{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T23:49:23Z","timestamp":1791935363697,"version":"4.3.4"},"reference-count":74,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2024YFF0509600"],"award-info":[{"award-number":["2024YFF0509600"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62373302"],"award-info":[{"award-number":["62373302"]}],"id":[{"id":"10.13039\/501100001809","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":[[2027,1]]},"DOI":"10.1016\/j.eswa.2026.133552","type":"journal-article","created":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:23:29Z","timestamp":1783437809000},"page":"133552","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PB","title":["Advancing image-to-text: MDE-net coupled with large language models for context-aware captioning"],"prefix":"10.1016","volume":"332","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-0540-4938","authenticated-orcid":false,"given":"Yang","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1803-3946","authenticated-orcid":false,"given":"Dengxiu","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5451-7230","authenticated-orcid":false,"given":"C.L. Philip","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.eswa.2026.133552_bib0001","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision (ICCV)","article-title":"Nocaps: Novel object captioning at scale","author":"Agrawal","year":"2019"},{"key":"10.1016\/j.eswa.2026.133552_bib0002","doi-asserted-by":"crossref","first-page":"63671","DOI":"10.1109\/ACCESS.2025.3552217","article-title":"Balanced-simplified spatiotemporal memory attention for image captioning","volume":"13","author":"Al-Qatf","year":"2025","journal-title":"IEEE Access"},{"key":"10.1016\/j.eswa.2026.133552_bib0003","unstructured":"Bai, J., Bai, S., Chu, Y., Cui, Z., Dang, K., Deng, X., Fan, Y., Ge, W., Han, Y., Huang, F. et al. (2025). Qwen technical report, Applied Intelligence, 55, 78. arXiv preprint arXiv: 2309.16609, 10.1007\/s10489-024-05883-3."},{"key":"10.1016\/j.eswa.2026.133552_bib0004","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"4662","article-title":"The unreasonable effectiveness of CLIP features for image captioning: An experimental analysis","author":"Barraco","year":"2022"},{"key":"10.1016\/j.eswa.2026.133552_bib0005","series-title":"2024\u202fIEEE International conference on image processing (ICIP)","first-page":"2550","article-title":"Distinctive image captioning: Leveraging ground truth captions in clip guided reinforcement learning","author":"Chaffin","year":"2024"},{"key":"10.1016\/j.eswa.2026.133552_bib0006","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"6097","article-title":"Bracketing image restoration and enhancement with high-low frequency decomposition","author":"Chen","year":"2024"},{"key":"10.1016\/j.eswa.2026.133552_bib0007","unstructured":"Chen, T., Zhang, R., & Hinton, G. (2022a). Analog bits: Generating discrete data using diffusion models with self-conditioning. arXiv: 2208."},{"issue":"3","key":"10.1016\/j.eswa.2026.133552_bib0008","first-page":"2359","article-title":"An object detection network based on YOLOv4 and improved spatial attention mechanism","volume":"42","author":"Chen","year":"2022","journal-title":"Journal of Intelligent & Fuzzy Systems"},{"key":"10.1016\/j.eswa.2026.133552_bib0009","first-page":"1","article-title":"NWPU-captions dataset and MLCA-Net for remote sensing image captioning","volume":"60","author":"Cheng","year":"2022","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"10.1016\/j.eswa.2026.133552_bib0010","series-title":"Proceedings of the 31st ACM international conference on multimedia","first-page":"1179","article-title":"Frequency perception network for camouflaged object detection","author":"Cong","year":"2023"},{"key":"10.1016\/j.eswa.2026.133552_bib0011","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"10578","article-title":"Meshed-memory transformer for image captioning","author":"Cornia","year":"2020"},{"key":"10.1016\/j.eswa.2026.133552_bib0012","article-title":"Migcl: Fake news detection with multimodal interaction and graph contrastive learning networks","volume":"55","author":"Cui","year":"2024","journal-title":"Applied Intelligence"},{"key":"10.1016\/j.eswa.2026.133552_bib0013","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.127886","article-title":"MRMNet: Multi-scale residual multi-branch neural network for object detection","volume":"596","author":"Dong","year":"2024","journal-title":"Neurocomputing"},{"key":"10.1016\/j.eswa.2026.133552_bib0014","series-title":"Proceedings of the international conference on learning representations","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021"},{"key":"10.1016\/j.eswa.2026.133552_bib0015","doi-asserted-by":"crossref","first-page":"812","DOI":"10.1016\/j.ins.2022.12.018","article-title":"Label-attention transformer with geometrically coherent objects for image captioning","volume":"623","author":"Dubey","year":"2023","journal-title":"Information Sciences"},{"key":"10.1016\/j.eswa.2026.133552_bib0016","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"18009","article-title":"Injecting semantic concepts into end-to-end image captioning","author":"Fang","year":"2022"},{"key":"10.1016\/j.eswa.2026.133552_bib0017","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"1317","article-title":"Memory-augmented image captioning","volume":"vol. 35","author":"Fei","year":"2021"},{"key":"10.1016\/j.eswa.2026.133552_bib0018","doi-asserted-by":"crossref","first-page":"56","DOI":"10.18653\/v1\/W17-3207","article-title":"Beam search strategies for neural machine translation","author":"Freitag","year":"2017","journal-title":"Proceedings of the First Workshop on Neural Machine Translation"},{"key":"10.1016\/j.eswa.2026.133552_bib0019","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.125847","article-title":"Multi-granularity semantic relational mapping for image caption","volume":"264","author":"Gao","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.133552_bib0020","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.126690","article-title":"Uncertainty-guided siamese transformer network for salient object detection","volume":"272","author":"Han","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.133552_bib0021","first-page":"820","article-title":"Dual learning for machine translation","volume":"29","author":"He","year":"2016","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"9","key":"10.1016\/j.eswa.2026.133552_bib0022","doi-asserted-by":"crossref","DOI":"10.3390\/electronics14091716","article-title":"DMFormer: Dense memory linformer for image captioning","volume":"14","author":"He","year":"2025","journal-title":"Electronics"},{"key":"10.1016\/j.eswa.2026.133552_bib0023","doi-asserted-by":"crossref","first-page":"853","DOI":"10.1613\/jair.3994","article-title":"Framing image description as a ranking task: Data, models and evaluation metrics","volume":"47","author":"Hodosh","year":"2013","journal-title":"Journal of Artificial Intelligence Research"},{"key":"10.1016\/j.eswa.2026.133552_bib0024","doi-asserted-by":"crossref","first-page":"383","DOI":"10.5194\/isprs-annals-X-G-2025-383-2025","article-title":"TextSCD: Leveraging text-based semantic guidance for remote sensing image semantic change detection","volume":"X-G-2025","author":"Huang","year":"2025","journal-title":"ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences"},{"key":"10.1016\/j.eswa.2026.133552_bib0025","doi-asserted-by":"crossref","DOI":"10.1080\/10095020.2026.2646372","article-title":"ChangeVFM: Unleashing the power of vision foundation models for semantic change detection in remote sensing images","author":"Huang","year":"2026","journal-title":"Geo-Spatial Information Science"},{"issue":"2","key":"10.1016\/j.eswa.2026.133552_bib0026","doi-asserted-by":"crossref","first-page":"3721","DOI":"10.1080\/17538947.2023.2283482","article-title":"MC-Net: Multi-scale contextual information aggregation network for image captioning on remote sensing images","volume":"16","author":"Huang","year":"2023","journal-title":"International Journal of Digital Earth"},{"key":"10.1016\/j.eswa.2026.133552_bib0027","doi-asserted-by":"crossref","first-page":"4013","DOI":"10.1109\/TIP.2020.2969330","article-title":"Image captioning with end-to-end attribute detection and subsequent attributes prediction","volume":"29","author":"Huang","year":"2020","journal-title":"IEEE Transactions on Image processing"},{"key":"10.1016\/j.eswa.2026.133552_bib0028","series-title":"Proceedings of the IEEE winter conference on applications of computer vision","first-page":"4228","article-title":"Scale-adaptive feature aggregation for efficient space-time video super-resolution","author":"Huang","year":"2024"},{"key":"10.1016\/j.eswa.2026.133552_bib0029","series-title":"Proceedings of the international conference on disruptive technologies","first-page":"1428","article-title":"Image captioning using VGG-16 deep learning model","author":"Jayaswal","year":"2024"},{"issue":"4","key":"10.1016\/j.eswa.2026.133552_bib0030","doi-asserted-by":"crossref","first-page":"664","DOI":"10.1109\/TPAMI.2016.2598339","article-title":"Deep visual-semantic alignments for generating image descriptions","volume":"39","author":"Karpathy","year":"2017","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.eswa.2026.133552_bib0031","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109713","article-title":"A multi-modal transformer network for action detection","volume":"142","author":"Korban","year":"2023","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.eswa.2026.133552_bib0032","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.eswa.2026.133552_bib0033","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109893","article-title":"Learning consensus-aware semantic knowledge for remote sensing image captioning","volume":"145","author":"Li","year":"2024","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.eswa.2026.133552_bib0034","series-title":"Proceedings of the IEEE international conference on computer vision","first-page":"963","article-title":"Frequency-aware self-supervised long-tailed learning","author":"Lin","year":"2023"},{"key":"10.1016\/j.eswa.2026.133552_bib0035","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"2117","article-title":"Feature pyramid networks for object detection","author":"Lin","year":"2017"},{"key":"10.1016\/j.eswa.2026.133552_bib0036","series-title":"Proceedings of the European conference on computer vision","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"Lin","year":"2014"},{"key":"10.1016\/j.eswa.2026.133552_bib0037","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111584","article-title":"Transformer-driven feature fusion network and visual feature coding for multi-label image classification","volume":"164","author":"Liu","year":"2025","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.eswa.2026.133552_bib0038","unstructured":"Liu, W., Chen, S., Guo, L., Zhu, X., & Liu, J. (2021a). CPTR: Full transformer network for image captioning. arXiv: 2101."},{"key":"10.1016\/j.eswa.2026.133552_bib0039","series-title":"Proceedings of the IEEE international conference on computer vision (ICCV)","first-page":"9992","article-title":"Swin transformer: Hierarchical vision transformer using shifted windows","author":"Liu","year":"2021"},{"key":"10.1016\/j.eswa.2026.133552_bib0040","doi-asserted-by":"crossref","DOI":"10.3389\/fnbot.2021.688344","article-title":"Spiking neural network for fourier transform and object detection for automotive radar","volume":"15","author":"L\u00f3pez-Randulfe","year":"2021","journal-title":"Frontiers in Neurorobotics"},{"key":"10.1016\/j.eswa.2026.133552_bib0041","series-title":"Proceedings of the international conference on learning representations","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2018"},{"key":"10.1016\/j.eswa.2026.133552_bib0042","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"3242","article-title":"Knowing when to look: Adaptive attention via a visual sentinel for image captioning","author":"Lu","year":"2017"},{"key":"10.1016\/j.eswa.2026.133552_bib0043","series-title":"Proceedings of the european conference on computer vision","first-page":"237","article-title":"Unleashing text-to-image diffusion prior for zero-shot image captioning","author":"Luo","year":"2024"},{"key":"10.1016\/j.eswa.2026.133552_bib0044","unstructured":"Luo, J., Li, Y., Pan, Y., Yao, T., Feng, J., Chao, H., & Mei, T. (2022). Semantic-conditional diffusion networks for image captioning. arXiv preprint arXiv: 2212.03099."},{"key":"10.1016\/j.eswa.2026.133552_bib0045","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109420","article-title":"Towards local visual modeling for image captioning","volume":"138","author":"Ma","year":"2023","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.eswa.2026.133552_bib0046","doi-asserted-by":"crossref","first-page":"27730","DOI":"10.52202\/068431-2011","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.133552_bib0047","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"2082","article-title":"Slide-transformer: Hierarchical vision transformer with local self-attention","author":"Pan","year":"2023"},{"key":"10.1016\/j.eswa.2026.133552_bib0048","article-title":"Flickr30k entities: Collecting region-to-phrase correspondences for richer image-to-sentence models","volume":"abs\/1505.04870","author":"Plummer","year":"2015","journal-title":"Proceedings of the IEEE International Conference on Computer Vision"},{"key":"10.1016\/j.eswa.2026.133552_bib0049","doi-asserted-by":"crossref","first-page":"4341","DOI":"10.1109\/TIP.2023.3297408","article-title":"Centralized feature pyramid for object detection","volume":"32","author":"Quan","year":"2023","journal-title":"IEEE Transactions on Image Processing"},{"issue":"8","key":"10.1016\/j.eswa.2026.133552_bib0050","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"10.1016\/j.eswa.2026.133552_bib0051","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"2840","article-title":"SmallCap: Lightweight image captioning prompted with retrieval augmentation","author":"Ramos","year":"2023"},{"key":"10.1016\/j.eswa.2026.133552_bib0052","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2024.103264","article-title":"From vision to text: A comprehensive review of natural image captioning in medical diagnosis and radiology report generation","author":"Reale-Nosei","year":"2024","journal-title":"Medical Image Analysis"},{"key":"10.1016\/j.eswa.2026.133552_bib0053","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.110120","article-title":"Distance-based weighted transformer network for image completion","volume":"147","author":"Shamsolmoali","year":"2024","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.eswa.2026.133552_bib0054","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.128597","article-title":"Dual dynamic transformer for image captioning","author":"Shan","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.133552_bib0055","series-title":"Proceedings of the international conference on artificial intelligence, internet of things and cloud computing technology","first-page":"130","article-title":"Multi-branch information network for advanced image captioning","author":"Song","year":"2024"},{"key":"10.1016\/j.eswa.2026.133552_bib0056","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"10781","article-title":"EfficientDET: Scalable and efficient object detection","author":"Tan","year":"2020"},{"key":"10.1016\/j.eswa.2026.133552_bib0057","unstructured":"Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M.-A., Lacroix, T., Rozi\u00e8re, B., Goyal, N., Hambro, E., Azhar, F. et al. (2023). Llama: Open and efficient foundation language models. arXiv preprint arXiv: 2302.13971."},{"key":"10.1016\/j.eswa.2026.133552_bib0058","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.133552_bib0059","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2022.117174","article-title":"Geometry attention transformer with position-aware LSTMs for image captioning","volume":"201","author":"Wang","year":"2022","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.133552_bib0060","doi-asserted-by":"crossref","first-page":"11900","DOI":"10.1109\/TCSVT.2024.3425513","article-title":"Regular constrained multimodal fusion for image captioning","volume":"34","author":"Wang","year":"2024","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.1016\/j.eswa.2026.133552_bib0061","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"2585","article-title":"End-to-end transformer based model for image captioning","volume":"vol. 36","author":"Wang","year":"2022"},{"key":"10.1016\/j.eswa.2026.133552_bib0062","doi-asserted-by":"crossref","first-page":"2154","DOI":"10.1109\/JSTARS.2022.3153636","article-title":"Multiscale multiinteraction network for remote sensing image captioning","volume":"15","author":"Wang","year":"2022","journal-title":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing"},{"key":"10.1016\/j.eswa.2026.133552_bib0063","unstructured":"Wu, Y., Schuster, M., Chen, Z., Le, Q. V., Norouzi, M., Macherey, W., Krikun, M., Cao, Y., Gao, Q., Macherey, K. et al. (2016). Google\u2019s neural machine translation system: Bridging the gap between human and machine translation. arXiv preprint arXiv: 1609.08144."},{"issue":"9","key":"10.1016\/j.eswa.2026.133552_bib0064","doi-asserted-by":"crossref","first-page":"726","DOI":"10.3390\/info16090726","article-title":"Image captioning using topic faster r-CNN-LSTM networks","volume":"16","author":"Yeh","year":"2025","journal-title":"Information"},{"key":"10.1016\/j.eswa.2026.133552_bib0065","series-title":"Proceedings of the international conference on artificial neural networks and machine learning","first-page":"163","article-title":"Pe-yolo: Pyramid enhancement network for dark object detection","author":"Yin","year":"2023"},{"key":"10.1016\/j.eswa.2026.133552_bib0066","doi-asserted-by":"crossref","first-page":"1775","DOI":"10.1109\/TMM.2021.3072479","article-title":"Dual attention on pyramid feature maps for image captioning","volume":"24","author":"Yu","year":"2021","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.eswa.2026.133552_bib0067","series-title":"Proceedings of the 23rd conference on computational natural language learning","first-page":"789","article-title":"Pretraining-based natural language generation for text summarization","author":"Zhang","year":"2019"},{"key":"10.1016\/j.eswa.2026.133552_bib0068","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","first-page":"15465","article-title":"RSTNet: Captioning with adaptive attention on visual and non-visual words","author":"Zhang","year":"2021"},{"key":"10.1016\/j.eswa.2026.133552_bib0069","unstructured":"Zhang, Y., Gong, K., Zhang, K., Li, H., Qiao, Y., Ouyang, W., & Yue, X. (2023). Meta-transformer: A unified framework for multimodal learning. arXiv preprint arXiv: 2307.10802."},{"key":"10.1016\/j.eswa.2026.133552_bib0070","doi-asserted-by":"crossref","first-page":"866","DOI":"10.3390\/e26100866","article-title":"Meshed context-aware beam search for image captioning","volume":"26","author":"Zhao","year":"2024","journal-title":"Entropy"},{"key":"10.1016\/j.eswa.2026.133552_bib0071","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.126850","article-title":"From grids to pseudo-regions: Dynamic memory augmented image captioning with dual relation transformer","volume":"273","author":"Zhou","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.133552_bib0072","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.112539","article-title":"ChangeViT: Unleashing plain vision transformers for change detection in remote sensing images","volume":"172","author":"Zhu","year":"2026","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.eswa.2026.133552_bib0073","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","first-page":"24011","article-title":"Change3D: Revisiting change detection and captioning from a video modeling perspective","author":"Zhu","year":"2025"},{"key":"10.1016\/j.eswa.2026.133552_bib0074","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"10323","article-title":"BIFormer: Vision transformer with bi-level routing attention","author":"Zhu","year":"2023"}],"container-title":["Expert Systems with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426024619?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426024619?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T23:30:49Z","timestamp":1791934249000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0957417426024619"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2027,1]]},"references-count":74,"alternative-id":["S0957417426024619"],"URL":"https:\/\/doi.org\/10.1016\/j.eswa.2026.133552","relation":{},"ISSN":["0957-4174"],"issn-type":[{"value":"0957-4174","type":"print"}],"subject":[],"published":{"date-parts":[[2027,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Advancing image-to-text: MDE-net coupled with large language models for context-aware captioning","name":"articletitle","label":"Article Title"},{"value":"Expert Systems with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.eswa.2026.133552","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"133552"}}