{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T14:15:17Z","timestamp":1788185717938,"version":"build-2803163510"},"reference-count":44,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/100016698","name":"Joint Fund of the National Natural Science Foundation of China and the Karst Science Research Center of Guizhou Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100016698","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.patcog.2026.114449","type":"journal-article","created":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T15:55:00Z","timestamp":1784303700000},"page":"114449","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PE","title":["PC2F: Language-guided Progressive Calibration and Cascade Filtering for Remote Sensing Visual Grounding"],"prefix":"10.1016","volume":"180","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7446-9336","authenticated-orcid":false,"given":"Long","family":"Sun","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhengyang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Licheng","family":"Jiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8780-5455","authenticated-orcid":false,"given":"Xu","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lingling","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoqiang","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuo","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaolin","family":"Tian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaowen","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"8","key":"10.1016\/j.patcog.2026.114449_b1","doi-asserted-by":"crossref","first-page":"5625","DOI":"10.1109\/TPAMI.2024.3369699","article-title":"Vision-language models for vision tasks: A survey","volume":"46","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.114449_b2","series-title":"Proceedings of the 38th International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume":"Vol. 139","author":"Radford","year":"2021"},{"key":"10.1016\/j.patcog.2026.114449_b3","series-title":"Proceedings of the 38th International Conference on Machine Learning","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume":"Vol. 139","author":"Jia","year":"2021"},{"key":"10.1016\/j.patcog.2026.114449_b4","doi-asserted-by":"crossref","first-page":"23716","DOI":"10.52202\/068431-1723","article-title":"Flamingo: a visual language model for few-shot learning","volume":"35","author":"Alayrac","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.114449_b5","doi-asserted-by":"crossref","unstructured":"O. Saha, G. Van Horn, S. Maji, Improved zero-shot classification by adapting vlms with text descriptions, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 17542\u201317552.","DOI":"10.1109\/CVPR52733.2024.01661"},{"key":"10.1016\/j.patcog.2026.114449_b6","doi-asserted-by":"crossref","unstructured":"X. Chen, J. Chen, Low-Sampling-Frequency Plane wave Medical Ultrasound Imaging based on Adversarial Learning, in: 2023 IEEE International Conference on Image Processing, ICIP, 2023, pp. 2085\u20132089.","DOI":"10.1109\/ICIP49359.2023.10222346"},{"issue":"3","key":"10.1016\/j.patcog.2026.114449_b7","doi-asserted-by":"crossref","first-page":"3273","DOI":"10.1109\/TITS.2024.3520893","article-title":"Repeated route naturalistic driver behavior analysis using motion and gaze measurements","volume":"26","author":"Adhikari","year":"2025","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.patcog.2026.114449_b8","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111583","article-title":"Layerlink: Bridging remote sensing object detection and large vision models with efficient fine-tuning","volume":"165","author":"Zhu","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114449_b9","series-title":"Computer Analysis of Images and Patterns","first-page":"281","article-title":"DADO: A depth-attention framework for object discovery","author":"Gonzalez","year":"2026"},{"key":"10.1016\/j.patcog.2026.114449_b10","doi-asserted-by":"crossref","unstructured":"A. Karpathy, L. Fei-Fei, Deep Visual-Semantic Alignments for Generating Image Descriptions, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015, pp. 3128\u20133137.","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"10.1016\/j.patcog.2026.114449_b11","doi-asserted-by":"crossref","unstructured":"Z. Yang, B. Gong, L. Wang, W. Huang, D. Yu, J. Luo, A fast and accurate one-stage approach to visual grounding, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019, pp. 4683\u20134693.","DOI":"10.1109\/ICCV.2019.00478"},{"key":"10.1016\/j.patcog.2026.114449_b12","doi-asserted-by":"crossref","unstructured":"L. Yu, Z. Lin, X. Shen, J. Yang, X. Lu, M. Bansal, T.L. Berg, MAttNet: Modular Attention Network for Referring Expression Comprehension, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 1307\u20131315.","DOI":"10.1109\/CVPR.2018.00142"},{"key":"10.1016\/j.patcog.2026.114449_b13","doi-asserted-by":"crossref","unstructured":"J. Deng, Z. Yang, T. Chen, W. Zhou, H. Li, Transvg: End-to-end visual grounding with transformers, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 1769\u20131779.","DOI":"10.1109\/ICCV48922.2021.00179"},{"key":"10.1016\/j.patcog.2026.114449_b14","first-page":"1","article-title":"Knowledge-aided momentum contrastive learning for remote-sensing image text retrieval","volume":"61","author":"Ji","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"issue":"3","key":"10.1016\/j.patcog.2026.114449_b15","doi-asserted-by":"crossref","first-page":"140","DOI":"10.1007\/s11263-026-02789-0","article-title":"Generative enhancement for 3D medical images: L. Zhu et al.","volume":"134","author":"Zhu","year":"2026","journal-title":"Int. J. Comput. Vis."},{"issue":"5","key":"10.1016\/j.patcog.2026.114449_b16","doi-asserted-by":"crossref","first-page":"3591","DOI":"10.1109\/TVCG.2025.3549563","article-title":"SplatLoc: 3D Gaussian splatting-based visual localization for augmented reality","volume":"31","author":"Zhai","year":"2025","journal-title":"IEEE Trans. Vis. Comput. Graphics"},{"key":"10.1016\/j.patcog.2026.114449_b17","doi-asserted-by":"crossref","unstructured":"Y. Sun, S. Feng, X. Li, Y. Ye, J. Kang, X. Huang, Visual grounding in remote sensing images, in: Proceedings of the 30th ACM International Conference on Multimedia, 2022, pp. 404\u2013412.","DOI":"10.1145\/3503161.3548316"},{"key":"10.1016\/j.patcog.2026.114449_b18","first-page":"1","article-title":"HiT: Building mapping with hierarchical transformers","volume":"62","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.patcog.2026.114449_b19","first-page":"1","article-title":"Generic knowledge boosted pretraining for remote sensing images","volume":"62","author":"Huang","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.patcog.2026.114449_b20","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.112961","article-title":"A YOLO-based polymerized head-auxiliary structures for target detection in remote sensing images","volume":"174","author":"Zhang","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114449_b21","first-page":"1","article-title":"Progressive feature interleaved fusion network for remote-sensing image salient object detection","volume":"62","author":"Han","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.patcog.2026.114449_b22","first-page":"1","article-title":"TERNformer: Topology-enhanced road network extraction by exploring local connectivity","volume":"61","author":"Wang","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.patcog.2026.114449_b23","first-page":"1","article-title":"G2HFNet: GeoGran-aware hierarchical feature fusion network for salient object detection in optical remote sensing images","author":"Wan","year":"2026","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.patcog.2026.114449_b24","first-page":"1","article-title":"Dual-stage prior-driven diffusion model for remote sensing spectral super-resolution","volume":"63","author":"Li","year":"2025","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.patcog.2026.114449_b25","doi-asserted-by":"crossref","first-page":"18727","DOI":"10.1109\/JSTARS.2024.3471625","article-title":"A lightweight sparse focus transformer for remote sensing image change captioning","volume":"17","author":"Sun","year":"2024","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"10.1016\/j.patcog.2026.114449_b26","first-page":"1","article-title":"RSVG: Exploring data and models for visual grounding on remote sensing data","volume":"61","author":"Zhan","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.patcog.2026.114449_b27","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TGRS.2024.3407598","article-title":"Language query-based transformer with multiscale cross-modal alignment for visual grounding on remote sensing images","volume":"62","author":"Lan","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.patcog.2026.114449_b28","first-page":"1","article-title":"Language-guided progressive attention for visual grounding in remote sensing images","volume":"62","author":"Li","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.patcog.2026.114449_b29","doi-asserted-by":"crossref","DOI":"10.1109\/TGRS.2025.3622554","article-title":"Language-guided progressive query refinement with diffusion model for visual grounding on remote sensing images","author":"Tang","year":"2025","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.patcog.2026.114449_b30","first-page":"1","article-title":"MSDformer: Multiscale deformable transformer for hyperspectral image super-resolution","volume":"61","author":"Chen","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.patcog.2026.114449_b31","first-page":"1","article-title":"Contrastive tokens and label activation for remote sensing weakly supervised semantic segmentation","volume":"62","author":"Hu","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.patcog.2026.114449_b32","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2026.113120","article-title":"Towards open-vocabulary semantic segmentation for remote sensing images","volume":"175","author":"Zhang","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114449_b33","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"11","key":"10.1016\/j.patcog.2026.114449_b34","doi-asserted-by":"crossref","first-page":"13636","DOI":"10.1109\/TPAMI.2023.3296823","article-title":"Transvg++: End-to-end visual grounding with language conditioned vision transformer","volume":"45","author":"Deng","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.114449_b35","doi-asserted-by":"crossref","unstructured":"L. Yang, Y. Xu, C. Yuan, W. Liu, B. Li, W. Hu, Improving visual grounding with visual-linguistic verification and iterative reasoning, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 9499\u20139508.","DOI":"10.1109\/CVPR52688.2022.00928"},{"key":"10.1016\/j.patcog.2026.114449_b36","first-page":"1","article-title":"EarthGPT-X: A spatial MLLM for multilevel multisource remote sensing imagery understanding with visual prompting","volume":"63","author":"Zhang","year":"2025","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.patcog.2026.114449_b37","doi-asserted-by":"crossref","unstructured":"K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"10.1016\/j.patcog.2026.114449_b38","series-title":"Proceedings of NaacL-HLT","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume":"Vol. 1","author":"Kenton","year":"2019"},{"key":"10.1016\/j.patcog.2026.114449_b39","series-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"10.1016\/j.patcog.2026.114449_b40","series-title":"European Conference on Computer Vision","first-page":"387","article-title":"Improving one-stage visual grounding by recursive sub-query construction","author":"Yang","year":"2020"},{"key":"10.1016\/j.patcog.2026.114449_b41","doi-asserted-by":"crossref","unstructured":"B. Huang, D. Lian, W. Luo, S. Gao, Look before you leap: Learning landmark features for one-stage visual grounding, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 16888\u201316897.","DOI":"10.1109\/CVPR46437.2021.01661"},{"key":"10.1016\/j.patcog.2026.114449_b42","doi-asserted-by":"crossref","unstructured":"J. Ye, J. Tian, M. Yan, X. Yang, X. Wang, J. Zhang, L. He, X. Lin, Shifting more attention to visual backbone: Query-modulated refinement networks for end-to-end visual grounding, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 15502\u201315512.","DOI":"10.1109\/CVPR52688.2022.01506"},{"key":"10.1016\/j.patcog.2026.114449_b43","first-page":"1","article-title":"Multistage synergistic aggregation network for remote sensing visual grounding","volume":"21","author":"Wang","year":"2024","journal-title":"IEEE Geosci. Remote. Sens. Lett."},{"key":"10.1016\/j.patcog.2026.114449_b44","article-title":"Efficient grounding DINO: Efficient cross-modality fusion and efficient label assignment for visual grounding in remote sensing","author":"Hu","year":"2025","journal-title":"IEEE Trans. Geosci. Remote Sens."}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326014147?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326014147?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T13:25:16Z","timestamp":1788182716000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326014147"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":44,"alternative-id":["S0031320326014147"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114449","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"PCF: Language-guided Progressive Calibration and Cascade Filtering for Remote Sensing Visual Grounding","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114449","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"114449"}}