{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T16:37:13Z","timestamp":1781714233540,"version":"3.54.5"},"publisher-location":"Singapore","reference-count":41,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819609628","type":"print"},{"value":"9789819609635","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,8]],"date-time":"2024-12-08T00:00:00Z","timestamp":1733616000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,8]],"date-time":"2024-12-08T00:00:00Z","timestamp":1733616000000},"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":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-981-96-0963-5_28","type":"book-chapter","created":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T07:47:49Z","timestamp":1733557669000},"page":"468-484","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["A Universal Structure of\u00a0YOLO Series Small Object Detection Models"],"prefix":"10.1007","author":[{"given":"Shengchao","family":"Hu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiao","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weijun","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianlun","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,12,8]]},"reference":[{"key":"28_CR1","unstructured":"Bochkovskiy, A., Wang, C.Y., Liao, H.Y.M.: Yolov4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934 (2020)"},{"key":"28_CR2","doi-asserted-by":"publisher","unstructured":"Cao, Y., He, Z., Wang, L., Wang, W., Yuan, Y., Zhang, D., Zhang, J., Zhu, P., Van\u00a0Gool, L., Han, J., Hoi, S., Hu, Q., Liu, M., Cheng, C., Liu, F., Cao, G., Li, G., Wang, H., He, J., Wan, J., Wan, Q., Zhao, Q., Lyu, S., Zhao, W., Lu, X., Zhu, X., Liu, Y., Lv, Y., Ma, Y., Yang, Y., Wang, Z., Xu, Z., Luo, Z., Zhang, Z., Zhang, Z., Li, Z., Zhang, Z.: Visdrone-det2021: The vision meets drone object detection challenge results. In: 2021 IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW). pp. 2847\u20132854 (2021). https:\/\/doi.org\/10.1109\/ICCVW54120.2021.00319","DOI":"10.1109\/ICCVW54120.2021.00319"},{"key":"28_CR3","unstructured":"Dai, J., Li, Y., He, K., Sun, J.: R-fcn: Object detection via region-based fully convolutional networks. Advances in neural information processing systems 29 (2016)"},{"key":"28_CR4","doi-asserted-by":"publisher","first-page":"1968","DOI":"10.1109\/TMM.2021.3074273","volume":"24","author":"C Deng","year":"2021","unstructured":"Deng, C., Wang, M., Liu, L., Liu, Y., Jiang, Y.: Extended feature pyramid network for small object detection. IEEE Trans. Multimedia 24, 1968\u20131979 (2021)","journal-title":"IEEE Trans. Multimedia"},{"key":"28_CR5","unstructured":"Deng, L., Yang, M., Li, T., He, Y., Wang, C.: Rfbnet: deep multimodal networks with residual fusion blocks for rgb-d semantic segmentation. arXiv preprint arXiv:1907.00135 (2019)"},{"key":"28_CR6","doi-asserted-by":"publisher","unstructured":"Everingham, M., Van\u00a0Gool, L., Williams, C., Winn, J., Zisserman, A.: The pascal visual object classes (voc) challenge. International Journal of Computer Vision 88, 303\u2013338 (06 2010). https:\/\/doi.org\/10.1007\/s11263-009-0275-4","DOI":"10.1007\/s11263-009-0275-4"},{"issue":"1","key":"28_CR7","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1016\/j.jvcir.2011.06.004","volume":"23","author":"C Fookes","year":"2012","unstructured":"Fookes, C., Lin, F., Chandran, V., Sridharan, S.: Evaluation of image resolution and super-resolution on face recognition performance. J. Vis. Commun. Image Represent. 23(1), 75\u201393 (2012)","journal-title":"J. Vis. Commun. Image Represent."},{"key":"28_CR8","unstructured":"Ge, Z., Liu, S., Wang, F., Li, Z., Sun, J.: Yolox: Exceeding yolo series in 2021. arXiv preprint arXiv:2107.08430 (2021)"},{"key":"28_CR9","doi-asserted-by":"crossref","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)","DOI":"10.1109\/CVPR.2014.81"},{"key":"28_CR10","doi-asserted-by":"crossref","unstructured":"Guo, J., Lou, H., Chen, H., Liu, H., Gu, J.J., Bi, L., Duan, X.: A new detection algorithm for alien intrusion on highway. Scientific Reports 13 (2023), https:\/\/api.semanticscholar.org\/CorpusID:259308664","DOI":"10.1038\/s41598-023-37686-w"},{"key":"28_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask r-cnn. In: Proceedings of the IEEE international conference on computer vision. pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"28_CR12","doi-asserted-by":"crossref","unstructured":"Hu, P., Ramanan, D.: Finding tiny faces. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 951\u2013959 (2017)","DOI":"10.1109\/CVPR.2017.166"},{"key":"28_CR13","doi-asserted-by":"publisher","unstructured":"Jocher, G.: YOLOv5 by Ultralytics (May 2020). https:\/\/doi.org\/10.5281\/zenodo.3908559, https:\/\/github.com\/ultralytics\/yolov5","DOI":"10.5281\/zenodo.3908559"},{"key":"28_CR14","unstructured":"Jocher, G., Chaurasia, A., Qiu, J.: Ultralytics YOLO (Jan 2023), https:\/\/github.com\/ultralytics\/ultralytics"},{"key":"28_CR15","doi-asserted-by":"publisher","first-page":"3765","DOI":"10.1109\/TMM.2023.3315558","volume":"26","author":"J Leng","year":"2024","unstructured":"Leng, J., Liu, Y., Gao, X., Wang, Z.: Crnet: Context-guided reasoning network for detecting hard objects. IEEE Trans. Multimedia 26, 3765\u20133777 (2024)","journal-title":"IEEE Trans. Multimedia"},{"issue":"3","key":"28_CR16","doi-asserted-by":"publisher","first-page":"1320","DOI":"10.1109\/TCSVT.2022.3210207","volume":"33","author":"J Leng","year":"2023","unstructured":"Leng, J., Mo, M., Zhou, Y., Gao, C., Li, W., Gao, X.: Pareto refocusing for drone-view object detection. IEEE Trans. Circuits Syst. Video Technol. 33(3), 1320\u20131334 (2023)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"28_CR17","doi-asserted-by":"crossref","unstructured":"Li, J., Liang, X., Wei, Y., Xu, T., Feng, J., Yan, S.: Perceptual generative adversarial networks for small object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 1222\u20131230 (2017)","DOI":"10.1109\/CVPR.2017.211"},{"key":"28_CR18","first-page":"1","volume":"71","author":"W Liang","year":"2022","unstructured":"Liang, W., Sun, Y.: Elcnn: A deep neural network for small object defect detection of magnetic tile. IEEE Trans. Instrum. Meas. 71, 1\u201310 (2022)","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"28_CR19","doi-asserted-by":"crossref","unstructured":"Lim, J.S., Astrid, M., Yoon, H.J., Lee, S.I.: Small object detection using context and attention. In: 2021 international Conference on Artificial intelligence in information and Communication (ICAIIC). pp. 181\u2013186. IEEE (2021)","DOI":"10.1109\/ICAIIC51459.2021.9415217"},{"key":"28_CR20","doi-asserted-by":"crossref","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)","DOI":"10.1109\/CVPR.2017.106"},{"key":"28_CR21","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: Proceedings of the IEEE international conference on computer vision. pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"28_CR22","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L.: Microsoft coco: Common objects in context. In: Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13. pp. 740\u2013755. Springer (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"28_CR23","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2021.104197","volume":"111","author":"G Liu","year":"2021","unstructured":"Liu, G., Han, J., Rong, W.: Feedback-driven loss function for small object detection. Image Vis. Comput. 111, 104197 (2021)","journal-title":"Image Vis. Comput."},{"key":"28_CR24","doi-asserted-by":"crossref","unstructured":"Liu, S., Qi, L., Qin, H., Shi, J., Jia, J.: Path aggregation network for instance segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 8759\u20138768 (2018)","DOI":"10.1109\/CVPR.2018.00913"},{"key":"28_CR25","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: Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11\u201314, 2016, Proceedings, Part I 14. pp. 21\u201337. Springer (2016)","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"28_CR26","doi-asserted-by":"crossref","unstructured":"Liu, Z., Gao, G., Sun, L., Fang, L.: Ipg-net: Image pyramid guidance network for small object detection. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). pp. 4422\u20134430 (2020)","DOI":"10.1109\/CVPRW50498.2020.00521"},{"key":"28_CR27","doi-asserted-by":"crossref","unstructured":"Lou, H., Duan, X., Guo, J., Liu, H., Gu, J., Bi, L., Chen, H.: Dc-yolov8: Small-size object detection algorithm based on camera sensor. Electronics 12(10) (2023)","DOI":"10.3390\/electronics12102323"},{"key":"28_CR28","unstructured":"Oktay, O., Schlemper, J., Folgoc, L.L., Lee, M., Heinrich, M., Misawa, K., Mori, K., McDonagh, S., Hammerla, N.Y., Kainz, B., et\u00a0al.: Attention u-net: Learning where to look for the pancreas. arXiv preprint arXiv:1804.03999 (2018)"},{"key":"28_CR29","doi-asserted-by":"crossref","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)","DOI":"10.1109\/CVPR.2016.91"},{"key":"28_CR30","doi-asserted-by":"crossref","unstructured":"Redmon, J., Farhadi, A.: Yolo9000: better, faster, stronger. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 7263\u20137271 (2017)","DOI":"10.1109\/CVPR.2017.690"},{"key":"28_CR31","unstructured":"Redmon, J., Farhadi, A.: Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767 (2018)"},{"key":"28_CR32","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems 28 (2015)"},{"key":"28_CR33","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I.: Attention is all you need. Advances in neural information processing systems 30 (2017)"},{"key":"28_CR34","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: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 7464\u20137475 (2023)","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"28_CR35","doi-asserted-by":"publisher","unstructured":"Wang, J., Yang, W., Guo, H., Zhang, R., Xia, G.S.: Tiny object detection in aerial images. In: 2020 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":"28_CR36","doi-asserted-by":"crossref","unstructured":"Wang, J., Liu, W., Zhang, W., Liu, B.: Lv-yolov5: A light-weight object detector of vit on drone-captured scenarios. In: 2022 16th IEEE International Conference on Signal Processing (ICSP). vol.\u00a01, pp. 178\u2013183 (2022)","DOI":"10.1109\/ICSP56322.2022.9965217"},{"issue":"6","key":"28_CR37","doi-asserted-by":"publisher","first-page":"3329","DOI":"10.1007\/s00530-023-01182-y","volume":"29","author":"X Wang","year":"2023","unstructured":"Wang, X., He, N., Hong, C., Sun, F., Han, W., Wang, Q.: Yolo-erf: lightweight object detector for uav aerial images. Multimedia Syst. 29(6), 3329\u20133339 (2023)","journal-title":"Multimedia Syst."},{"issue":"11","key":"28_CR38","doi-asserted-by":"publisher","first-page":"11139","DOI":"10.1109\/JSEN.2022.3219199","volume":"23","author":"Y Yang","year":"2023","unstructured":"Yang, Y., Gao, X., Wang, Y., Song, S.: Vamyolox: An accurate and efficient object detection algorithm based on visual attention mechanism for uav optical sensors. IEEE Sens. J. 23(11), 11139\u201311155 (2023)","journal-title":"IEEE Sens. J."},{"key":"28_CR39","doi-asserted-by":"crossref","unstructured":"Yu, X., Gong, Y., Jiang, N., Ye, Q., Han, Z.: Scale match for tiny person detection. In: Proceedings of the IEEE\/CVF winter conference on applications of computer vision. pp. 1257\u20131265 (2020)","DOI":"10.1109\/WACV45572.2020.9093394"},{"key":"28_CR40","first-page":"1","volume":"71","author":"N Zeng","year":"2022","unstructured":"Zeng, N., Wu, P., Wang, Z., Li, H., Liu, W., Liu, X.: A small-sized object detection oriented multi-scale feature fusion approach with application to defect detection. IEEE Trans. Instrum. Meas. 71, 1\u201314 (2022)","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"28_CR41","doi-asserted-by":"crossref","unstructured":"Zhang, H., Wang, Y., Dayoub, F., Sunderhauf, N.: Varifocalnet: An iou-aware dense object detector. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 8514\u20138523 (2021)","DOI":"10.1109\/CVPR46437.2021.00841"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-0963-5_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T08:42:50Z","timestamp":1733560970000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-0963-5_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,8]]},"ISBN":["9789819609628","9789819609635"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-0963-5_28","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,8]]},"assertion":[{"value":"8 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hanoi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}