{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,27]],"date-time":"2026-10-27T20:21:44Z","timestamp":1793132504726,"version":"4.5.0"},"reference-count":95,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T00:00:00Z","timestamp":1770249600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T00:00:00Z","timestamp":1771891200000},"content-version":"vor","delay-in-days":19,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Interdisciplinary Research Project for Young Teachers ofUSTB","award":["FRF-IDRY-23-010"],"award-info":[{"award-number":["FRF-IDRY-23-010"]}]},{"name":"the USTB Research Center for International People-to-people Exchange in Science, Technology and Civilization","award":["2023KFZD001"],"award-info":[{"award-number":["2023KFZD001"]}]},{"name":"the Platform of Data Analysis and Processing for Multimodal Material Large Language Model (LLM)-B","award":["Grant No. z20250473"],"award-info":[{"award-number":["Grant No. z20250473"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Object detection, a cornerstone of computer vision, aims to localize and classify objects within images. This comprehensive survey reviews modern object detection methods, focusing on two dominant paradigms: Convolutional Neural Networks (CNNs) and Transformer-based architectures. This work provides a structured comparison of CNN-based and Transformer-based detection paradigms, highlighting their complementary strengths and trade-offs. CNNs demonstrate advantages in local feature extraction and computational efficiency, whereas Transformers excel at capturing global context through self-attention mechanisms. We also analyze multi-modal fusion techniques integrating Red-Green-Blue (RGB), Light Detection and Ranging (LiDAR), and language embeddings. Benchmark results from representative models include: Real-Time Detection Transformer (RT-DETR) achieves 53.1% mean Average Precision (mAP) at Intersection over Union (IoU) at 0.5\u00a0:\u00a00.95, You Only Look Once version 8 (YOLOv8) achieves 50.2% mAP at 0.5:0.95, real-time detectors exceed 100 frames per second (FPS) with competitive accuracy, and specialized infrared methods achieve 92.45% F-measure on NUAA-SIRST dataset. The work introduces a novel taxonomy of multi-modal fusion strategies, documents field-wide and review-specific limitations, and synthesizes recent 2024 to 2025 benchmarks across diverse datasets. Despite these advances, significant challenges remain in handling scale variation, occlusion effects, and domain adaptation. This survey outlines these persistent obstacles and promising research directions, providing a structured reference for researchers and practitioners.<\/jats:p>","DOI":"10.1038\/s41598-026-37052-6","type":"journal-article","created":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T08:48:45Z","timestamp":1770281325000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["The evolution of object detection from CNNs to transformers and multi-modal fusion"],"prefix":"10.1038","volume":"16","author":[{"given":"Zeran","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuan","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuhao","family":"Gu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xudong","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mianwang","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,2,5]]},"reference":[{"key":"37052_CR1","doi-asserted-by":"crossref","unstructured":"Prakash, A., Chitta, K., Geiger, A. Multi-modal fusion transformer for end-to-end autonomous driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition vol. 2021, pp. 7077\u20137087.","DOI":"10.1109\/CVPR46437.2021.00700"},{"issue":"8","key":"37052_CR2","doi-asserted-by":"publisher","first-page":"14047","DOI":"10.1109\/JIOT.2023.3339476","volume":"11","author":"H Tao","year":"2023","unstructured":"Tao, H. Smoke recognition in satellite imagery via an attention pyramid network with bidirectional multilevel multigranularity feature aggregation and gated fusion[J]. IEEE Internet Things J. 11(8), 14047\u201314057 (2023).","journal-title":"IEEE Internet Things J."},{"key":"37052_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107853","volume":"239","author":"Q Zhou","year":"2022","unstructured":"Zhou, Q. et al. MOLS-Net: Multi-organ and lesion segmentation network based on sequence feature pyramid and attention mechanism for aortic dissection diagnosis[J]. Knowl.-Based Syst. 239, 107853 (2022).","journal-title":"Knowl.-Based Syst."},{"key":"37052_CR4","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.106217","volume":"123","author":"G Liu","year":"2023","unstructured":"Liu, G. et al. Lightweight object detection algorithm for robots with improved YOLOv5. Eng. Appl. Artif. Intell. 123, 106217 (2023).","journal-title":"Eng. Appl. Artif. Intell."},{"key":"37052_CR5","volume":"130","author":"L Xie","year":"2020","unstructured":"Xie, L., Zhang, L. & Liu, X. A comprehensive survey of object detection in robotics: Challenges and future directions. Robot. Auton. Syst. 130, 103565 (2020).","journal-title":"Robot. Auton. Syst."},{"issue":"1","key":"37052_CR6","first-page":"56","volume":"39","author":"Y Li","year":"2022","unstructured":"Li, Y., Wang, S. & Chen, Z. Deep learning-based object detection and its applications in robotics. J. Field Robot. 39(1), 56\u201372 (2022).","journal-title":"J. Field Robot."},{"key":"37052_CR7","unstructured":"Hussain, M. YOLOv5, YOLOv8, and YOLOv10: The go-to detectors for real-time vision. arXiv:2407.02988 (2024)."},{"key":"37052_CR8","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y. & Berg, A. C. SSD: Single shot multibox detector. In: Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany 21\u201337 (2019).","DOI":"10.1007\/978-3-319-46448-0_2"},{"issue":"4","key":"37052_CR9","first-page":"112","volume":"18","author":"Y Zhang","year":"2022","unstructured":"Zhang, Y., Chen, X. & Li, X. Efficient object detection in robotics: A survey of advancements and challenges. Robot. Sci. Syst. 18(4), 112\u2013129 (2022).","journal-title":"Robot. Sci. Syst."},{"key":"37052_CR10","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A. & Zagoruyko, S. End-to-end object detection with Transformers. arXiv:2005.12872 (2020).","DOI":"10.1007\/978-3-030-58452-8_13"},{"issue":"8","key":"37052_CR11","first-page":"1841","volume":"37","author":"X Zhou","year":"2021","unstructured":"Zhou, X., Yang, Z. & Zhang, S. Multi-modal sensor fusion for object detection in dynamic environments. IEEE Trans. Rob. 37(8), 1841\u20131854 (2021).","journal-title":"IEEE Trans. Rob."},{"key":"37052_CR12","volume":"150","author":"Q Chen","year":"2023","unstructured":"Chen, Q., Li, Y. & Wu, M. Challenges and solutions in multi-modal object detection for robotics. Robot. Auton. Syst. 150, 103933 (2023).","journal-title":"Robot. Auton. Syst."},{"key":"37052_CR13","doi-asserted-by":"publisher","first-page":"2847","DOI":"10.1109\/ACCESS.2019.2962554","volume":"8","author":"Z Wang","year":"2020","unstructured":"Wang, Z., Wu, Y. & Niu, Q. Multi-sensor fusion in automated driving: A survey. IEEE Access 8, 2847\u20132868 (2020).","journal-title":"IEEE Access"},{"issue":"13","key":"37052_CR14","doi-asserted-by":"publisher","first-page":"24013","DOI":"10.1109\/JIOT.2024.3388045","volume":"11","author":"X Min","year":"2024","unstructured":"Min, X. et al. Lwuavdet: A lightweight uav object detection network on edge devices[J]. IEEE Internet Things J. 11(13), 24013\u201324023 (2024).","journal-title":"IEEE Internet Things J."},{"issue":"3","key":"37052_CR15","doi-asserted-by":"publisher","first-page":"2467","DOI":"10.1109\/TETCI.2024.3367821","volume":"8","author":"X Yue","year":"2024","unstructured":"Yue, X. & Meng, L. Yolo-sm: A lightweight single-class multi-deformation object detection network. IEEE Trans. Emerg. Top. Comput. Intell. 8(3), 2467\u20132480 (2024).","journal-title":"IEEE Trans. Emerg. Top. Comput. Intell."},{"key":"37052_CR16","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2024.121366","volume":"686","author":"Q Fan","year":"2025","unstructured":"Fan, Q. et al. LUD-YOLO: A novel lightweight object detection network for unmanned aerial vehicle[J]. Inf. Sci. 686, 121366 (2025).","journal-title":"Inf. Sci."},{"issue":"9","key":"37052_CR17","doi-asserted-by":"publisher","first-page":"2905","DOI":"10.3390\/s24092905","volume":"24","author":"X Jiang","year":"2024","unstructured":"Jiang, X. et al. YOLOv8-MU: An improved YOLOv8 underwater detector based on a large kernel block and a multi-branch reparameterization module[J]. Sensors 24(9), 2905 (2024).","journal-title":"Sensors"},{"issue":"19","key":"37052_CR18","doi-asserted-by":"publisher","first-page":"6209","DOI":"10.3390\/s24196209","volume":"24","author":"B Khalili","year":"2024","unstructured":"Khalili, B. & Smyth, A. W. Sod-yolov8\u2013enhancing yolov8 for small object detection in aerial imagery and traffic scenes[J]. Sensors 24(19), 6209 (2024).","journal-title":"Sensors"},{"key":"37052_CR19","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.127685","volume":"588","author":"S Sun","year":"2024","unstructured":"Sun, S. et al. Multi-YOLOv8: An infrared moving small object detection model based on YOLOv8 for air vehicle[J]. Neurocomputing 588, 127685 (2024).","journal-title":"Neurocomputing"},{"key":"37052_CR20","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Lv, W. & Xu, S. et al. Detrs beat yolos on real-time object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition 16965\u201316974 (2024).","DOI":"10.1109\/CVPR52733.2024.01605"},{"key":"37052_CR21","doi-asserted-by":"crossref","unstructured":"Cho, J. H. & Kr\u00e4henb\u00fchl, P. Language-conditioned detection transformer. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition 16593\u201316603 (2024).","DOI":"10.1109\/CVPR52733.2024.01570"},{"key":"37052_CR22","doi-asserted-by":"crossref","unstructured":"Koohpayegani, S.A. & Pirsiavash, H. Sima: Simple softmax-free attention for vision Transformers. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision 2607\u20132617 (2024).","DOI":"10.1109\/WACV57701.2024.00259"},{"key":"37052_CR23","doi-asserted-by":"crossref","unstructured":"Xu, X., Wang, S. & Chen, Y. et al. GTP-ViT: efficient Vision Transformers via graph-based token propagation. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision 86\u201395 (2024).","DOI":"10.1109\/WACV57701.2024.00016"},{"key":"37052_CR24","doi-asserted-by":"crossref","unstructured":"Prakash, A., Chitta, K. & Geiger, A. Multi-modal fusion transformer for end-to-end autonomous driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 7077\u20137087 (2021).","DOI":"10.1109\/CVPR46437.2021.00700"},{"key":"37052_CR25","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Chen, J. & Huang, D. Cat-det: Contrastively augmented transformer for multi-modal 3d object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition 908\u2013917 (2022).","DOI":"10.1109\/CVPR52688.2022.00098"},{"key":"37052_CR26","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107853","volume":"239","author":"Q Zhou","year":"2022","unstructured":"Zhou, Q. et al. MOLS-Net: Multi-organ and lesion segmentation network based on sequence feature pyramid and attention mechanism for aortic dissection diagnosis[J]. Knowl.-Based Syst. 239, 107853 (2022).","journal-title":"Knowl.-Based Syst."},{"key":"37052_CR27","doi-asserted-by":"crossref","unstructured":"Yu, J., Cheng, Y., & Zhao, R.W. et al. Mm-pyramid: Multimodal pyramid attentional network for audio-visual event localization and video parsing. In: Proceedings of the 30th ACM International Conference on Multimedia 6241\u20136249 (2022).","DOI":"10.1145\/3503161.3547869"},{"issue":"12","key":"37052_CR28","doi-asserted-by":"publisher","first-page":"3541","DOI":"10.1049\/ipr2.12884","volume":"17","author":"W Liu","year":"2023","unstructured":"Liu, W. et al. Multi-modal object detection via transformer network[J]. IET Image Proc. 17(12), 3541\u20133550 (2023).","journal-title":"IET Image Proc."},{"key":"37052_CR29","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.106217","volume":"123","author":"G Liu","year":"2023","unstructured":"Liu, G., Hu, Y., Chen, Z., Wang, H. & Zhang, L. Lightweight object detection algorithm for robots with improved YOLOv5. Eng. Appl. Artif. Intell. 123, 106217 (2023).","journal-title":"Eng. Appl. Artif. Intell."},{"key":"37052_CR30","doi-asserted-by":"crossref","unstructured":"Zhong, T., Gan, Y., Han, Z., Li, J. & Chen, W. A lightweight object detection network for industrial robot based on YOLOv5. In: Proceedings of the 2023 China Automation Congress (CAC), Beijing, China 4685\u20134690 (2023).","DOI":"10.1109\/CAC59555.2023.10449979"},{"issue":"1","key":"37052_CR31","doi-asserted-by":"publisher","first-page":"9711","DOI":"10.1038\/s41598-023-36868-w","volume":"13","author":"X Jia","year":"2023","unstructured":"Jia, X., Tong, Y., Qiao, H., Li, S. & Wang, Z. Fast and accurate object detector for autonomous driving based on improved YOLOv5. Sci. Rep. 13(1), 9711 (2023).","journal-title":"Sci. Rep."},{"key":"37052_CR32","doi-asserted-by":"crossref","unstructured":"Tang, S., Zhang, S., Fang, Y., Zhao, L. & Wu, J. HIC-YOLOv5: Improved YOLOv5 for small object detection. In: Proceedings of the 2024 IEEE International Conference on Robotics and Automation (ICRA), Yokohama, Japan 6614\u20136619 (2024).","DOI":"10.1109\/ICRA57147.2024.10610273"},{"key":"37052_CR33","doi-asserted-by":"crossref","unstructured":"Li, X., Pan, B., Cheng, Y., Xu, M. & Zhang, H. Underwater fish object detection based on attention mechanism improved ghost-YOLOv5. In: Proceedings of the 2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP), Xi\u2019an, China 599\u2013603 (2022).","DOI":"10.1109\/ICSP54964.2022.9778582"},{"key":"37052_CR34","unstructured":"Ma, S. & Xu, Y. MPDIoU: A loss for efficient and accurate bounding box regression. arXiv:2307.07662 (2023)."},{"issue":"9","key":"37052_CR35","doi-asserted-by":"publisher","first-page":"2905","DOI":"10.3390\/s24092905","volume":"24","author":"X Jiang","year":"2024","unstructured":"Jiang, X., Zhuang, X., Chen, J., Wang, Y. & Liu, L. YOLOv8-MU: An improved YOLOv8 underwater detector based on a large kernel block and a multi-branch reparameterization module. Sensors 24(9), 2905 (2024).","journal-title":"Sensors"},{"issue":"3","key":"37052_CR36","doi-asserted-by":"publisher","first-page":"1095","DOI":"10.3390\/app14031095","volume":"14","author":"M Zhang","year":"2024","unstructured":"Zhang, M., Wang, Z., Song, W., Li, Y. & Chen, X. Efficient small-object detection in underwater images using the enhanced YOLOv8 network. Appl. Sci. 14(3), 1095 (2024).","journal-title":"Appl. Sci."},{"key":"37052_CR37","doi-asserted-by":"crossref","unstructured":"Khalili, B. & Smyth, A. W. SOD-YOLOv8: Enhancing YOLOv8 for small object detection in traffic scenes. arXiv:2408.04786 (2024).","DOI":"10.3390\/s24196209"},{"key":"37052_CR38","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.127685","volume":"588","author":"S Sun","year":"2024","unstructured":"Sun, S., Mo, B., Xu, J., Yang, L. & Zhang, Q. Multi-YOLOv8: An infrared moving small object detection model based on YOLOv8 for air vehicle. Neurocomputing 588, 127685 (2024).","journal-title":"Neurocomputing"},{"key":"37052_CR39","doi-asserted-by":"publisher","DOI":"10.1016\/j.aei.2024.102709","volume":"62","author":"D Wan","year":"2024","unstructured":"Wan, D., Lu, R., Hu, B., Zhou, Y. & Li, T. YOLO-MIF: Improved YOLOv8 with multi-information fusion for object detection in gray-scale images. Adv. Eng. Inform. 62, 102709 (2024).","journal-title":"Adv. Eng. Inform."},{"issue":"6","key":"37052_CR40","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2016","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(6), 1137\u20131149 (2016).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"37052_CR41","doi-asserted-by":"crossref","unstructured":"Dhakal, S., Chen, Q., Qu, D., Wang, Y. & Li, X. Sniffer Faster R-CNN: A joint camera-LiDAR object detection framework with proposal refinement. In: Proceedings of the 2023 IEEE International Conference on Mobility, Operations, Services, and Technologies (MOST), Singapore 1\u201310 (2023).","DOI":"10.1109\/MOST57249.2023.00009"},{"key":"37052_CR42","doi-asserted-by":"crossref","unstructured":"Liu, Y., Zhou, S., Liu, X., Wu, Z. & Chen, H. Unbiased Faster R-CNN for single-source domain generalized object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA 28838\u201328847 (2024).","DOI":"10.1109\/CVPR52733.2024.02724"},{"key":"37052_CR43","doi-asserted-by":"publisher","DOI":"10.1016\/j.compind.2021.103551","volume":"134","author":"M Chen","year":"2022","unstructured":"Chen, M., Yu, L., Zhi, C., Zhang, X. & Huang, W. Improved Faster R-CNN for fabric defect detection based on Gabor filter with genetic algorithm optimization. Comput. Ind. 134, 103551 (2022).","journal-title":"Comput. Ind."},{"key":"37052_CR44","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecoinf.2023.102210","volume":"77","author":"J Li","year":"2023","unstructured":"Li, J., Zhu, Z., Liu, H., Wang, Y. & Guo, X. Strawberry R-CNN: Recognition and counting model of strawberry based on improved Faster R-CNN. Eco. Inform. 77, 102210 (2023).","journal-title":"Eco. Inform."},{"key":"37052_CR45","unstructured":"Vaswani, A. et al. Attention is all you need. Adv. Neural Inf. Process. Syst. 30, (2017)."},{"key":"37052_CR46","doi-asserted-by":"crossref","unstructured":"Koohpayegani, S. A. & Pirsiavash, H. SIMA: Simple softmax-free attention for vision Transformers. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), Waikoloa, HI, USA 2607\u20132617 (2024).","DOI":"10.1109\/WACV57701.2024.00259"},{"key":"37052_CR47","doi-asserted-by":"crossref","unstructured":"Zheng, D., Dong, W., Hu, H., Zhang, Y. & Wang, L. Less is more: Focus attention for efficient DETR. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), Paris, France 6674\u20136683 (2023).","DOI":"10.1109\/ICCV51070.2023.00614"},{"key":"37052_CR48","doi-asserted-by":"crossref","unstructured":"Xu, X., Wang, S., Chen, Y., Li, Z. & Zhao, Q. GTP-ViT: Efficient vision Transformers via graph-based token propagation. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), Waikoloa, HI, USA 86\u201395 (2024).","DOI":"10.1109\/WACV57701.2024.00016"},{"key":"37052_CR49","doi-asserted-by":"crossref","unstructured":"Bulat, A., Guerrero, R., Martinez, B., Alvi, J., Desai, K. & Torresani, L. FS-DETR: Few-shot detection Transformer with prompting and without re-training. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), Paris, France 11793\u201311802 (2023).","DOI":"10.1109\/ICCV51070.2023.01083"},{"key":"37052_CR50","doi-asserted-by":"crossref","unstructured":"Liu, F., Zhang, X., Peng, Z., Zhou, W., Li, Q. & Yang, H. Integrally migrating pre-trained Transformer encoder-decoders for visual object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), Paris, France 6825\u20136834 (2023).","DOI":"10.1109\/ICCV51070.2023.00628"},{"key":"37052_CR51","doi-asserted-by":"crossref","unstructured":"Dai, Z., Cai, B., Lin, Y., Zhang, J., Wang, Y. & Hu, H. UP-DETR: Unsupervised pre-training for object detection with Transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA 1601\u20131610 (2021).","DOI":"10.1109\/CVPR46437.2021.00165"},{"key":"37052_CR52","doi-asserted-by":"crossref","unstructured":"Chen, D. J., Hsieh, H.-Y. & Liu, T.-L. (2021) Adaptive image Transformer for one-shot object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA 12247\u201312256.","DOI":"10.1109\/CVPR46437.2021.01207"},{"key":"37052_CR53","doi-asserted-by":"crossref","unstructured":"Cho, J. H. & Kr\u00e4henb\u00fchl, P. P. Language-conditioned detection Transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA 16593\u201316603 (2024).","DOI":"10.1109\/CVPR52733.2024.01570"},{"issue":"8","key":"37052_CR54","doi-asserted-by":"publisher","first-page":"3541","DOI":"10.1049\/ipr2.12884","volume":"17","author":"W Liu","year":"2023","unstructured":"Liu, W., Wang, H., Gao, Q. & Zhu, Z. Multi-modal object detection via Transformer network. IET Image Proc. 17(8), 3541\u20133550 (2023).","journal-title":"IET Image Proc."},{"key":"37052_CR55","doi-asserted-by":"crossref","unstructured":"Prakash, A., Chitta, K. & Geiger, A. Multi-modal fusion Transformer for end-to-end autonomous driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA 7077\u20137087 (2021).","DOI":"10.1109\/CVPR46437.2021.00700"},{"key":"37052_CR56","doi-asserted-by":"crossref","unstructured":"Zhang, Y. Chen, J. & Huang, D. CAT-DET: Contrastively augmented Transformer for multi-modal 3D object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA 908\u2013917 (2022).","DOI":"10.1109\/CVPR52688.2022.00098"},{"key":"37052_CR57","doi-asserted-by":"crossref","unstructured":"Curto, D., Clap\u00e9s, A., Selva, J., Villanueva, M. & Escalera, S. Dyadformer: A multi-modal Transformer for long-range modeling of dyadic interactions. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), Montreal, Canada 2177\u20132188 ( 2021).","DOI":"10.1109\/ICCVW54120.2021.00247"},{"key":"37052_CR58","doi-asserted-by":"crossref","unstructured":"Shvetsova, N., Chen, B., Rouditchenko, A., Thomas, S. & Kuehne, H. Everything at once: Multi-modal fusion Transformer for video retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA 20020\u201320029 (2022).","DOI":"10.1109\/CVPR52688.2022.01939"},{"key":"37052_CR59","doi-asserted-by":"crossref","unstructured":"Xu et al. PointFusion: Deep Sensor Fusion for 3D Bounding Box Estimation. In: CVPR (2018).","DOI":"10.1109\/CVPR.2018.00033"},{"key":"37052_CR60","doi-asserted-by":"crossref","unstructured":"Ku et al. Joint 3D proposal generation and object detection from view aggregation. IROS (2018).","DOI":"10.1109\/IROS.2018.8594049"},{"key":"37052_CR61","doi-asserted-by":"crossref","unstructured":"Geiger et al. Vision meets Robotics: The KITTI dataset. IJRR (2013).","DOI":"10.1177\/0278364913491297"},{"key":"37052_CR62","doi-asserted-by":"crossref","unstructured":"Caesar et al. nuScenes: A Multimodal Dataset for Autonomous Driving. In: CVPR (2020).","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"37052_CR63","doi-asserted-by":"crossref","unstructured":"Prakash, A., Chitta, K. & Geiger, A. Multi-modal fusion Transformer for end-to-end autonomous driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA 7077\u20137087 (2021).","DOI":"10.1109\/CVPR46437.2021.00700"},{"key":"37052_CR64","doi-asserted-by":"crossref","unstructured":"Zhang Y., Chen, J. & Huang, D. \u201cCat-det: Contrastively augmented transformer for multi-modal 3d object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2022).","DOI":"10.1109\/CVPR52688.2022.00098"},{"key":"37052_CR65","doi-asserted-by":"crossref","unstructured":"Dai et al. ScanNet: Richly-Annotated 3D Reconstructions of Indoor Scenes. In CVPR (2017).","DOI":"10.1109\/CVPR.2017.261"},{"key":"37052_CR66","unstructured":"Liang et al. CLASTA: A late fusion framework for multi-modal 3D object detection. In: ICRA (2023)."},{"key":"37052_CR67","doi-asserted-by":"crossref","unstructured":"Sun et al. Scalability in perception for autonomous driving: Waymo open dataset. In: CVPR (2020).","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"37052_CR68","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Mintun, E. & Ravi, N. et al. Segment anything. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision 4015\u20134026 (2023).","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"37052_CR69","doi-asserted-by":"crossref","unstructured":"Wang, Y., Zhang, X. & Yang, T. et al. Anchor detr: Query design for transformer-based detector. In: Proceedings of the AAAI Conference on Artificial Intelligence vol. 36(3), pp. 2567\u20132575 (2022).","DOI":"10.1609\/aaai.v36i3.20158"},{"key":"37052_CR70","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Mintun. E., & Ravi, N. et al. Segment anything. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision 4015\u20134026 (2023).","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"37052_CR71","doi-asserted-by":"crossref","unstructured":"Liu, S., Zeng, Z., & Ren, T. et al. Grounding dino: Marrying dino with grounded pre-training for open-set object detection. In: European Conference on Computer Vision 38\u201355 (Springer Nature Switzerland, 2024).","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"37052_CR72","doi-asserted-by":"crossref","unstructured":"Li, L. H., Zhang, P. & Zhang, H. et al. Grounded language-image pre-training. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition 10965\u201310975 (2022).","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"37052_CR73","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Maire, M., Belongie, S., Bourdev, L., Girshick, R., Hays, J., Perona, P., Ramanan, D., Zitnick C. L. & Dollar, P. Microsoft COCO: Common objects in context. In: European Conference on Computer Vision (ECCV), Zurich, Switzerland 740\u2013755 (2014).","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"37052_CR74","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Lv, W., Xu, S., Jin, J. & Tian, Q. DETR beats YOLOs on real-time object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA 16965\u201316974 (2024).","DOI":"10.1109\/CVPR52733.2024.01605"},{"key":"37052_CR75","doi-asserted-by":"publisher","unstructured":"Ji, Y., Ding, Y., Zhou, J. & Zhang, K. Robust and accurate multi-UAV cooperative semantic SLAM leveraging lightweight YOLO. In: Proceedings of the 2023 7th International Symposium on Computer Science and Intelligent Control (ISCSIC), Nanjing, China 155\u2013159, (2023). https:\/\/doi.org\/10.1109\/ISCSIC60498.2023.00041.","DOI":"10.1109\/ISCSIC60498.2023.00041"},{"key":"37052_CR76","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.127685","volume":"588","author":"S Sun","year":"2024","unstructured":"Sun, S., Mo, B., Xu, J., Wang, L. & Liu, Z. Multi-YOLOv8: An infrared moving small object detection model based on YOLOv8 for air vehicle. Neurocomputing 588, 127685 (2024).","journal-title":"Neurocomputing"},{"key":"37052_CR77","first-page":"1","volume":"62","author":"S Xu","year":"2024","unstructured":"Xu, S., Li, F., Song, Z., Chen, Y. & Zhang, H. Multi-sem fusion: Multimodal semantic fusion for 3D object detection. IEEE Trans. Geosci. Remote Sens. 62, 1\u201315 (2024).","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"issue":"4","key":"37052_CR78","first-page":"5123","volume":"35","author":"G Chen","year":"2024","unstructured":"Chen, G., Wang, Q., Dong, B., Liu, W. & Li, X. Edge-aware multimodal Transformer for RGB-D salient object detection. IEEE Trans. Neural Netw. Learn. Syst. 35(4), 5123\u20135135 (2024).","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"37052_CR79","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.106217","volume":"123","author":"G Liu","year":"2023","unstructured":"Liu, G., Hu, Y., Chen, Z., Zhang, L. & Yang, M. Lightweight object detection algorithm for robots with improved YOLOv5. Eng. Appl. Artif. Intell. 123, 106217 (2023).","journal-title":"Eng. Appl. Artif. Intell."},{"issue":"9","key":"37052_CR80","doi-asserted-by":"publisher","first-page":"242","DOI":"10.1007\/s10462-024-10877-1","volume":"57","author":"P Mittal","year":"2024","unstructured":"Mittal, P. A comprehensive survey of deep learning-based lightweight object detection models for edge devices. Artif. Intell. Rev. 57(9), 242 (2024).","journal-title":"Artif. Intell. Rev."},{"issue":"5","key":"37052_CR81","first-page":"8765","volume":"11","author":"X Min","year":"2024","unstructured":"Min, X., Zhou, W., Hu, R., Zhao, L. & Wang, T. LWuAVDet: A lightweight UAV object detection network on edge devices. IEEE Internet Things J. 11(5), 8765\u20138778 (2024).","journal-title":"IEEE Internet Things J."},{"issue":"2","key":"37052_CR82","first-page":"1024","volume":"8","author":"X Yue","year":"2024","unstructured":"Yue, X. & Meng, L. YOLO-SM: A lightweight single-class multi-deformation object detection network. IEEE Trans. Emerg. Top. Comput. Intell. 8(2), 1024\u20131036 (2024).","journal-title":"IEEE Trans. Emerg. Top. Comput. Intell."},{"key":"37052_CR83","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2024.121366","volume":"686","author":"Q Fan","year":"2025","unstructured":"Fan, Q., Li, Y., Deveci, M., Chen, R. & Wang, Z. LUD-YOLO: A novel lightweight object detection network for unmanned aerial vehicle. Inf. Sci. 686, 121366 (2025).","journal-title":"Inf. Sci."},{"key":"37052_CR84","doi-asserted-by":"crossref","unstructured":"Nigam, C., Kirubasri, G., Jayachitra, S., Kumar,V., & Sharma, A. Real-time object detection on edge devices using mobile neural networks. In: Proceedings of the 2024 International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics (IITCEE), Kuala Lumpur, Malaysia 1\u20134 (2024).","DOI":"10.1109\/IITCEE59897.2024.10467220"},{"issue":"5","key":"37052_CR85","doi-asserted-by":"publisher","first-page":"3086","DOI":"10.1109\/TNSE.2022.3151502","volume":"10","author":"Y Wu","year":"2022","unstructured":"Wu, Y., Li, X., Wang, Z., Zhang, H. & Chen, L. Edge computing driven low-light image dynamic enhancement for object detection. IEEE Trans. Netw. Sci. Eng. 10(5), 3086\u20133098 (2022).","journal-title":"IEEE Trans. Netw. Sci. Eng."},{"key":"37052_CR86","unstructured":"Zhang, Y.-M., Chen, L., Wang, H., Li, T. & Zhou, J. (2021) CSL-YOLO: A new lightweight object detection system for edge computing. arXiv:2107.04829."},{"issue":"12","key":"37052_CR87","doi-asserted-by":"publisher","first-page":"25345","DOI":"10.1109\/TITS.2022.3158253","volume":"23","author":"S Liang","year":"2022","unstructured":"Liang, S., Zhang, Y., Li, T., Xu, W. & Liu, K. Edge YOLO: Real-time intelligent object detection system based on edge-cloud cooperation in autonomous vehicles. IEEE Trans. Intell. Transp. Syst. 23(12), 25345\u201325360 (2022).","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"37052_CR88","doi-asserted-by":"crossref","unstructured":"Liu, S., Wang, J., Zhang, K., Yang, L., & Li, H. EdgeYOLO: An edge-real-time object detector. In: Proceedings of the 42nd Chinese Control Conference (CCC), Tianjin, China 6782\u20136787 (2023).","DOI":"10.23919\/CCC58697.2023.10239786"},{"key":"37052_CR89","doi-asserted-by":"crossref","unstructured":"Li, Y., Chen, X., Liu, Z., Zhang, W. & Wang, Q. DeepFusion: LiDAR-camera deep fusion for multi-modal 3D object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA 17182\u201317191 (2022).","DOI":"10.1109\/CVPR52688.2022.01667"},{"issue":"3","key":"37052_CR90","doi-asserted-by":"publisher","first-page":"8260","DOI":"10.1109\/LRA.2022.3187264","volume":"7","author":"J Wang","year":"2022","unstructured":"Wang, J., Zhang, S., Li, Y., Chen, H. & Zhao, L. DeepFusionMOT: A 3D multi-object tracking framework based on camera-LiDAR fusion with deep association. IEEE Robot. Autom. Lett. 7(3), 8260\u20138267 (2022).","journal-title":"IEEE Robot. Autom. Lett."},{"key":"37052_CR91","doi-asserted-by":"publisher","first-page":"1158","DOI":"10.1109\/TMM.2023.3277281","volume":"26","author":"L Zhao","year":"2023","unstructured":"Zhao, L., Wang, H., Zhang, Q., Liu, Y. & Chen, X. LiF-Seg: LiDAR and camera image fusion for 3D LiDAR semantic segmentation. IEEE Trans. Multimedia 26, 1158\u20131168 (2023).","journal-title":"IEEE Trans. Multimedia"},{"issue":"8","key":"37052_CR92","doi-asserted-by":"publisher","first-page":"14047","DOI":"10.1109\/JIOT.2023.3339476","volume":"11","author":"H Tao","year":"2023","unstructured":"Tao, H. Smoke recognition in satellite imagery via an attention pyramid network with bidirectional multilevel multigranularity feature aggregation and gated fusion. IEEE Internet Things J. 11(8), 14047\u201314057 (2023).","journal-title":"IEEE Internet Things J."},{"key":"37052_CR93","doi-asserted-by":"crossref","unstructured":"Yu, J., Wang, Y., Liu, Z., Zhang, L. & Zhou, M. MM-Pyramid: Multimodal pyramid attentional network for audio-visual event localization and video parsing. In: Proceedings of the 30th ACM International Conference on Multimedia, Lisbon, Portugal 1234\u20131243 (2022).","DOI":"10.1145\/3503161.3547869"},{"key":"37052_CR94","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107853","volume":"239","author":"Q Zhou","year":"2022","unstructured":"Zhou, Q., Li, X., Zhang, H., Wang, Y. & Liu, Z. MOLS-Net: Multi-organ and lesion segmentation network based on sequence feature pyramid and attention mechanism for aortic dissection diagnosis. Knowl.-Based Syst. 239, 107853 (2022).","journal-title":"Knowl.-Based Syst."},{"key":"37052_CR95","doi-asserted-by":"crossref","unstructured":"Ali-Bey, A., Chaib-Draa, B., & Gigu\u00e8re, P. MixVPR: Feature mixing for visual place recognition. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), Waikoloa, HI, USA 2998\u20133007 (2023).","DOI":"10.1109\/WACV56688.2023.00301"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-37052-6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-37052-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-37052-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T00:07:52Z","timestamp":1771978072000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-37052-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,5]]},"references-count":95,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["37052"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-37052-6","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,5]]},"assertion":[{"value":"6 October 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 January 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 February 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":"7517"}}