{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T14:08:43Z","timestamp":1780495723401,"version":"3.54.1"},"reference-count":47,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62306241"],"award-info":[{"award-number":["62306241"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62576284"],"award-info":[{"award-number":["62576284"]}],"id":[{"id":"10.13039\/501100001809","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":[[2026,11]]},"DOI":"10.1016\/j.patcog.2026.113579","type":"journal-article","created":{"date-parts":[[2026,3,22]],"date-time":"2026-03-22T22:56:24Z","timestamp":1774220184000},"page":"113579","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PA","title":["Hierarchical textual-visual guidance for referring remote sensing segmentation"],"prefix":"10.1016","volume":"179","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-8177-9165","authenticated-orcid":false,"given":"Shiyu","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3300-0805","authenticated-orcid":false,"given":"Qing","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7028-4956","authenticated-orcid":false,"given":"Qi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1860-3275","authenticated-orcid":false,"given":"Yuan","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6000-8168","authenticated-orcid":false,"given":"Junyu","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.113579_bib0001","article-title":"RRSIS: referring remote sensing image segmentation","author":"Yuan","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.patcog.2026.113579_bib0002","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2020.114417","article-title":"A review of deep learning methods for semantic segmentation of remote sensing imagery","author":"Yuan","year":"2021","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.patcog.2026.113579_bib0003","doi-asserted-by":"crossref","first-page":"4940","DOI":"10.1109\/TPAMI.2025.3546356","article-title":"Reliable representation learning for incomplete multi-view missing multi-label classification","volume":"47","author":"Liu","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113579_bib0004","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","first-page":"108","article-title":"Segmentation from natural language expressions","author":"Hu","year":"2016"},{"key":"10.1016\/j.patcog.2026.113579_bib0005","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"10502","article-title":"Cross-modal self-attention network for referring image segmentation","author":"Ye","year":"2019"},{"key":"10.1016\/j.patcog.2026.113579_bib0006","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"18155","article-title":"LAVT: language-aware vision transformer for referring image segmentation","author":"Yang","year":"2022"},{"key":"10.1016\/j.patcog.2026.113579_bib0007","series-title":"International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.patcog.2026.113579_bib0008","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"11686","article-title":"CRIS: CLIP-driven referring image segmentation","author":"Wang","year":"2022"},{"key":"10.1016\/j.patcog.2026.113579_bib0009","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"26658","article-title":"Rotated multi-scale interaction network for referring remote sensing image segmentation","author":"Liu","year":"2024"},{"key":"10.1016\/j.patcog.2026.113579_bib0010","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TGRS.2024.3508136","article-title":"Exploring fine-grained image-text alignment for referring remote sensing image segmentation","volume":"63","author":"Lei","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.patcog.2026.113579_bib0011","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"1271","article-title":"Recurrent multimodal interaction for referring image segmentation","author":"Liu","year":"2017"},{"key":"10.1016\/j.patcog.2026.113579_bib0012","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"5745","article-title":"Referring image segmentation via recurrent refinement networks","author":"Li","year":"2018"},{"key":"10.1016\/j.patcog.2026.113579_bib0013","series-title":"Proceedings of the 28th ACM International Conference on Multimedia","first-page":"1274","article-title":"Cascade grouped attention network for referring expression segmentation","author":"Luo","year":"2020"},{"key":"10.1016\/j.patcog.2026.113579_bib0014","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","article-title":"Bi-directional relationship inferring network for referring image segmentation","author":"Hu","year":"2020"},{"key":"10.1016\/j.patcog.2026.113579_bib0015","series-title":"ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"2020","article-title":"Deep object detection with example attribute based prediction modulation","author":"Wu","year":"2022"},{"key":"10.1016\/j.patcog.2026.113579_bib0016","first-page":"19652","article-title":"Referring transformer: a one-step approach to multi-task visual grounding","volume":"34","author":"Li","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.113579_bib0017","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"4974","article-title":"Language as queries for referring video object segmentation","author":"Wu","year":"2022"},{"key":"10.1016\/j.patcog.2026.113579_bib0018","unstructured":"A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, M. Dehghani, M. Minderer, G. Heigold, S. Gelly, et al., An image is worth 16x16 words: transformers for image recognition at scale, arXiv preprint arXiv: 2010.11929(2020)."},{"key":"10.1016\/j.patcog.2026.113579_bib0019","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"10012","article-title":"Swin transformer: hierarchical vision transformer using shifted windows","author":"Liu","year":"2021"},{"key":"10.1016\/j.patcog.2026.113579_bib0020","first-page":"14729","article-title":"CoupAlign: coupling word-pixel with sentence-mask alignments for referring image segmentation","volume":"35","author":"Zhang","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.113579_bib0021","unstructured":"B. Chen, Z. Hu, Z. Ji, J. Bai, W. Zuo, Position-aware contrastive alignment for referring image segmentation, arXiv preprint arXiv: 2212.13419(2022)."},{"key":"10.1016\/j.patcog.2026.113579_bib0022","unstructured":"T. Zhang, Z. Wen, B. Kong, K. Liu, Y. Zhang, P. Zhuang, J. Li, Referring remote sensing image segmentation via bidirectional alignment guided joint prediction, arXiv preprint arXiv: 2502.08486(2025)."},{"key":"10.1016\/j.patcog.2026.113579_bib0023","unstructured":"Z. Yang, H. Yao, L. Tian, X. Zhao, Q. Li, Q. Wang, A large-scale referring remote sensing image segmentation dataset and benchmark, arXiv preprint arXiv: 2506.03583(2025)."},{"key":"10.1016\/j.patcog.2026.113579_bib0024","doi-asserted-by":"crossref","unstructured":"K. Chen, J. Zhang, C. Liu, Z. Zou, Z. Shi, RSRefSeg: referring remote sensing image segmentation with foundation models, arXiv preprint arXiv: 2501.06809(2025).","DOI":"10.1109\/IGARSS55030.2025.11243338"},{"key":"10.1016\/j.patcog.2026.113579_bib0025","unstructured":"B. Li, H. Dong, D. Zhang, Z. Zhao, J. Gao, X. Li, Exploring efficient open-vocabulary segmentation in the remote sensing, arXiv preprint arXiv: 2509.12040(2025)."},{"key":"10.1016\/j.patcog.2026.113579_bib0026","doi-asserted-by":"crossref","unstructured":"Z. Dong, Y. Sun, T. Liu, Y. Gu, DiffRIS: enhancing referring remote sensing image segmentation with pre-trained text-to-image diffusion models, arXiv preprint arXiv: 2506.18946(2025).","DOI":"10.1016\/j.fmre.2025.11.017"},{"key":"10.1016\/j.patcog.2026.113579_bib0027","unstructured":"J. Yang, L. Zhang, H. Lu, Referring remote sensing image segmentation with cross-view semantics interaction network, arXiv preprint arXiv: 2508.01331(2025)."},{"key":"10.1016\/j.patcog.2026.113579_bib0028","doi-asserted-by":"crossref","first-page":"6906","DOI":"10.1109\/TMM.2024.3358085","article-title":"CM-MaskSD: cross-modality masked self-distillation for referring image segmentation","volume":"26","author":"Wang","year":"2024","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.patcog.2026.113579_bib0029","series-title":"Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","first-page":"4611","article-title":"Extending clip\u2019s image-text alignment to referring image segmentation","author":"Kim","year":"2024"},{"key":"10.1016\/j.patcog.2026.113579_bib0030","series-title":"International Conference on Machine Learning","first-page":"19730","article-title":"BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023"},{"key":"10.1016\/j.patcog.2026.113579_bib0031","unstructured":"D. Zhu, J. Chen, X. Shen, X. Li, M. Elhoseiny, MiniGPT-4: enhancing vision-language understanding with advanced large language models, arXiv preprint arXiv: 2304.10592(2023)."},{"key":"10.1016\/j.patcog.2026.113579_bib0032","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"9579","article-title":"LISA: reasoning segmentation via large language model","author":"Lai","year":"2024"},{"key":"10.1016\/j.patcog.2026.113579_bib0033","doi-asserted-by":"crossref","first-page":"6833","DOI":"10.52202\/079017-0219","article-title":"One token to seg them all: language instructed reasoning segmentation in videos","volume":"37","author":"Bai","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.113579_bib0034","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"26374","article-title":"PixelLM: pixel reasoning with large multimodal model","author":"Ren","year":"2024"},{"key":"10.1016\/j.patcog.2026.113579_bib0035","unstructured":"T. Ren, S. Liu, A. Zeng, J. Lin, K. Li, H. Cao, J. Chen, X. Huang, Y. Chen, F. Yan, et al., Grounded sam: assembling open-world models for diverse visual tasks, arXiv preprint arXiv: 2401.14159(2024b)."},{"key":"10.1016\/j.patcog.2026.113579_bib0036","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"4015","article-title":"Segment anything","author":"Kirillov","year":"2023"},{"key":"10.1016\/j.patcog.2026.113579_bib0037","unstructured":"P. Wang, S. Bai, S. Tan, S. Wang, Z. Fan, J. Bai, K. Chen, X. Liu, J. Wang, W. Ge, et al., Qwen2-VL: enhancing vision-language model\u2019s perception of the world at any resolution, arXiv preprint arXiv: 2409.12191(2024)."},{"key":"10.1016\/j.patcog.2026.113579_bib0038","series-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)","first-page":"4171","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"key":"10.1016\/j.patcog.2026.113579_bib0039","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.113579_bib0040","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"13733","article-title":"RepVGG: making VGG-style convnets great again","author":"Ding","year":"2021"},{"key":"10.1016\/j.patcog.2026.113579_bib0041","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","first-page":"59","article-title":"Linguistic structure guided context modeling for referring image segmentation","author":"Hui","year":"2020"},{"key":"10.1016\/j.patcog.2026.113579_bib0042","doi-asserted-by":"crossref","unstructured":"S. Huang, T. Hui, S. Liu, G. Li, Y. Wei, J. Han, L. Liu, B. Li, Referring image segmentation via cross-modal progressive comprehension in: Proceedings 29 of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition(2020) pp. 10488\u201310497.","DOI":"10.1109\/CVPR42600.2020.01050"},{"key":"10.1016\/j.patcog.2026.113579_bib0043","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"4424","article-title":"Bi-directional relationship inferring network for referring image segmentation","author":"Hu","year":"2020"},{"issue":"9","key":"10.1016\/j.patcog.2026.113579_bib0044","first-page":"4761","article-title":"Cross-modal progressive compre hension for referring segmentation","volume":"44","author":"Liu","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113579_bib0045","doi-asserted-by":"crossref","first-page":"5823","DOI":"10.1109\/TMM.2023.3340062","article-title":"Cross-aware early fusion with stage-divided vision and language transformer encoders for referring image segmentation","volume":"26","author":"Cho","year":"2023","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.patcog.2026.113579_bib0046","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"5729","article-title":"Unleashing text-to-image diffusion models for visual perception","author":"Zhao","year":"2023"},{"key":"10.1016\/j.patcog.2026.113579_bib0047","unstructured":"Y. Zhang, T. Cheng, L. Zhu, R. Hu, L. Liu, H. Liu, L. Ran, X. Chen, W. Liu, X. Wang, EVF-SAM: early vision-language fusion for text-prompted segment anything model, arXiv preprint arXiv: 2406.20076(2024)."}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326005455?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326005455?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T13:08:55Z","timestamp":1780492135000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326005455"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":47,"alternative-id":["S0031320326005455"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113579","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Hierarchical textual-visual guidance for referring remote sensing segmentation","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113579","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":"113579"}}