{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T07:12:01Z","timestamp":1778051521657,"version":"3.51.4"},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T00:00:00Z","timestamp":1778025600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T00:00:00Z","timestamp":1778025600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Basic Scientific Research Program of Universities under the Liaoning Provincial Department of Education","award":["LJ212410142048"],"award-info":[{"award-number":["LJ212410142048"]}]},{"DOI":"10.13039\/501100005047","name":"Natural Science Foundation of Liaoning Province","doi-asserted-by":"publisher","award":["JYTMS20231211"],"award-info":[{"award-number":["JYTMS20231211"]}],"id":[{"id":"10.13039\/501100005047","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Liaoning Provincial Science and Technology Department Joint Fund Project","award":["2023-MSLH-262"],"award-info":[{"award-number":["2023-MSLH-262"]}]},{"name":"Youth Program of the National Natural Science Foundation of China","award":["Grant No. 62301341"],"award-info":[{"award-number":["Grant No. 62301341"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["Grant No. 62371315"],"award-info":[{"award-number":["Grant No. 62371315"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1007\/s00530-026-02378-8","type":"journal-article","created":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:15:52Z","timestamp":1778048152000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["GCS-DETR: a global context-driven detection model of small objects with occlusion suppression in unmanned aerial vehicle imagery"],"prefix":"10.1007","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3539-9077","authenticated-orcid":false,"given":"Shaoli","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0126-3437","authenticated-orcid":false,"given":"Xiangyu","family":"Ren","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7875-5986","authenticated-orcid":false,"given":"Dejian","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2624-9684","authenticated-orcid":false,"given":"Siying","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6697-2705","authenticated-orcid":false,"given":"Luyao","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8278-1589","authenticated-orcid":false,"given":"Bin","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,5,6]]},"reference":[{"issue":"20","key":"2378_CR1","doi-asserted-by":"publisher","DOI":"10.3390\/app132011524","volume":"13","author":"J Song","year":"2023","unstructured":"Song, J., Yu, Z., Qi, G., Su, Q., Xie, J., Liu, W.: UAV image small object detection based on RSAD algorithm. Appl. Sci. 13(20), 11524 (2023). https:\/\/doi.org\/10.3390\/app132011524","journal-title":"Applied Sciences"},{"key":"2378_CR2","doi-asserted-by":"publisher","first-page":"41999","DOI":"10.1109\/ACCESS.2024.3378248","volume":"12","author":"K Ou","year":"2024","unstructured":"Ou, K., Dong, C., Liu, X., Zhai, Y., Li, Y., Huang, W., Qiu, W., Wang, Y., Wang, C.: Drone-TOOD: A lightweight task-aligned object detection algorithm for vehicle detection in UAV images. IEEE Access 12, 41999\u201342016 (2024). https:\/\/doi.org\/10.1109\/ACCESS.2024.3378248","journal-title":"IEEE Access"},{"key":"2378_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.iswa.2025.200561","author":"M Nikouei","year":"2025","unstructured":"Nikouei, M., Baroutian, B., Nabavi, S., Taraghi, F., Aghaei, A., Sajedi, A., Moghaddam, M.E.: Small object detection: a comprehensive survey on challenges, techniques and real-world applications. Intell. Syst. Appl. (2025). https:\/\/doi.org\/10.1016\/j.iswa.2025.200561","journal-title":"Intelligent Systems with Applications"},{"key":"2378_CR4","doi-asserted-by":"publisher","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 580\u2013587). (2014). https:\/\/doi.org\/10.1109\/cvpr.2014.81","DOI":"10.1109\/cvpr.2014.81"},{"key":"2378_CR5","doi-asserted-by":"publisher","unstructured":"Girshick, R.: Fast r-cnn. In Proceedings of the IEEE international conference on computer vision (pp. 1440\u20131448). (2015). https:\/\/doi.org\/10.1109\/ICCV.2015.169","DOI":"10.1109\/ICCV.2015.169"},{"key":"2378_CR6","doi-asserted-by":"publisher","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: Towards real-time object detection with region proposal networks. Adv. Neural. Inf. Process. Syst. 28 (2015). https:\/\/doi.org\/10.1109\/TPAMI.2016.2577031","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"2378_CR7","doi-asserted-by":"publisher","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.Y., Berg, A.C.: Ssd: Single shot multibox detector. In European conference on computer vision (pp. 21\u201337). Cham: Springer International Publishing. (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"2378_CR8","doi-asserted-by":"publisher","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: Unified, real-time object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 779\u2013788). (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.91","DOI":"10.1109\/CVPR.2016.91"},{"key":"2378_CR9","doi-asserted-by":"publisher","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In European conference on computer vision (pp. 213\u2013229). Cham: Springer International Publishing. (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"2378_CR10","doi-asserted-by":"publisher","unstructured":"Zhao, Y., Lv, W., Xu, S., Wei, J., Wang, G., Dang, Q., Chen, J.: Detrs beat yolos on real-time object detection. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 16965\u201316974). (2024). https:\/\/doi.org\/10.1109\/CVPR52733.2024.01605","DOI":"10.1109\/CVPR52733.2024.01605"},{"issue":"3","key":"2378_CR11","doi-asserted-by":"publisher","first-page":"1845","DOI":"10.1109\/TIT.2017.2776228","volume":"64","author":"T Wiatowski","year":"2017","unstructured":"Wiatowski, T., B\u00f6lcskei, H.: A mathematical theory of deep convolutional neural networks for feature extraction. IEEE Trans. Inf. Theory 64(3), 1845\u20131866 (2017). https:\/\/doi.org\/10.1109\/TIT.2017.2776228","journal-title":"IEEE Transactions on Information Theory"},{"key":"2378_CR12","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2501.17983","author":"X Wang","year":"2025","unstructured":"Wang, X., Peng, Y., Shen, C.: Efficient Feature Fusion for UAV Object Detection. arXiv preprint arXiv:2501 17983. (2025). https:\/\/doi.org\/10.48550\/arXiv.2501.17983","journal-title":"arXiv preprint arXiv:2501 17983"},{"issue":"2","key":"2378_CR13","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1007\/s40745-020-00253-5","volume":"9","author":"Q Wang","year":"2022","unstructured":"Wang, Q., Ma, Y., Zhao, K., Tian, Y.: A comprehensive survey of loss functions in machine learning. Ann. Data Sci. 9(2), 187\u2013212 (2022). https:\/\/doi.org\/10.1007\/s40745-020-00253-5","journal-title":"Annals of Data Science"},{"key":"2378_CR14","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In Proceedings of theIEEE conference on computer vision and pattern recognition (pp. 770\u2013778). (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"2378_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2024.104682","volume":"154","author":"P Vasanthi","year":"2024","unstructured":"Vasanthi, P., Mohan, L.: Efficient YOLOv8 algorithm for extreme small-scale object detection. Digital Signal Process. 154, 104682 (2024). https:\/\/doi.org\/10.1016\/j.dsp.2024.104682","journal-title":"Digital Signal Processing"},{"key":"2378_CR16","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2024.105232","volume":"150","author":"N Battish","year":"2024","unstructured":"Battish, N., Kaur, D., Chugh, M., Poddar, S.: SDMNet: spatially dilated multi-scale network for object detection for drone aerial imagery. Image Vision Comput. 150, 105232 (2024). https:\/\/doi.org\/10.1016\/j.imavis.2024.105232","journal-title":"Image and Vision Computing"},{"key":"2378_CR17","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2025.104481","volume":"260","author":"B Li","year":"2025","unstructured":"Li, B., Yang, H., Xia, C., Zheng, H., Zhang, T.: Adaptive Detr: a framework with dynamic sampling points and feature-guided adaptive attention udates. Comput. Vision Image Underst. 260, 104481 (2025). https:\/\/doi.org\/10.1016\/j.cviu.2025.104481","journal-title":"Computer Vision and Image Understanding"},{"key":"2378_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2025.113253","volume":"315","author":"L Zhou","year":"2025","unstructured":"Zhou, L., Zhao, S., Li, S., Wang, Y., Liu, Y., Zuo, X.: A lightweight object detection method based on fine-grained information extraction and exchange in UAV aerial images. Knowledge-Based Syst. 315, 113253 (2025). https:\/\/doi.org\/10.1016\/j.knosys.2025.113253","journal-title":"Knowledge-Based Systems"},{"issue":"12","key":"2378_CR19","doi-asserted-by":"publisher","first-page":"24330","DOI":"10.1109\/TITS.2022.3203715","volume":"23","author":"J Shen","year":"2022","unstructured":"Shen, J., Zhou, W., Liu, N., Sun, H., Li, D., Zhang, Y.: An anchor-free lightweight deep convolutional network for vehicle detection in aerial images. IEEE Trans. Intell. Transp. Syst. 23(12), 24330\u201324342 (2022). https:\/\/doi.org\/10.1109\/TITS.2022.3203715","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"2378_CR20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2023.3346488","volume":"73","author":"J Shen","year":"2024","unstructured":"Shen, J., Liu, N., Sun, H., Li, D., Zhang, Y.: An instrument indication acquisition algorithm based on lightweight deep convolutional neural network and hybrid attention fine-grained features. IEEE Trans. Instrum. Measurement 73, 1\u201316 (2024). https:\/\/doi.org\/10.1109\/TIM.2023.3346488","journal-title":"IEEE transactions on instrumentation and measurement"},{"key":"2378_CR21","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2025.3642410","author":"J Shen","year":"2025","unstructured":"Shen, J., Liu, N., Sun, H., Wu, S., Liang, Z., Han, L., Li, D.: Lightweight semantic feature extraction model with direction awareness for aerial traffic object detection. IEEE Trans. Intell. Transp. Syst. (2025). https:\/\/doi.org\/10.1109\/TITS.2025.3642410","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"2378_CR22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2021.3132332","volume":"71","author":"J Shen","year":"2021","unstructured":"Shen, J., Liu, N., Xu, C., Sun, H., Xiao, Y., Li, D., Zhang, Y.: Finger vein recognition algorithm based on lightweight deep convolutional neural network. IEEE Trans. Instrum. Meas. 71, 1\u201313 (2021). https:\/\/doi.org\/10.1109\/TIM.2021.3132332","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"2378_CR23","doi-asserted-by":"publisher","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2117\u20132125). (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.106","DOI":"10.1109\/CVPR.2017.106"},{"key":"2378_CR24","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2025.110413","volume":"125","author":"X Wang","year":"2025","unstructured":"Wang, X., Xu, G., Hong, C., He, N., Li, R., Sun, F., Han, W.: A real-time detector for small-object remote sensing. Comput. Electr. Eng. 125, 110413 (2025). https:\/\/doi.org\/10.1016\/j.compeleceng.2025.110413","journal-title":"Computers and Electrical Engineering"},{"key":"2378_CR25","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2025.105297","volume":"164","author":"D Bian","year":"2025","unstructured":"Bian, D., Tang, M., Ling, M., Xu, H., Lv, S., Tang, Q., Hu, J.: A refined methodology for small objectdetection: multi-scale feature extraction and cross-stage feature fusion network. Digital Signal Process. 105297 (2025). https:\/\/doi.org\/10.1016\/j.dsp.2025.105297","journal-title":"Digital Signal Processing"},{"key":"2378_CR26","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2025.104472","volume":"260","author":"L Shang","year":"2025","unstructured":"Shang, L., He, Q., Lei, H., Yang, W.: CCANet: a cross-scale context aggregation network for UAV object detection. Comput. Vision Image Underst. 104472 (2025). https:\/\/doi.org\/10.1016\/j.cviu.2025.104472","journal-title":"Computer Vision and Image Understanding"},{"key":"2378_CR27","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2025.127595","volume":"281","author":"Q Gu","year":"2025","unstructured":"Gu, Q., Han, Z., Kong, S., Huang, H., Li, Y., Fan, Q., Wu, R.: DCYOLO: dual negative weighting label assignment and cross-layer decouple head for YOLO in remote sensing images. Expert Syst. Appl. 281, 127595 (2025). https:\/\/doi.org\/10.1016\/j.eswa.2025.127595","journal-title":"Expert Syst. Appl."},{"key":"2378_CR28","doi-asserted-by":"publisher","unstructured":"Yu, J., Jiang, Y., Wang, Z., Cao, Z., Huang, T.: Unitbox: an advanced object detection network. In Proceedings of the 24th ACM international conference on Multimedia (pp. 516\u2013520). (2016)., October https:\/\/doi.org\/10.1145\/2964284.2967274","DOI":"10.1145\/2964284.2967274"},{"key":"2378_CR29","doi-asserted-by":"publisher","unstructured":"Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., Savarese, S.: Generalized intersection over union: a metric and a loss for bounding box regression. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 658\u2013666). (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00075","DOI":"10.1109\/CVPR.2019.00075"},{"key":"2378_CR30","doi-asserted-by":"publisher","unstructured":"Zheng, Z., Wang, P., Liu, W., Li, J., Ye, R., Ren, D.: Distance-IoU loss: faster and better learning for bounding box regression. In Proceedings of the AAAI conference on artificial intelligence (Vol. 34, No. 07, pp. 12993\u201313000). (2020). https:\/\/doi.org\/10.1609\/aaai.v34i07.6999","DOI":"10.1609\/aaai.v34i07.6999"},{"issue":"8","key":"2378_CR31","doi-asserted-by":"publisher","first-page":"8574","DOI":"10.1109\/TCYB.2021.3095305","volume":"52","author":"Z Zheng","year":"2021","unstructured":"Zheng, Z., Wang, P., Ren, D., Liu, W., Ye, R., Hu, Q., Zuo, W.: Enhancing geometric factors in model learning and inference for object detection and instance segmentation. IEEE Trans. Cybern. 52(8), 8574\u20138586 (2021). https:\/\/doi.org\/10.1109\/TCYB.2021.3095305","journal-title":"IEEE Trans. Cybernetics"},{"key":"2378_CR32","doi-asserted-by":"publisher","unstructured":"Chen, Z., Chen, K., Lin, W., See, J., Yu, H., Ke, Y., Yang, C.: Piou loss: towards accurate oriented object detection in complex environments. In European conference on computer vision (pp. 195\u2013211). Cham: Springer International Publishing. (2020). https:\/\/doi.org\/10.1007\/978-3-030-58558-7_12","DOI":"10.1007\/978-3-030-58558-7_12"},{"key":"2378_CR33","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2311.02877","author":"H Zhang","year":"2023","unstructured":"Zhang, H., Xu, C., Zhang, S.: Inner-IoU: more effective intersection over union loss with auxiliary bounding box. arXiv preprint. (2023). https:\/\/doi.org\/10.48550\/arXiv.2311.02877 arXiv:2311.02877","journal-title":"arXiv preprint"},{"key":"2378_CR34","doi-asserted-by":"publisher","unstructured":"Tatsunami, Y., Taki, M.: Fft-based dynamic token mixer for vision. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 38, No. 14, pp. 15328\u201315336). (2024). https:\/\/doi.org\/10.1609\/aaai.v38i14.29457","DOI":"10.1609\/aaai.v38i14.29457"},{"issue":"17","key":"2378_CR35","doi-asserted-by":"publisher","DOI":"10.3390\/s24175496","volume":"24","author":"Y Kong","year":"2024","unstructured":"Kong, Y., Shang, X., Jia, S.: Drone-DETR: efficient small object detection for remote sensing image using enhanced RT-DETR model. Sensors 24(17), 5496 (2024). https:\/\/doi.org\/10.3390\/s24175496","journal-title":"Sensors"},{"key":"2378_CR36","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1007\/978-3-030-69251-3","volume-title":"Fundamentals of image data mining: Analysis, Features, Classification and Retrieval","author":"D Zhang","year":"2019","unstructured":"Zhang, D.: Wavelet transform. In: Fundamentals of image data mining: analysis, features, classification and retrieval, pp. 35\u201344. Springer International Publishing, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-69251-3"},{"key":"2378_CR37","doi-asserted-by":"publisher","unstructured":"Chollet, F.: Xception: deep learning with depthwise separable convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 1251\u20131258). (2017). https:\/\/doi.org\/10.1109\/cvpr.2017.195","DOI":"10.1109\/cvpr.2017.195"},{"key":"2378_CR38","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2112.05561","author":"Y Liu","year":"2021","unstructured":"Liu, Y., Shao, Z., Hoffmann, N.: Global attention mechanism: retain information to enhance channel-spatial interactions. arXiv preprint. (2021). https:\/\/doi.org\/10.48550\/arXiv.2112.05561 arXiv:2112.05561","journal-title":"arXiv preprint"},{"key":"2378_CR39","doi-asserted-by":"publisher","unstructured":"Kong, L., Dong, J., Ge, J., Li, M., Pan, J.: Efficient frequency domain-based transformers for high-quality image deblurring. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (pp. 5886\u20135895). (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.00570","DOI":"10.1109\/CVPR52729.2023.00570"},{"key":"2378_CR40","doi-asserted-by":"publisher","unstructured":"Du, D., Zhu, P., Wen, L., Bian, X., Lin, H., Hu, Q., Zhang, L.: VisDrone-DET2019: the vision meets drone object detection in image challenge results. In Proceedings of the IEEE\/CVF international conference on computer vision workshops (pp. 0\u20130). (2019). https:\/\/doi.org\/10.1109\/ICCVW.2019.00031","DOI":"10.1109\/ICCVW.2019.00031"},{"issue":"1","key":"2378_CR41","doi-asserted-by":"publisher","first-page":"227","DOI":"10.48550\/arXiv.2204.03245","volume":"10","author":"J Suo","year":"2023","unstructured":"Suo, J., Wang, T., Zhang, X., Chen, H., Zhou, W., Shi, W.: HIT-UAV: a high-altitude infrared thermal dataset for unmanned aerial vehicle-based object detection. Sci. Data 10(1), 227 (2023). https:\/\/doi.org\/10.48550\/arXiv.2204.03245","journal-title":"Sci. Data"},{"key":"2378_CR42","doi-asserted-by":"publisher","unstructured":"Chen, J., Kao, S.H., He, H., Zhuo, W., Wen, S., Lee, C.H., Chan, S.H.G.: Run, don\u2019t walk: chasing higher FLOPS for faster neural networks. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 12021\u201312031) (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.01157","DOI":"10.1109\/CVPR52729.2023.01157"},{"key":"2378_CR43","doi-asserted-by":"publisher","unstructured":"Woo, S., Debnath, S., Hu, R., Chen, X., Liu, Z., Kweon, I.S., Xie, S.: Convnext v2: co-designing and scaling convnets with masked autoencoders. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 16133\u201316142). (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.01548","DOI":"10.1109\/CVPR52729.2023.01548"},{"key":"2378_CR44","doi-asserted-by":"publisher","first-page":"12934","DOI":"10.48550\/arXiv.2206.01191","volume":"35","author":"Y Li","year":"2022","unstructured":"Li, Y., Yuan, G., Wen, Y., Hu, J., Evangelidis, G., Tulyakov, S., Ren, J.: Efficientformer: vision transformers at mobilenet speed. Adv. Neural. Inf. Process. Syst. 35, 12934\u201312949 (2022). https:\/\/doi.org\/10.48550\/arXiv.2206.01191","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2378_CR45","doi-asserted-by":"publisher","first-page":"7050","DOI":"10.48550\/arXiv.2305.12972","volume":"36","author":"H Chen","year":"2023","unstructured":"Chen, H., Wang, Y., Guo, J., Tao, D.: Vanillanet: the power of minimalism in deep learning. Adv. Neural. Inf. Process. Syst. 36, 7050\u20137064 (2023). https:\/\/doi.org\/10.48550\/arXiv.2305.12972","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2378_CR46","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.107917","volume":"170","author":"Y Chen","year":"2024","unstructured":"Chen, Y., Zhang, C., Chen, B., Huang, Y., Sun, Y., Wang, C., Fu, X., Dai, Y., Qin, F., Peng, Y., Gao, Y.: Accurate leukocyte detection based on deformable-DETR and multi-level feature fusion for aiding diagnosis of blood diseases. Comput. Biol. Med. 170, 107917 (2024). https:\/\/doi.org\/10.1016\/j.compbiomed.2024.107917","journal-title":"Computers in biology and medicine"},{"key":"2378_CR47","doi-asserted-by":"publisher","unstructured":"Yang, Z., Guan, Q., Zhao, K., Yang, J., Xu, X., Long, H., Tang, Y.: Multi-branch auxiliary fusion yolo with re-parameterization heterogeneous convolutional for accurate object detection. In Chinese Conference on Pattern Recognition and Computer Vision (PRCV) (pp. 492\u2013505). Singapore: Springer Nature Singapore. (2024). https:\/\/doi.org\/10.1007\/978-981-97-8858-3_34","DOI":"10.1007\/978-981-97-8858-3_34"},{"issue":"1","key":"2378_CR48","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1007\/s11554-025-01622-0","volume":"22","author":"Y Dong","year":"2025","unstructured":"Dong, Y., Xu, F., Guo, J.: LKR-DETR: Small object detection in remote sensing images based on multi-large kernel convolution. J. Real-Time Image Proc. 22(1), 46 (2025). https:\/\/doi.org\/10.1007\/s11554-025-01622-0","journal-title":"J. Real-Time Image Proc."},{"issue":"2","key":"2378_CR49","doi-asserted-by":"publisher","DOI":"10.3390\/drones9020143","volume":"9","author":"Y Liu","year":"2025","unstructured":"Liu, Y., He, M., Hui, B.: ESO-DETR: an improved real-time detection transformer model for enhanced small object detection inUAV imagery. Drones 9(2), 143 (2025). https:\/\/doi.org\/10.3390\/drones9020143","journal-title":"Drones"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-026-02378-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-026-02378-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-026-02378-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:16:04Z","timestamp":1778048164000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-026-02378-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,6]]},"references-count":49,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,8]]}},"alternative-id":["2378"],"URL":"https:\/\/doi.org\/10.1007\/s00530-026-02378-8","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,6]]},"assertion":[{"value":"8 January 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 March 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 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 conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"304"}}