{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T01:48:02Z","timestamp":1777081682450,"version":"3.51.4"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Real-Time Image Proc"],"published-print":{"date-parts":[[2024,4]]},"DOI":"10.1007\/s11554-024-01426-8","type":"journal-article","created":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T05:05:01Z","timestamp":1709269501000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Improving small object detection via context-aware and feature-enhanced plug-and-play modules"],"prefix":"10.1007","volume":"21","author":[{"given":"Xiao","family":"He","sequence":"first","affiliation":[]},{"given":"Xiaolong","family":"Zheng","sequence":"additional","affiliation":[]},{"given":"Xiyu","family":"Hao","sequence":"additional","affiliation":[]},{"given":"Heng","family":"Jin","sequence":"additional","affiliation":[]},{"given":"Xiangming","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Lihuan","family":"Shao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,3,1]]},"reference":[{"key":"1426_CR1","doi-asserted-by":"publisher","first-page":"128837","DOI":"10.1109\/ACCESS.2019.2939201","volume":"7","author":"L Jiao","year":"2019","unstructured":"Jiao, L., Zhang, F., Liu, F., Yang, S., Li, L., Feng, Z., Qu, R.: A survey of deep learning-based object detection. IEEE Access 7, 128837\u2013128868 (2019). https:\/\/doi.org\/10.1109\/ACCESS.2019.2939201","journal-title":"IEEE Access"},{"key":"1426_CR2","doi-asserted-by":"crossref","unstructured":"Zou, Z., Chen, K., Shi, Z., Guo, Y., Ye, J.: Object detection in 20 years: A survey (2023) arXiv:1905.05055 [cs.CV]","DOI":"10.1109\/JPROC.2023.3238524"},{"key":"1426_CR3","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2023.3290594","author":"G Cheng","year":"2023","unstructured":"Cheng, G., Yuan, X., Yao, X., Yan, K., Zeng, Q., Xie, X., Han, J.: Towards large-scale small object detection: survey and benchmarks. IEEE Trans. Pattern Anal. Mach. Intell. (2023). https:\/\/doi.org\/10.1109\/tpami.2023.3290594","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"2","key":"1426_CR4","doi-asserted-by":"publisher","first-page":"936","DOI":"10.1109\/TSMC.2020.3005231","volume":"52","author":"G Chen","year":"2022","unstructured":"Chen, G., Wang, H., Chen, K., Li, Z., Song, Z., Liu, Y., Chen, W., Knoll, A.: A survey of the four pillars for small object detection: multiscale representation, contextual information, super-resolution, and region proposal. IEEE Trans. Syst., Man., Cybern.: Syst. 52(2), 936\u2013953 (2022). https:\/\/doi.org\/10.1109\/TSMC.2020.3005231","journal-title":"IEEE Trans. Syst., Man., Cybern.: Syst."},{"key":"1426_CR5","doi-asserted-by":"publisher","DOI":"10.1111\/mice.12334","author":"Y Cha","year":"2018","unstructured":"Cha, Y., Choi, W., Suh, G., Mahmoudkhani, S., B\u00fcy\u00fck\u00f6zt\u00fcrk, O.: Autonomous structural visual inspection using region-based deep learning for detecting multiple damage types. Comput. Aided Civ. Infrastruct. Eng. (2018). https:\/\/doi.org\/10.1111\/mice.12334","journal-title":"Comput. Aided Civ. Infrastruct. Eng."},{"issue":"10","key":"1426_CR6","doi-asserted-by":"publisher","first-page":"3782","DOI":"10.1109\/TITS.2019.2892405","volume":"20","author":"E Arnold","year":"2019","unstructured":"Arnold, E., Al-Jarrah, O.Y., Dianati, M., Fallah, S., Oxtoby, D., Mouzakitis, A.: A survey on 3d object detection methods for autonomous driving applications. IEEE Trans. Intell. Transp. Syst. 20(10), 3782\u20133795 (2019). https:\/\/doi.org\/10.1109\/TITS.2019.2892405","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"1426_CR7","doi-asserted-by":"publisher","first-page":"3465","DOI":"10.1007\/s00170-017-0882-0","volume":"94","author":"T Wang","year":"2018","unstructured":"Wang, T., Chen, Y., Qiao, M., Snoussi, H.: A fast and robust convolutional neural network-based defect detection model in product quality control. Int. J. Adv. Manuf. Technol. 94, 3465\u20133471 (2018)","journal-title":"Int. J. Adv. Manuf. Technol."},{"key":"1426_CR8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3119563","author":"P Zhu","year":"2021","unstructured":"Zhu, P., Wen, L., Du, D., Bian, X., Fan, H., Hu, Q., Ling, H.: Detection and tracking meet drones challenge. IEEE Trans. Pattern Anal. Mach. Intell. (2021). https:\/\/doi.org\/10.1109\/TPAMI.2021.3119563","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1426_CR9","doi-asserted-by":"publisher","unstructured":"Wang, J., Yang, W., Guo, H., Zhang, R., Xia, G.-S.: Tiny object detection in aerial images. In: 25th International Conference on Pattern Recognition (ICPR), pp. 3791\u20133798 (2021). https:\/\/doi.org\/10.1109\/ICPR48806.2021.9413340","DOI":"10.1109\/ICPR48806.2021.9413340"},{"key":"1426_CR10","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1007\/s11263-013-0620-5","volume":"104","author":"JRR Uijlings","year":"2013","unstructured":"Uijlings, J.R.R., Sande, K.E.A., Gevers, T., Smeulders, A.W.M.: Selective search for object recognition. Int. J. Comput. Vis. 104, 154\u2013171 (2013)","journal-title":"Int. J. Comput. Vis."},{"key":"1426_CR11","doi-asserted-by":"publisher","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 580\u2013587 (2014). https:\/\/doi.org\/10.1109\/CVPR.2014.81","DOI":"10.1109\/CVPR.2014.81"},{"issue":"9","key":"1426_CR12","doi-asserted-by":"publisher","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","volume":"37","author":"K He","year":"2015","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 37(9), 1904\u20131916 (2015). https:\/\/doi.org\/10.1109\/TPAMI.2015.2389824","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1426_CR13","doi-asserted-by":"publisher","unstructured":"Girshick, R.: Fast R-CNN. In: IEEE International Conference on Computer Vision (ICCV), pp. 1440\u20131448 (2015). https:\/\/doi.org\/10.1109\/ICCV.2015.169","DOI":"10.1109\/ICCV.2015.169"},{"issue":"6","key":"1426_CR14","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(6), 1137\u20131149 (2017). https:\/\/doi.org\/10.1109\/TPAMI.2016.2577031","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1426_CR15","doi-asserted-by":"publisher","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 779\u2013788 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.91","DOI":"10.1109\/CVPR.2016.91"},{"key":"1426_CR16","doi-asserted-by":"publisher","unstructured":"Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6517\u20136525 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.690","DOI":"10.1109\/CVPR.2017.690"},{"key":"1426_CR17","unstructured":"Redmon, J., Farhadi, A.: YOLOv3: an incremental improvement. CoRR abs\/1804.02767 (2018) 1804.02767"},{"key":"1426_CR18","unstructured":"Bochkovskiy, A., Wang, C., Liao, H.M.: YOLOv4: Optimal speed and accuracy of object detection. CoRR abs\/2004.10934 (2020) 2004.10934"},{"key":"1426_CR19","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: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 936\u2013944 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.106","DOI":"10.1109\/CVPR.2017.106"},{"key":"1426_CR20","doi-asserted-by":"publisher","unstructured":"Wang, W., Xie, E., Song, X., Zang, Y., Wang, W., Lu, T., Yu, G., Shen, C.: Efficient and accurate arbitrary-shaped text detection with pixel aggregation network. In: IEEE International Conference on Computer Vision (ICCV), pp. 8439\u20138448 (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00853","DOI":"10.1109\/ICCV.2019.00853"},{"key":"1426_CR21","doi-asserted-by":"publisher","unstructured":"Jocher, G.: YOLOv5 by Ultralytics. https:\/\/doi.org\/10.5281\/zenodo.3908559 . https:\/\/github.com\/ultralytics\/yolov5","DOI":"10.5281\/zenodo.3908559"},{"key":"1426_CR22","unstructured":"Jocher, G., Chaurasia, A., Qiu, J.: YOLO by Ultralytics. https:\/\/github.com\/ultralytics\/ultralytics"},{"key":"1426_CR23","doi-asserted-by":"publisher","unstructured":"Ghodrati, A., Diba, A., Pedersoli, M., Tuytelaars, T., Van\u00a0Gool, L.: Deepproposal: Hunting objects by cascading deep convolutional layers. In: IEEE International Conference on Computer Vision (ICCV), pp. 2578\u20132586 (2015). https:\/\/doi.org\/10.1109\/ICCV.2015.296","DOI":"10.1109\/ICCV.2015.296"},{"key":"1426_CR24","doi-asserted-by":"publisher","unstructured":"Cai, Z., Vasconcelos, N.: Cascade r-cnn: Delving into high quality object detection. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6154\u20136162 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00644","DOI":"10.1109\/CVPR.2018.00644"},{"key":"1426_CR25","doi-asserted-by":"publisher","unstructured":"Zhang, S., Wen, L., Bian, X., Lei, Z., Li, S.Z.: Single-shot refinement neural network for object detection. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4203\u20134212 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00442","DOI":"10.1109\/CVPR.2018.00442"},{"key":"1426_CR26","unstructured":"Etten, A.V.: You Only Look Twice: Rapid multi-scale object detection in satellite imagery. CoRR abs\/1805.09512 (2018) 1805.09512"},{"key":"1426_CR27","doi-asserted-by":"publisher","unstructured":"Bell, S., Zitnick, C.L., Bala, K., Girshick, R.: Inside-Outside Net: Detecting objects in context with skip pooling and recurrent neural networks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2874\u20132883 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.314","DOI":"10.1109\/CVPR.2016.314"},{"issue":"7","key":"1426_CR28","doi-asserted-by":"publisher","first-page":"3423","DOI":"10.1109\/TIP.2019.2896952","volume":"28","author":"Y Yuan","year":"2019","unstructured":"Yuan, Y., Xiong, Z., Wang, Q.: VSSA-NET: vertical spatial sequence attention network for traffic sign detection. IEEE Trans. Image Process. 28(7), 3423\u20133434 (2019). https:\/\/doi.org\/10.1109\/TIP.2019.2896952","journal-title":"IEEE Trans. Image Process."},{"key":"1426_CR29","doi-asserted-by":"publisher","unstructured":"M\u00fcller, J., Dietmayer, K.: Detecting traffic lights by single shot detection. In: 21st International Conference on Intelligent Transportation Systems (ITSC), pp. 266\u2013273 (2018). https:\/\/doi.org\/10.1109\/ITSC.2018.8569683","DOI":"10.1109\/ITSC.2018.8569683"},{"issue":"21","key":"1426_CR30","doi-asserted-by":"publisher","first-page":"8221","DOI":"10.3390\/s22218221","volume":"22","author":"B Yan","year":"2022","unstructured":"Yan, B., Li, J., Yang, Z., Zhang, X., Hao, X.: AIE-YOLO: auxiliary information enhanced YOLO for small object detection. Sensors 22(21), 8221 (2022)","journal-title":"Sensors"},{"key":"1426_CR31","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2023.103752","volume":"90","author":"M Wang","year":"2023","unstructured":"Wang, M., Yang, W., Wang, L., Chen, D., Wei, F., KeZiErBieKe, H., Liao, Y.: FE-YOLOv5: Feature enhancement network based on YOLOv5 for small object detection. J. Vis. Commun. Image Represent. 90, 103752 (2023)","journal-title":"J. Vis. Commun. Image Represent."},{"key":"1426_CR32","doi-asserted-by":"publisher","unstructured":"Hu, J., Shen, L., Sun, G.: squeeze-and-excitation networks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7132\u20137141 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00745","DOI":"10.1109\/CVPR.2018.00745"},{"key":"1426_CR33","doi-asserted-by":"publisher","unstructured":"Wang, Q., Wu, B., Zhu, P., Li, P., Zuo, W., Hu, Q.: ECA-Net: Efficient channel attention for deep convolutional neural networks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11531\u201311539 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.01155","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"1426_CR34","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.-Y., Kweon, I.S.: CBAM: convolutional block attention module. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 3\u201319 (2018)","DOI":"10.1007\/978-3-030-01234-2_1"},{"issue":"4","key":"1426_CR35","doi-asserted-by":"publisher","first-page":"817","DOI":"10.3390\/electronics12040817","volume":"12","author":"R Yang","year":"2023","unstructured":"Yang, R., Li, W., Shang, X., Zhu, D., Man, X.: KPE-YOLOv5: an improved small target detection algorithm based on YOLOv5. Electronics 12(4), 817 (2023)","journal-title":"Electronics"},{"key":"1426_CR36","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-023-17628-4","author":"W Zhou","year":"2023","unstructured":"Zhou, W., Cai, C., Zheng, L., Li, C., Zeng, D.: ASSD-YOLO: a small object detection method based on improved YOLOv7 for airport surface surveillance. Multimed. Tools Appl. (2023). https:\/\/doi.org\/10.1007\/s11042-023-17628-4","journal-title":"Multimed. Tools Appl."},{"key":"1426_CR37","doi-asserted-by":"publisher","unstructured":"Lim, J.-S., Astrid, M., Yoon, H.-J., Lee, S.-I.: Small object detection using context and attention. In: International Conference on Artificial Intelligence in Information and Communication (ICAIIC), pp. 181\u2013186 (2021). https:\/\/doi.org\/10.1109\/ICAIIC51459.2021.9415217","DOI":"10.1109\/ICAIIC51459.2021.9415217"},{"key":"1426_CR38","unstructured":"Luo, W., Li, Y., Urtasun, R., Zemel, R.: Understanding the effective receptive field in deep convolutional neural networks. In: Neural Information Processing Systems (NeurIPS), vol. 29 (2016). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2016\/file\/c8067ad1937f728f51288b3eb986afaa-Paper.pdf"},{"key":"1426_CR39","doi-asserted-by":"publisher","unstructured":"Duan, K., Bai, S., Xie, L., Qi, H., Huang, Q., Tian, Q.: CenterNet: Keypoint triplets for object detection. In: IEEE International Conference on Computer Vision (ICCV), pp. 6568\u20136577 (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00667","DOI":"10.1109\/ICCV.2019.00667"},{"key":"1426_CR40","doi-asserted-by":"publisher","unstructured":"Xie, X., Cheng, G., Wang, J., Yao, X., Han, J.: Oriented R-CNN for object detection. In: IEEE International Conference on Computer Vision (ICCV), pp. 3500\u20133509 (2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.00350","DOI":"10.1109\/ICCV48922.2021.00350"},{"key":"1426_CR41","doi-asserted-by":"publisher","unstructured":"Lin, T.-Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: IEEE International Conference on Computer Vision (ICCV), pp. 2999\u20133007 (2017). https:\/\/doi.org\/10.1109\/ICCV.2017.324","DOI":"10.1109\/ICCV.2017.324"},{"key":"1426_CR42","doi-asserted-by":"crossref","unstructured":"Tan, M., Pang, R., Le, Q.V.: EfficientDet: Scalable and efficient object detection. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"1426_CR43","doi-asserted-by":"crossref","unstructured":"Wang, C.-Y., Bochkovskiy, A., Liao, H.-Y.M.: YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7464\u20137475 (2023)","DOI":"10.1109\/CVPR52729.2023.00721"}],"container-title":["Journal of Real-Time Image Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11554-024-01426-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11554-024-01426-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11554-024-01426-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,5]],"date-time":"2024-04-05T12:30:44Z","timestamp":1712320244000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11554-024-01426-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,1]]},"references-count":43,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2024,4]]}},"alternative-id":["1426"],"URL":"https:\/\/doi.org\/10.1007\/s11554-024-01426-8","relation":{},"ISSN":["1861-8200","1861-8219"],"issn-type":[{"value":"1861-8200","type":"print"},{"value":"1861-8219","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,1]]},"assertion":[{"value":"17 October 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 January 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 March 2024","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 that they have no conflicts of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"44"}}