{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T17:20:35Z","timestamp":1783099235213,"version":"3.54.6"},"reference-count":54,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"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":["62403404"],"award-info":[{"award-number":["62403404"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100009110","name":"Xinjiang Uygur Autonomous Region Natural Science Foundation","doi-asserted-by":"publisher","award":["2024D01C238"],"award-info":[{"award-number":["2024D01C238"]}],"id":[{"id":"10.13039\/100009110","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2024M762716"],"award-info":[{"award-number":["2024M762716"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems with Applications"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.eswa.2026.132953","type":"journal-article","created":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T15:14:55Z","timestamp":1779290095000},"page":"132953","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["RSHR+: Progressive question-conditioned visual calibration and structured state-space reasoning for remote sensing visual question answering"],"prefix":"10.1016","volume":"328","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-8655-7672","authenticated-orcid":false,"given":"Pengfei","family":"Xu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8615-139X","authenticated-orcid":false,"given":"Feng","family":"Yan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-8608-0956","authenticated-orcid":false,"given":"Yuqing","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0210-2273","authenticated-orcid":false,"given":"Yuancheng","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4089-2484","authenticated-orcid":false,"given":"Chuanrui","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.eswa.2026.132953_bib0001","series-title":"Proceedings of the 2023 Conference on empirical methods in natural language processing","first-page":"4895","article-title":"GQA: Training generalized multi-query transformer models from multi-head checkpoints","author":"Ainslie","year":"2023"},{"key":"10.1016\/j.eswa.2026.132953_bib0002","unstructured":"Bai, S., Cai, Y., Chen, R., Chen, K., Chen, X., Cheng, Z., Deng, L., Ding, W., Gao, C., Ge, C. et al. (2025). Qwen3-vl technical report. arXiv preprint arXiv: 2511.21631."},{"key":"10.1016\/j.eswa.2026.132953_bib0003","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TGRS.2022.3192460","article-title":"Bi-modal transformer-based approach for visual question answering in remote sensing imagery","volume":"60","author":"Bazi","year":"2022","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"issue":"9","key":"10.1016\/j.eswa.2026.132953_bib0004","doi-asserted-by":"crossref","first-page":"1477","DOI":"10.3390\/rs16091477","article-title":"Rs-LLAVA: A large vision-language model for joint captioning and question answering in remote sensing imagery","volume":"16","author":"Bazi","year":"2024","journal-title":"Remote Sensing"},{"key":"10.1016\/j.eswa.2026.132953_bib0005","unstructured":"Beyer, L., Steiner, A., Pinto, A. S., Kolesnikov, A., Wang, X., Salz, D., Neumann, M., Alabdulmohsin, I., Tschannen, M., Bugliarello, E. et al. (2024). Paligemma: A versatile 3b VLM for transfer. arXiv preprint arXiv: 2407.07726."},{"key":"10.1016\/j.eswa.2026.132953_bib0006","unstructured":"Cao, L., Chen, H., Fan, X., Gama, J., Ong, Y.-S., & Kumar, V. (2023). Bayesian federated learning: A survey. arXiv preprint arXiv: 2304.13267."},{"key":"10.1016\/j.eswa.2026.132953_bib0007","article-title":"Federated neural nonparametric point processes","author":"Chen","year":"2025","journal-title":"Artificial Intelligence"},{"issue":"9","key":"10.1016\/j.eswa.2026.132953_bib0008","doi-asserted-by":"crossref","first-page":"16975","DOI":"10.1109\/TNNLS.2025.3562164","article-title":"Fedsi: Federated subnetwork inference for efficient uncertainty quantification","volume":"36","author":"Chen","year":"2025","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.1016\/j.eswa.2026.132953_bib0009","first-page":"1","article-title":"Changemamba: Remote sensing change detection with spatiotemporal state space model","volume":"62","author":"Chen","year":"2024","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"10.1016\/j.eswa.2026.132953_bib0010","unstructured":"Chen, J., Xu, Z., Pan, X., Hu, Y., Qin, C., Goldstein, T., Huang, L., Zhou, T., Xie, S., Savarese, S. et al. (2025c). Blip3-o: A family of fully open unified multimodal models-architecture, training and dataset. arXiv preprint arXiv: 2505.09568."},{"key":"10.1016\/j.eswa.2026.132953_bib0011","unstructured":"Chen, Z., Wang, W., Cao, Y., Liu, Y., Gao, Z., Cui, E., Zhu, J., Ye, S., Tian, H., Liu, Z. et al. (2024b). Expanding performance boundaries of open-source multimodal models with model, data, and test-time scaling. arXiv preprint arXiv: 2412.05271."},{"key":"10.1016\/j.eswa.2026.132953_bib0012","doi-asserted-by":"crossref","first-page":"49250","DOI":"10.52202\/075280-2142","article-title":"Instructblip: Towards general-purpose vision-language models with instruction tuning","volume":"36","author":"Dai","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.132953_bib0013","unstructured":"Dao, T. (2023). Flashattention-2: Faster attention with better parallelism and work partitioning. arXiv preprint arXiv: 2307.08691."},{"key":"10.1016\/j.eswa.2026.132953_bib0014","unstructured":"Dao, T., & Gu, A. (2024). Transformers are ssms: Generalized models and efficient algorithms through structured state space duality. arXiv preprint arXiv: 2405.21060."},{"key":"10.1016\/j.eswa.2026.132953_bib0015","unstructured":"Grattafiori, A., Dubey, A., Jauhri, A., Pandey, A., Kadian, A., Al-Dahle, A., Letman, A., Mathur, A., Schelten, A., Vaughan, A. et al. (2024). The LLAMA 3 herd of models. arXiv preprint arXiv: 2407.21783."},{"key":"10.1016\/j.eswa.2026.132953_bib0016","series-title":"First conference on language modeling","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2024"},{"key":"10.1016\/j.eswa.2026.132953_bib0017","unstructured":"Gu, A., Johnson, I., Timalsina, A., Rudra, A., & R\u00e9, C. (2022). How to train your hippo: State space models with generalized orthogonal basis projections. arXiv preprint arXiv: 2206.12037."},{"key":"10.1016\/j.eswa.2026.132953_bib0018","series-title":"Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition","first-page":"27672","article-title":"SkySense: A multi-modal remote sensing foundation model towards universal interpretation for earth observation imagery","author":"Guo","year":"2024"},{"key":"10.1016\/j.eswa.2026.132953_bib0019","doi-asserted-by":"crossref","first-page":"272","DOI":"10.1016\/j.isprsjprs.2025.03.028","article-title":"RSGPT: A remote sensing vision language model and benchmark","volume":"224","author":"Hu","year":"2025","journal-title":"ISPRS Journal of Photogrammetry and Remote Sensing"},{"key":"10.1016\/j.eswa.2026.132953_bib0020","series-title":"International conference on machine learning","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","author":"Jia","year":"2021"},{"key":"10.1016\/j.eswa.2026.132953_bib0021","series-title":"Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition","first-page":"27831","article-title":"Geochat: Grounded large vision-language model for remote sensing","author":"Kuckreja","year":"2024"},{"key":"10.1016\/j.eswa.2026.132953_bib0022","unstructured":"Li, B., Zhang, Y., Guo, D., Zhang, R., Li, F., Zhang, H., Zhang, K., Zhang, P., Li, Y., Liu, Z. et al. (2024a). Llava-onevision: Easy visual task transfer. arXiv preprint arXiv: 2408.03326."},{"key":"10.1016\/j.eswa.2026.132953_bib0023","series-title":"International conference on machine learning","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","author":"Li","year":"2022"},{"key":"10.1016\/j.eswa.2026.132953_bib0024","article-title":"SearchExpert: A genAI-driven framework for reasoning-intensive multimedia information fusion through fine-tuning and reinforcement learning","author":"Li","year":"2025","journal-title":"Information Fusion"},{"key":"10.1016\/j.eswa.2026.132953_bib0025","doi-asserted-by":"crossref","first-page":"16799","DOI":"10.1109\/JSTARS.2024.3419035","article-title":"RSMoDM: Multimodal momentum distillation model for remote sensing visual question answering","volume":"17","author":"Li","year":"2024","journal-title":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing"},{"key":"10.1016\/j.eswa.2026.132953_bib0026","first-page":"1","article-title":"Enhancing remote sensing visual question answering: A mask-based dual-stream feature mutual attention network","volume":"21","author":"Li","year":"2024","journal-title":"IEEE Geoscience and Remote Sensing Letters"},{"key":"10.1016\/j.eswa.2026.132953_bib0027","series-title":"Advances in neural information processing systems","article-title":"Visual instruction tuning. advances in neural information processing systems","volume":"vol. 36","author":"Liu","year":"2023"},{"key":"10.1016\/j.eswa.2026.132953_bib0028","doi-asserted-by":"crossref","first-page":"103031","DOI":"10.52202\/079017-3273","article-title":"VMamba: Visual state space model","volume":"37","author":"Liu","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"12","key":"10.1016\/j.eswa.2026.132953_bib0029","doi-asserted-by":"crossref","first-page":"8555","DOI":"10.1109\/TGRS.2020.2988782","article-title":"RSVQA: Visual question answering for remote sensing data","volume":"58","author":"Lobry","year":"2020","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"10.1016\/j.eswa.2026.132953_bib0030","unstructured":"Luo, J., Pang, Z., Zhang, Y., Wang, T., Wang, L., Dang, B., Lao, J., Wang, J., Chen, J., Tan, Y. et al. (2024). SkySenseGPT: A fine-grained instruction tuning dataset and model for remote sensing vision-language understanding. arXiv preprint arXiv: 2406.10100."},{"key":"10.1016\/j.eswa.2026.132953_bib0031","series-title":"European conference on computer vision","first-page":"440","article-title":"Lhrs-bot: Empowering remote sensing with vgi-enhanced large multimodal language model","author":"Muhtar","year":"2024"},{"key":"10.1016\/j.eswa.2026.132953_bib0032","series-title":"Proceedings of the AAAI Conference on artificial intelligence","first-page":"6381","article-title":"VHM: Versatile and honest vision language model for remote sensing image analysis","volume":"vol. 39","author":"Pang","year":"2025"},{"key":"10.1016\/j.eswa.2026.132953_bib0033","doi-asserted-by":"crossref","first-page":"89644","DOI":"10.1109\/ACCESS.2021.3090981","article-title":"FloodNet: A high resolution aerial imagery dataset for post flood scene understanding","volume":"9","author":"Rahnemoonfar","year":"2021","journal-title":"IEEE Access"},{"key":"10.1016\/j.eswa.2026.132953_bib0034","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TGRS.2023.3276293","article-title":"SAM-VQA: Supervised attention-based visual question answering model for post-disaster damage assessment on remote sensing imagery","volume":"61","author":"Sarkar","year":"2023","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"10.1016\/j.eswa.2026.132953_bib0035","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2023.127063","article-title":"Roformer: Enhanced transformer with rotary position embedding","volume":"568","author":"Su","year":"2024","journal-title":"Neurocomputing"},{"issue":"3","key":"10.1016\/j.eswa.2026.132953_bib0036","doi-asserted-by":"crossref","first-page":"3154","DOI":"10.1109\/TPAMI.2025.3635844","article-title":"Learning task-preferred inference routes for gradient de-conflict in multi-output dnns","volume":"48","author":"Sun","year":"2025","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.eswa.2026.132953_bib0037","first-page":"1-1","article-title":"FedKT: A nature-inspired Bayesian federated learning framework for privacy-preserving and lightweight consumer devices","author":"Tian","year":"2026","journal-title":"IEEE Transactions on Consumer Electronics"},{"key":"10.1016\/j.eswa.2026.132953_bib0038","unstructured":"Tschannen, M., Gritsenko, A., Wang, X., Naeem, M. F., Alabdulmohsin, I., Parthasarathy, N., Evans, T., Beyer, L., Xia, Y., Mustafa, B. et al. (2025). SigLIP 2: Multilingual vision-language encoders with improved semantic understanding, localization, and dense features. arXiv preprint arXiv: 2502.14786."},{"key":"10.1016\/j.eswa.2026.132953_bib0039","unstructured":"Wang, F., Wang, Y., Chen, M., Zhao, H., Sun, Y., Wang, S., Wang, H., Wang, D., Lan, L., Yang, W. et al. (2025a). Roma: Scaling up mamba-based foundation models for remote sensing. arXiv preprint arXiv: 2503.10392."},{"key":"10.1016\/j.eswa.2026.132953_bib0040","first-page":"1","article-title":"Gradient decoupling guided network for high-resolution remote sensing segmentation","volume":"63","author":"Wang","year":"2025","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"10.1016\/j.eswa.2026.132953_bib0041","doi-asserted-by":"crossref","DOI":"10.1016\/j.array.2025.100445","article-title":"Raft: Robust adversarial fusion transformer for multimodal sentiment analysis","author":"Wang","year":"2025","journal-title":"Array"},{"key":"10.1016\/j.eswa.2026.132953_bib0042","first-page":"1","article-title":"Rsadapter: Adapting multimodal models for remote sensing visual question answering","volume":"62","author":"Wang","year":"2024","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"10.1016\/j.eswa.2026.132953_bib0043","doi-asserted-by":"crossref","first-page":"1783","DOI":"10.1109\/TMM.2024.3521798","article-title":"Frequency-assisted mamba for remote sensing image super-resolution","volume":"27","author":"Xiao","year":"2024","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.eswa.2026.132953_bib0044","doi-asserted-by":"crossref","first-page":"738","DOI":"10.1109\/TIP.2023.3349004","article-title":"Ttst: A top-k token selective transformer for remote sensing image super-resolution","volume":"33","author":"Xiao","year":"2024","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.eswa.2026.132953_bib0045","doi-asserted-by":"crossref","first-page":"3789","DOI":"10.1007\/s10994-023-06426-6","article-title":"Knowledge-aware image understanding with multi-level visual representation enhancement for visual question answering","volume":"113","author":"Yan","year":"2024","journal-title":"Machine Learning"},{"key":"10.1016\/j.eswa.2026.132953_bib0046","series-title":"Proc. IEEE conf. comput. vis. pattern recognit. (CVPR)","article-title":"Stacked attention networks for image question answering","author":"Yang","year":"2016"},{"key":"10.1016\/j.eswa.2026.132953_bib0047","first-page":"1","article-title":"From easy to hard: Learning language-guided curriculum for visual question answering on remote sensing data","volume":"60","author":"Yuan","year":"2022","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"10.1016\/j.eswa.2026.132953_bib0048","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"11975","article-title":"Sigmoid loss for language image pre-training","author":"Zhai","year":"2023"},{"key":"10.1016\/j.eswa.2026.132953_bib0049","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1016\/j.isprsjprs.2025.01.020","article-title":"Skyeyegpt: Unifying remote sensing vision-language tasks via instruction tuning with large language model","volume":"221","author":"Zhan","year":"2025","journal-title":"ISPRS Journal of Photogrammetry and Remote Sensing"},{"key":"10.1016\/j.eswa.2026.132953_bib0050","first-page":"1","article-title":"CdMamba: Incorporating local clues into Mamba for remote sensing image binary change detection","volume":"63","author":"Zhang","year":"2025","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"issue":"5","key":"10.1016\/j.eswa.2026.132953_bib0051","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1109\/MIS.2025.3597120","article-title":"A generative random modality dropout framework for robust multimodal emotion recognition","volume":"40","author":"Zhang","year":"2025","journal-title":"IEEE Intelligent Systems"},{"key":"10.1016\/j.eswa.2026.132953_bib0052","first-page":"1","article-title":"A spatial hierarchical reasoning network for remote sensing visual question answering","volume":"61","author":"Zhang","year":"2023","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"10.1016\/j.eswa.2026.132953_bib0053","first-page":"1","article-title":"Visual-grounded hierarchical perception for remote sensing visual question answering","volume":"63","author":"Zhang","year":"2025","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"10.1016\/j.eswa.2026.132953_bib0054","doi-asserted-by":"crossref","DOI":"10.1016\/j.cmpb.2024.108564","article-title":"A client\u2013server based recognition system: Non-contact single\/multiple emotional and behavioral state assessment methods","volume":"260","author":"Zhu","year":"2025","journal-title":"Computer Methods and Programs in Biomedicine"}],"container-title":["Expert Systems with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426018658?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426018658?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T16:41:16Z","timestamp":1783096876000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0957417426018658"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":54,"alternative-id":["S0957417426018658"],"URL":"https:\/\/doi.org\/10.1016\/j.eswa.2026.132953","relation":{},"ISSN":["0957-4174"],"issn-type":[{"value":"0957-4174","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"RSHR+: Progressive question-conditioned visual calibration and structured state-space reasoning for remote sensing visual question answering","name":"articletitle","label":"Article Title"},{"value":"Expert Systems with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.eswa.2026.132953","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":"132953"}}