{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T19:16:51Z","timestamp":1783711011702,"version":"3.55.0"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"1","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"}],"funder":[{"DOI":"10.13039\/501100003482","name":"Department of Education of Hebei Province","doi-asserted-by":"publisher","award":["2023JCT008"],"award-info":[{"award-number":["2023JCT008"]}],"id":[{"id":"10.13039\/501100003482","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62571039"],"award-info":[{"award-number":["62571039"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Central Government-Guided Fund for Local Science and Technology Development, Regional Science and Technology Innovation System Programme","award":["254Z3801G"],"award-info":[{"award-number":["254Z3801G"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1007\/s00371-025-04336-3","type":"journal-article","created":{"date-parts":[[2026,1,11]],"date-time":"2026-01-11T02:57:32Z","timestamp":1768100252000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Adaptive transformer-based detection: enhancing infrared image target recognition"],"prefix":"10.1007","volume":"42","author":[{"given":"Chong","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Yue","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianglong","family":"Fu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,1,11]]},"reference":[{"key":"4336_CR1","doi-asserted-by":"publisher","first-page":"129640","DOI":"10.1016\/j.neucom.2025.129640","volume":"630","author":"N Kumar","year":"2025","unstructured":"Kumar, N., Singh, P.: Small and dim target detection in infrared imagery: a review, current techniques and future directions. Neurocomputing 630, 129640 (2025)","journal-title":"Neurocomputing"},{"key":"4336_CR2","first-page":"1","volume":"22","author":"C Hu","year":"2025","unstructured":"Hu, C., et al.: Datransnet: dynamic attention transformer network for infrared small target detection. IEEE Geosci. Remote Sens. Lett. 22, 1\u20135 (2025)","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"4336_CR3","doi-asserted-by":"publisher","first-page":"129289","DOI":"10.1016\/j.neucom.2024.129289","volume":"621","author":"H Yang","year":"2025","unstructured":"Yang, H., Wang, J., Bo, Y., Wang, J.: ISTD-DETR: a deep learning algorithm based on DETR and super-resolution for infrared small target detection. Neurocomputing 621, 129289 (2025)","journal-title":"Neurocomputing"},{"key":"4336_CR4","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39, 1137\u20131149 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"4336_CR5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322","author":"K He","year":"2017","unstructured":"He, K., Gkioxari, G., Dollar, P., Girshick, R.: Mask R-CNN. IEEE Comput. Soc. (2017). https:\/\/doi.org\/10.1109\/ICCV.2017.322","journal-title":"IEEE Comput. Soc."},{"key":"4336_CR6","doi-asserted-by":"publisher","unstructured":"Wei, L., et al.: SSD: Single Shot MultiBox Detector. Springer, Cham (2016) https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2.","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"4336_CR7","unstructured":"yolov5\/models at master \u00b7 ultralytics\/yolov5. https:\/\/github.com\/ultralytics\/yolov5\/tree\/master\/models."},{"key":"4336_CR8","doi-asserted-by":"publisher","unstructured":"Li, C., et al.: YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2209.02976 (2022).","DOI":"10.48550\/arXiv.2209.02976"},{"key":"4336_CR9","unstructured":"Pertical\/YOLOv8: YOLOv8 in PyTorch > ONNX > CoreML > TFLite. https:\/\/github.com\/Pertical\/YOLOv8\/tree\/main."},{"key":"4336_CR10","doi-asserted-by":"publisher","unstructured":"Wang, A., et al.: YOLOv10: Real-Time End-to-End Object Detection. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2405.14458 (2024).","DOI":"10.48550\/arXiv.2405.14458"},{"key":"4336_CR11","unstructured":"Khanam, R., Hussain, M.: YOLOv11: An Overview of the Key Architectural Enhancements, http:\/\/arxiv.org\/abs\/2410.17725, (2024)."},{"key":"4336_CR12","unstructured":"Tian, Y., Ye, Q., Doermann, D.: YOLOv12: Attention-Centric Real-Time Object Detectors, http:\/\/arxiv.org\/abs\/2502.12524, (2025)."},{"key":"4336_CR13","unstructured":"Dosovitskiy, A., et al.: An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In: 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3\u20137, 2021 (OpenReview.net, 2021)."},{"key":"4336_CR14","doi-asserted-by":"publisher","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., & Dai, J.: Deformable DETR: Deformable Transformers for End-to-End Object Detection (2020). https:\/\/doi.org\/10.48550\/arXiv.2010.04159.","DOI":"10.48550\/arXiv.2010.04159"},{"key":"4336_CR15","doi-asserted-by":"publisher","unstructured":"Zhang, H., et al.: DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection. arXiv e-prints (2022). https:\/\/doi.org\/10.48550\/arXiv.2203.03605.","DOI":"10.48550\/arXiv.2203.03605"},{"key":"4336_CR16","doi-asserted-by":"publisher","unstructured":"Yao, Z., Ai, J., Li, B., & Zhang, C.: Efficient DETR: Improving End-to-End Object Detector with Dense Prior (2021). https:\/\/doi.org\/10.48550\/arXiv.2104.01318.","DOI":"10.48550\/arXiv.2104.01318"},{"key":"4336_CR17","doi-asserted-by":"publisher","unstructured":"Zhao, Y., et al.: DETRs Beat YOLOs on Real-time Object Detection. In: 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 16965\u201316974 (IEEE, Seattle, WA, USA, 2024). https:\/\/doi.org\/10.1109\/CVPR52733.2024.01605.","DOI":"10.1109\/CVPR52733.2024.01605"},{"key":"4336_CR18","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1016\/j.vrih.2022.07.006","volume":"5","author":"M Zhang","year":"2023","unstructured":"Zhang, M., Tian, X.: Transformer architecture based on mutual attention for image-anomaly detection. Virtual Reality Intell. Hardw. 5, 57\u201367 (2023)","journal-title":"Virtual Reality Intell. Hardw."},{"key":"4336_CR19","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1109\/TMM.2021.3120873","volume":"25","author":"X Lin","year":"2023","unstructured":"Lin, X., et al.: Eapt: efficient attention pyramid transformer for image processing. IEEE Trans. Multimed. 25, 50\u201361 (2023)","journal-title":"IEEE Trans. Multimed."},{"key":"4336_CR20","doi-asserted-by":"publisher","DOI":"10.1002\/cav.2201","author":"X Zhu","year":"2024","unstructured":"Zhu, X., et al.: Tmsdnet: transformer with multi-scale dense network for single and multi-view 3D reconstruction. Comput. Anim. Virtual Worlds (2024). https:\/\/doi.org\/10.1002\/cav.2201","journal-title":"Comput. Anim. Virtual Worlds"},{"key":"4336_CR21","doi-asserted-by":"publisher","DOI":"10.1002\/cav.2293","author":"Z Xiao","year":"2024","unstructured":"Xiao, Z., et al.: Human action recognition in immersive virtual reality based on multi-scale spatio-temporal attention network. Comput. Anim. Virtual Worlds (2024). https:\/\/doi.org\/10.1002\/cav.2293","journal-title":"Comput. Anim. Virtual Worlds"},{"key":"4336_CR22","doi-asserted-by":"publisher","unstructured":"Wen, Y., et al.: SAT-Net: Structure-Aware Transformer-Based Attention Fusion Network for Low-Quality Retinal Fundus Images Enhancement. In: IEEE Transactions on Multimedia 1\u201314 (2025) https:\/\/doi.org\/10.1109\/TMM.2025.3565935.","DOI":"10.1109\/TMM.2025.3565935"},{"key":"4336_CR23","doi-asserted-by":"publisher","first-page":"110133","DOI":"10.1016\/j.compeleceng.2025.110133","volume":"123","author":"H Yu","year":"2025","unstructured":"Yu, H., et al.: Cross-modality target detection using infrared and visible image fusion for robust objection recognition. Comput. Electr. Eng. 123, 110133 (2025)","journal-title":"Comput. Electr. Eng."},{"key":"4336_CR24","doi-asserted-by":"publisher","DOI":"10.1049\/ipr2.13320","author":"J Jing","year":"2025","unstructured":"Jing, J., Hu, J.F., Zhao, Z.P., Liu, Y.: Mcfnet: research on small target detection of RGB-infrared under UAV perspective with multi-scale complementary feature fusion. IET Image Process. (2025). https:\/\/doi.org\/10.1049\/ipr2.13320","journal-title":"IET Image Process."},{"key":"4336_CR25","doi-asserted-by":"publisher","first-page":"105435","DOI":"10.1016\/j.imavis.2025.105435","volume":"154","author":"S Zhu","year":"2025","unstructured":"Zhu, S., Ji, L., Chen, S., Duan, W.: Spatial-temporal-channel collaborative feature learning with transformers for infrared small target detection. Image Vis. Comput. 154, 105435 (2025)","journal-title":"Image Vis. Comput."},{"key":"4336_CR26","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1007\/s11227-024-06509-8","volume":"81","author":"Q Liu","year":"2025","unstructured":"Liu, Q., Chen, H., Zhao, F.: Maritime target detection algorithm based on fusion of visible and infrared images. J. Supercomput. 81, 22 (2025)","journal-title":"J. Supercomput."},{"key":"4336_CR27","first-page":"1","volume":"74","author":"J Fu","year":"2025","unstructured":"Fu, J., Li, F., Zhao, J.: Regional saliency combined with morphological filtering for infrared maritime target detection in autonomous aerial vehicles images. IEEE Trans. Instrum. Meas. 74, 1\u201316 (2025)","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"4336_CR28","doi-asserted-by":"publisher","first-page":"3650","DOI":"10.1049\/ipr2.13203","volume":"18","author":"R Yang","year":"2024","unstructured":"Yang, R., Zhang, Y., Gao, G., Liao, L., Li, C.: Global information aware network with global interaction graph attention for infrared small target detection. IET Image Process. 18, 3650\u20133666 (2024)","journal-title":"IET Image Process."},{"key":"4336_CR29","doi-asserted-by":"publisher","unstructured":"Musso, C., Lefebvre, S., & Thetas, S.: Moving target\u2019s detection performances in a sequence of infrared multispectral images. In: 27th International Conference on Information Fusion, FUSION 2024, Venice, Italy, July 8\u201311, 2024 1\u20137 (IEEE, 2024). https:\/\/doi.org\/10.23919\/FUSION59988.2024.10706485.","DOI":"10.23919\/FUSION59988.2024.10706485"},{"key":"4336_CR30","doi-asserted-by":"publisher","first-page":"6723","DOI":"10.1007\/s00371-022-02759-w","volume":"39","author":"W Yin","year":"2023","unstructured":"Yin, W., He, K., Xu, D., Yue, Y., Luo, Y.: Adaptive low light visual enhancement and high-significant target detection for infrared and visible image fusion. Vis. Comput. 39, 6723\u20136742 (2023)","journal-title":"Vis. Comput."},{"key":"4336_CR31","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1049\/ipr2.12616","volume":"17","author":"X Li","year":"2023","unstructured":"Li, X., Qian, Y., Guo, R., Ao, N.: I-CenterNet: road infrared target detection based on improved CenterNet. IET Image Process. 17, 57\u201366 (2023)","journal-title":"IET Image Process."},{"key":"4336_CR32","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1007\/s00371-022-02765-y","volume":"40","author":"H Lu","year":"2024","unstructured":"Lu, H., Liu, Z., Pan, X., et al.: Enhancing infrared images via multi-resolution contrast stretching and adaptive multi-scale detail boosting. Vis. Comput. 40, 53\u201371 (2024). https:\/\/doi.org\/10.1007\/s00371-022-02765-y","journal-title":"Vis. Comput."},{"key":"4336_CR33","doi-asserted-by":"publisher","first-page":"8927","DOI":"10.1007\/s00371-024-03284-8","volume":"40","author":"K Tong","year":"2024","unstructured":"Tong, K., Wu, Y.: I-YOLO: a novel single-stage framework for small object detection. Vis. Comput. 40, 8927\u20138944 (2024). https:\/\/doi.org\/10.1007\/s00371-024-03284-8","journal-title":"Vis. Comput."},{"key":"4336_CR34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90","author":"K He","year":"2016","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. IEEE (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.90","journal-title":"IEEE"},{"key":"4336_CR35","unstructured":"Shi, B., Gai, S., Darrell, T., Wang, X.: Refocusing Is Key to Transfer Learning (2023). http:\/\/arxiv.org\/abs\/2305.15542."},{"key":"4336_CR36","unstructured":"Meng, W., Luo, Y., Li, X., Jiang, D., & Zhang, Z.: PolaFormer: Polarity-aware Linear Attention for Vision Transformers. CoRR http:\/\/arxiv.org\/abs\/2501.15061)."},{"key":"4336_CR37","unstructured":"CVPR Poster 5%>100%: Breaking Performance Shackles of Full Fine-Tuning on Visual Recognition Tasks. https:\/\/cvpr.thecvf.com\/virtual\/2025\/poster\/34704."},{"key":"4336_CR38","doi-asserted-by":"crossref","unstructured":"Zhu, J., Chen, X., He, K., LeCun, Y., & Liu, Z.: Transformers without Normalization. CoRR http:\/\/arxiv.org\/abs\/2503.10622 (2025).","DOI":"10.1109\/CVPR52734.2025.01388"},{"key":"4336_CR39","unstructured":"Infrared Image Detection Dataset by wesam. https:\/\/universe.roboflow.com\/wesam\/q8-jqylh."},{"key":"4336_CR40","doi-asserted-by":"crossref","unstructured":"Carion, N., et al.: End-to-End Object Detection with Transformers. in (2020).","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"4336_CR41","unstructured":"FLIR-ADAS Dataset by workspace. https:\/\/universe.roboflow.com\/workspace-ficab\/yolo-flir-adas."}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-025-04336-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-025-04336-3","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-025-04336-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T13:04:55Z","timestamp":1772629495000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-025-04336-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":41,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["4336"],"URL":"https:\/\/doi.org\/10.1007\/s00371-025-04336-3","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]},"assertion":[{"value":"1 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 December 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 January 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"121"}}