{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T08:54:16Z","timestamp":1781513656676,"version":"3.54.1"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T00:00:00Z","timestamp":1779235200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T00:00:00Z","timestamp":1781481600000},"content-version":"vor","delay-in-days":26,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"name":"Natural Science Foundation of Shandong Province, China\u4e2d\u56fd\u5c71\u4e1c\u7701\u81ea\u7136\u79d1\u5b66\u57fa\u91d1\u4f1a","award":["ZR2024MA055"],"award-info":[{"award-number":["ZR2024MA055"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"DOI":"10.1038\/s41598-026-53189-w","type":"journal-article","created":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T21:34:30Z","timestamp":1779312870000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["TLCFormer: synergizing temporal motion and local contrast for robust infrared video small object detection"],"prefix":"10.1038","volume":"16","author":[{"given":"Zihan","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lun","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fan","family":"Bai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,20]]},"reference":[{"issue":"2","key":"53189_CR1","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1109\/MGRS.2022.3145502","volume":"10","author":"M Zhao","year":"2022","unstructured":"Zhao, M. et al. Infrared small target detection: A survey. IEEE Geosci. Remote Sens. Mag. 10 (2), 64\u201399 (2022).","journal-title":"IEEE Geosci. Remote Sens. Mag."},{"issue":"12","key":"53189_CR2","doi-asserted-by":"publisher","first-page":"4996","DOI":"10.1109\/TIP.2013.2281420","volume":"22","author":"C Gao","year":"2013","unstructured":"Gao, C. et al. Infrared patch-image model for small target detection in a single image. IEEE Trans. Image Process. 22 (12), 4996\u20135009 (2013).","journal-title":"IEEE Trans. Image Process."},{"key":"53189_CR3","doi-asserted-by":"crossref","unstructured":"Carion, N. et al. End-to-end object detection with transformers. In European Conference on Computer Vision (ECCV), 213\u2013229 (Springer, 2020).","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"53189_CR4","unstructured":"Zhu, X. et al. Deformable DETR: Deformable transformers for end-to-end object detection. In European Conference on Computer Vision (ECCV), 152\u2013168 (Springer, 2020)."},{"key":"53189_CR5","doi-asserted-by":"crossref","unstructured":"Wang, W. et al. Pyramid vision transformer: A versatile backbone for dense prediction without convolutions. In IEEE\/CVF International Conference on Computer Vision (ICCV), 568\u2013578 (2021).","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"53189_CR6","doi-asserted-by":"crossref","unstructured":"Piccardi, M. Background subtraction techniques: A review. In IEEE International Conference on Systems, Man and Cybernetics (SMC), 3099\u20133104 (2004).","DOI":"10.1109\/ICSMC.2004.1400815"},{"issue":"12","key":"53189_CR7","first-page":"10395","volume":"59","author":"T Liu","year":"2021","unstructured":"Liu, T. et al. OSFormer: One-step transformer for infrared video small object detection. IEEE Trans. Geosci. Remote Sens. 59 (12), 10395\u201310409 (2021).","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"issue":"1","key":"53189_CR8","doi-asserted-by":"publisher","first-page":"574","DOI":"10.1109\/TGRS.2013.2242477","volume":"52","author":"CP Chen","year":"2014","unstructured":"Chen, C. P., Li, H., Wei, Y., Xia, T. & Tang, Y. Y. A local contrast method for small infrared target detection. IEEE Trans. Geosci. Remote Sens. 52 (1), 574\u2013581 (2014).","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"issue":"7","key":"53189_CR9","doi-asserted-by":"publisher","first-page":"4204","DOI":"10.1109\/TGRS.2016.2538295","volume":"54","author":"H Deng","year":"2016","unstructured":"Deng, H., Sun, X., Liu, M., Ye, C. & Zhou, X. Small infrared target detection based on weighted local difference measure. IEEE Trans. Geosci. Remote Sens. 54 (7), 4204\u20134214 (2016).","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"53189_CR10","doi-asserted-by":"crossref","unstructured":"Liu, Z. et al. Swin Transformer: Hierarchical vision transformer using shifted windows. In IEEE\/CVF International Conference on Computer Vision (ICCV), 10012\u201310022 (2021).","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"53189_CR11","unstructured":"Bertasius, G., Wang, H. & Torresani, L. Is space-time attention all you need for video understanding? In International Conference on Machine Learning (ICML), Proceedings of Machine Learning Research, vol. 139, 813\u2013824 (2021)."},{"key":"53189_CR12","doi-asserted-by":"crossref","unstructured":"Dosovitskiy, A. et al. FlowNet: Learning optical flow with convolutional networks. In IEEE International Conference on Computer Vision (ICCV), 2758\u20132766 (2015).","DOI":"10.1109\/ICCV.2015.316"},{"key":"53189_CR13","doi-asserted-by":"crossref","unstructured":"Yu, W. et al. MetaFormer is actually what you need for vision. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 10819\u201310829 (2022).","DOI":"10.1109\/CVPR52688.2022.01055"},{"key":"53189_CR14","doi-asserted-by":"crossref","unstructured":"Hong, J. et al. Multi-target tracking for satellite videos guided by spatial-temporal proximity and topological relationships. IEEE Trans. Geosci. Remote Sens. 63 (2025).","DOI":"10.1109\/TGRS.2025.3539462"},{"issue":"000","key":"53189_CR15","first-page":"1","volume":"63","author":"J Hong","year":"2025","unstructured":"Hong, J. et al. A multivehicle tracking method for video-SAR with reliable foreground\u2013background motion feature compensation. Geosci. Remote Sens. IEEE Trans.. 63 (000), 1\u201322 (2025).","journal-title":"Geosci. Remote Sens. IEEE Trans."},{"issue":"000","key":"53189_CR16","doi-asserted-by":"publisher","first-page":"108975","DOI":"10.1109\/ACCESS.2024.3439358","volume":"12","author":"X Wu","year":"2024","unstructured":"Wu, X. et al. A 3D reconstruction of terahertz images based on the FCTMVSNet algorithm. IEEE. 12 (000), 108975\u2013108985. https:\/\/doi.org\/10.1109\/ACCESS.2024.3439358 (2024).","journal-title":"Access. IEEE"},{"key":"53189_CR17","doi-asserted-by":"publisher","unstructured":"Bai, F., Li, L., Wang, W. & Wu, X. DETransMVSnet: Research on terahertz 3D reconstruction of multi-view stereo network with deep equilibrium transformers. IEEE Access. 11, 146042\u2013146053. https:\/\/doi.org\/10.1109\/ACCESS.2023.3342847 (2023).","DOI":"10.1109\/ACCESS.2023.3342847"},{"key":"53189_CR18","doi-asserted-by":"crossref","unstructured":"Xiaojin Wu, F. et al. Unsupervised disparity-tolerant algorithm for terahertz image stitching. Sci. Rep. 15(1), (2025).","DOI":"10.1038\/s41598-025-16594-1"},{"key":"53189_CR19","doi-asserted-by":"crossref","unstructured":"Dai, Y., Wu, Y., Zhou, F. & Barnard, K. Asymmetric contextual modulation for infrared small target detection. In IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), 950\u2013959 (2021).","DOI":"10.1109\/WACV48630.2021.00099"},{"issue":"5","key":"53189_CR20","doi-asserted-by":"publisher","first-page":"559","DOI":"10.3390\/rs11050559","volume":"11","author":"L Zhang","year":"2019","unstructured":"Zhang, L., Peng, L., Zhang, T., Cao, S. & Peng, Z. Infrared small target detection via non-convex rank approximation minimization joint l2,1-norm. Remote Sens. 11 (5), 559 (2019).","journal-title":"Remote Sens."},{"key":"53189_CR21","doi-asserted-by":"crossref","unstructured":"Tian, Z., Shen, C., Chen, H. & He, T. FCOS: Fully convolutional one-stage object detection. In IEEE\/CVF International Conference on Computer Vision (ICCV), 9627\u20139636 (2019).","DOI":"10.1109\/ICCV.2019.00972"},{"key":"53189_CR22","doi-asserted-by":"publisher","first-page":"364","DOI":"10.1109\/TIP.2022.3228497","volume":"32","author":"X Wu","year":"2022","unstructured":"Wu, X., Hong, D. & Chanussot, J. UIU-Net: U-Net in U-Net for infrared small object detection. IEEE Trans. Image Process. 32, 364\u2013376 (2022).","journal-title":"IEEE Trans. Image Process."},{"key":"53189_CR23","doi-asserted-by":"crossref","unstructured":"Zheng, J. et al. DFGOVD: A new dataset and benchmark for drone fine-grained oriented vehicle detection in the wild. IEEE Trans. Geosci. Remote Sens. 64[2026-04-02].","DOI":"10.1109\/TGRS.2026.3660958"},{"key":"53189_CR24","unstructured":"Dosovitskiy, A. et al. An image is worth 16x16 words: Transformers for image recognition at scale. In International Conference on Learning Representations (ICLR) (2021)."},{"key":"53189_CR25","doi-asserted-by":"crossref","unstructured":"Liu, Z. et al. Swin transformer: Hierarchical vision transformer using shifted windows. In Proceedings of the IEEE\/CVF International Conference on Computer Vision 10012\u201310022 (2021).","DOI":"10.1109\/ICCV48922.2021.00986"},{"issue":"3","key":"53189_CR26","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1007\/s41095-022-0274-8","volume":"8","author":"W Wang","year":"2022","unstructured":"Wang, W. et al. Pvt v2: Improved baselines with pyramid vision transformer. Comput. Visual Media. 8 (3), 415\u2013424 (2022).","journal-title":"Comput. Visual Media"},{"key":"53189_CR27","doi-asserted-by":"crossref","unstructured":"Yu, W. et al. Metaformer is actually what you need for vision. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 10819\u201310829 (2022).","DOI":"10.1109\/CVPR52688.2022.01055"},{"key":"53189_CR28","doi-asserted-by":"crossref","unstructured":"Ilg, E. et al. Flownet 2.0: Evolution of optical flow estimation with deep networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2462\u20132470 (2017).","DOI":"10.1109\/CVPR.2017.179"},{"key":"53189_CR29","doi-asserted-by":"crossref","unstructured":"Piccardi, M. Background subtraction techniques: a review. In 2004 IEEE International Conference on Systems, Man and Cybernetics (IEEE Cat. No. 04CH37583), vol. 4, 3099\u20133104 (IEEE, 2004).","DOI":"10.1109\/ICSMC.2004.1400815"},{"key":"53189_CR30","doi-asserted-by":"crossref","unstructured":"Wang, J. et al. Long-short temporal contrastive learning of video transformers. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 14010\u201314020 (2022).","DOI":"10.1109\/CVPR52688.2022.01362"},{"key":"53189_CR31","doi-asserted-by":"crossref","unstructured":"Liu, Z. et al. Video swin transformer. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 3202\u20133211 (2022).","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"53189_CR32","doi-asserted-by":"crossref","unstructured":"Xing, M. et al. Unbiased spatial\u2013temporal atomic fusion-based zero-shot action recognition. Inform. Fusion 126(PartB) (2025).","DOI":"10.1016\/j.inffus.2025.103633"},{"key":"53189_CR33","doi-asserted-by":"crossref","unstructured":"Xing, M. et al. From gaze to masks: Gaze-based weakly-supervised medical image segmentation. In 2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM).","DOI":"10.1109\/BIBM66473.2025.11357139"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-53189-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-53189-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-53189-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T08:12:36Z","timestamp":1781511156000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-53189-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,20]]},"references-count":33,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["53189"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-53189-w","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,20]]},"assertion":[{"value":"5 March 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 May 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 May 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":"18519"}}