doi-asserted-by":"crossref","unstructured":"Wolf, T., et\u00a0al.: Transformers: state-of-the-art natural language processing. In: Conference on Empirical Methods in Natural Language Processing, pp. 38\u201345 (2020)","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"12_CR23","doi-asserted-by":"publisher","unstructured":"Wu, C., Lin, Z., Cohen, S., Bui, T., Maji, S.: PhraseCut: language-based image segmentation in the wild. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2020 (2020). https:\/\/doi.org\/10.1109\/cvpr42600.2020.01023","DOI":"10.1109\/cvpr42600.2020.01023"},{"key":"12_CR24","doi-asserted-by":"crossref","unstructured":"Xu, Z., Chen, Z., Zhang, Y., Song, Y., Wan, X., Li, G.: Bridging vision and language encoders: parameter-efficient tuning for referring image segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 17503\u201317512 (2023)","DOI":"10.1109\/ICCV51070.2023.01605"},{"key":"12_CR25","doi-asserted-by":"publisher","unstructured":"Yang, Z., Wang, J., Tang, Y., Chen, K., Zhao, H., Torr, P.H.: LAVT: language-aware vision transformer for referring image segmentation. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2022 (2022). https:\/\/doi.org\/10.1109\/cvpr52688.2022.01762","DOI":"10.1109\/cvpr52688.2022.01762"},{"key":"12_CR26","doi-asserted-by":"crossref","unstructured":"Yuan, Z., Mou, L., Hua, Y., Zhu, X.X.: RRSIS: referring remote sensing image segmentation. IEEE Trans. Geosci. Remote Sens. (2024)","DOI":"10.1109\/TGRS.2024.3369720"},{"key":"12_CR27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2023.3250471","volume":"61","author":"Y Zhan","year":"2023","unstructured":"Zhan, Y., Xiong, Z., Yuan, Y.: RSVG: exploring data and models for visual grounding on remote sensing data. IEEE Trans. Geosci. Remote Sens. 61, 1\u201313 (2023). https:\/\/doi.org\/10.1109\/TGRS.2023.3250471","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"12_CR28","doi-asserted-by":"crossref","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Conditional prompt learning for vision-language models. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01631"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-5567-3_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T21:14:01Z","timestamp":1769116441000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-5567-3_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819555666","9789819555673"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-5567-3_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"23 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shanghai","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":"15 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2025.prcv.cn\/index.asp","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}