{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T15:14:06Z","timestamp":1778858046436,"version":"3.51.4"},"publisher-location":"Singapore","reference-count":33,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819620531","type":"print"},{"value":"9789819620548","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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\/978-981-96-2054-8_6","type":"book-chapter","created":{"date-parts":[[2025,1,2]],"date-time":"2025-01-02T15:46:01Z","timestamp":1735832761000},"page":"72-85","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["AMFT-YOLO: A Adaptive Multi-scale YOLO Algorithm with\u00a0Multi-level Feature Fusion for\u00a0Object Detection in\u00a0UAV Scenes"],"prefix":"10.1007","author":[{"given":"Tiebiao","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenchao","family":"Cui","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoyang","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,1,3]]},"reference":[{"key":"6_CR1","doi-asserted-by":"crossref","unstructured":"Cai, Z., Vasconcelos, N.: Cascade r-cnn: Delving into high quality object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 6154\u20136162 (2018)","DOI":"10.1109\/CVPR.2018.00644"},{"key":"6_CR2","doi-asserted-by":"publisher","first-page":"1556","DOI":"10.1109\/TIP.2020.3045636","volume":"30","author":"S Deng","year":"2020","unstructured":"Deng, S., Li, S., Xie, K., Song, W., Liao, X., Hao, A., Qin, H.: A global-local self-adaptive network for drone-view object detection. IEEE Trans. Image Process. 30, 1556\u20131569 (2020)","journal-title":"IEEE Trans. Image Process."},{"key":"6_CR3","doi-asserted-by":"crossref","unstructured":"Duan, C., Wei, Z., Zhang, C., Qu, S., Wang, H.: Coarse-grained density map guided object detection in aerial images. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 2789\u20132798 (2021)","DOI":"10.1109\/ICCVW54120.2021.00313"},{"key":"6_CR4","doi-asserted-by":"crossref","unstructured":"Fang, K., Li, W.J.: Dmnet: difference minimization network for semi-supervised segmentation in medical images. In: International Conference on Medical Image Computing and Computer-Assisted Intervention. pp. 532\u2013541. Springer (2020)","DOI":"10.1007\/978-3-030-59710-8_52"},{"key":"6_CR5","doi-asserted-by":"crossref","unstructured":"Fu, Y., Zhang, X., Wang, M.: Dshnet: A semantic segmentation model of remote sensing images based on dual stream hybrid network. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing (2024)","DOI":"10.1109\/JSTARS.2024.3355943"},{"key":"6_CR6","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast r-cnn. In: Proceedings of the IEEE international conference on computer vision. pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"6_CR7","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"},{"issue":"19","key":"6_CR8","doi-asserted-by":"publisher","first-page":"4801","DOI":"10.3390\/rs14194801","volume":"14","author":"Y Guo","year":"2022","unstructured":"Guo, Y., Chen, S., Zhan, R., Wang, W., Zhang, J.: Lmsd-yolo: A lightweight yolo algorithm for multi-scale sar ship detection. Remote Sensing 14(19), 4801 (2022)","journal-title":"Remote Sensing"},{"issue":"9","key":"6_CR9","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)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"6_CR10","doi-asserted-by":"crossref","unstructured":"Hou, Q., Ni, J., Hu, X.: Aerial image object detection method based on improved yolov5. In: International Conference on Mechatronic Engineering and Artificial Intelligence (MEAI 2023). vol. 13071, pp. 591\u2013596. SPIE (2024)","DOI":"10.1117\/12.3025652"},{"key":"6_CR11","doi-asserted-by":"crossref","unstructured":"Huang, Y., Chen, J., Huang, D.: Ufpmp-det: Toward accurate and efficient object detection on drone imagery. In: Proceedings of the AAAI Conference on Artificial Intelligence. pp. 1026\u20131033 (2022)","DOI":"10.1609\/aaai.v36i1.19986"},{"key":"6_CR12","doi-asserted-by":"crossref","unstructured":"Law, H., Deng, J.: Cornernet: Detecting objects as paired keypoints. In: Proceedings of the European conference on computer vision (ECCV). pp. 734\u2013750 (2018)","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"6_CR13","unstructured":"Li, H., Xiong, P., An, J., Wang, L.: Pyramid attention network for semantic segmentation. arXiv preprint arXiv:1805.10180 (2018)"},{"key":"6_CR14","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2022.104426","volume":"81","author":"J Li","year":"2023","unstructured":"Li, J., Gao, G., Yang, L., Liu, Y.: Gdf-net: A multi-task symmetrical network for retinal vessel segmentation. Biomed. Signal Process. Control 81, 104426 (2023)","journal-title":"Biomed. Signal Process. Control"},{"key":"6_CR15","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":"6_CR16","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":"6_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","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: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"6_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-3-319-46448-0_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"W Liu","year":"2016","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., Berg, A.C.: SSD: Single Shot MultiBox Detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21\u201337. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2"},{"key":"6_CR19","doi-asserted-by":"publisher","first-page":"145740","DOI":"10.1109\/ACCESS.2020.3014910","volume":"8","author":"Y Liu","year":"2020","unstructured":"Liu, Y., Yang, F., Hu, P.: Small-object detection in uav-captured images via multi-branch parallel feature pyramid networks. IEEE access 8, 145740\u2013145750 (2020)","journal-title":"IEEE access"},{"key":"6_CR20","doi-asserted-by":"crossref","unstructured":"Osco, L.P., et al.: A review on deep learning in UAV remote sensing. International J. Appl. Earth Observ. Geoinf. 102, 102456 (2021)","DOI":"10.1016\/j.jag.2021.102456"},{"issue":"2","key":"6_CR21","doi-asserted-by":"publisher","first-page":"420","DOI":"10.3390\/rs14020420","volume":"14","author":"G Qi","year":"2022","unstructured":"Qi, G., Zhang, Y., Wang, K., Mazur, N., Liu, Y., Malaviya, D.: Small object detection method based on adaptive spatial parallel convolution and fast multi-scale fusion. Remote Sens. 14(2), 420 (2022)","journal-title":"Remote Sens."},{"key":"6_CR22","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"},{"issue":"6","key":"6_CR23","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."},{"issue":"21","key":"6_CR24","doi-asserted-by":"publisher","first-page":"4209","DOI":"10.3390\/rs13214209","volume":"13","author":"Z Sun","year":"2021","unstructured":"Sun, Z., Leng, X., Lei, Y., Xiong, B., Ji, K., Kuang, G.: BIFA-YOLO: a novel yolo-based method for arbitrary-oriented ship detection in high-resolution SAR images. Remote Sens. 13(21), 4209 (2021)","journal-title":"Remote Sens."},{"key":"6_CR25","doi-asserted-by":"crossref","unstructured":"Vicente, S., Carreira, J., Agapito, L., Batista, J.: Reconstructing pascal voc. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 41\u201348 (2014)","DOI":"10.1109\/CVPR.2014.13"},{"key":"6_CR26","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":"6_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"403","DOI":"10.1007\/978-3-030-58548-8_24","volume-title":"Computer Vision \u2013 ECCV 2020","author":"J Wang","year":"2020","unstructured":"Wang, J., et al.: Side-aware boundary localization for more precise object detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12349, pp. 403\u2013419. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58548-8_24"},{"key":"6_CR28","unstructured":"Wang, J., Xu, C., Yang, W., Yu, L.: A normalized gaussian wasserstein distance for tiny object detection. arXiv preprint arXiv:2110.13389 (2021)"},{"key":"6_CR29","doi-asserted-by":"crossref","unstructured":"Yang, F., Fan, H., Chu, P., Blasch, E., Ling, H.: Clustered object detection in aerial images. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8311\u20138320 (2019)","DOI":"10.1109\/ICCV.2019.00840"},{"key":"6_CR30","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1016\/j.isprsjprs.2021.08.002","volume":"180","author":"R Zhang","year":"2021","unstructured":"Zhang, R., Newsam, S., Shao, Z., Huang, X., Wang, J., Li, D.: Multi-scale adversarial network for vehicle detection in UAV imagery. ISPRS J. Photogramm. Remote. Sens. 180, 283\u2013295 (2021)","journal-title":"ISPRS J. Photogramm. Remote. Sens."},{"issue":"19","key":"6_CR31","doi-asserted-by":"publisher","first-page":"3140","DOI":"10.3390\/rs12193140","volume":"12","author":"R Zhang","year":"2020","unstructured":"Zhang, R., Shao, Z., Huang, X., Wang, J., Li, D.: Object detection in UAV images via global density fused convolutional network. Remote Sens. 12(19), 3140 (2020)","journal-title":"Remote Sens."},{"key":"6_CR32","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2881\u20132890 (2017)","DOI":"10.1109\/CVPR.2017.660"},{"issue":"6","key":"6_CR33","doi-asserted-by":"publisher","first-page":"1687","DOI":"10.3390\/rs15061687","volume":"15","author":"Q Zhao","year":"2023","unstructured":"Zhao, Q., Liu, B., Lyu, S., Wang, C., Zhang, H.: Tph-yolov5++: Boosting object detection on drone-captured scenarios with cross-layer asymmetric transformer. Remote Sens. 15(6), 1687 (2023)","journal-title":"Remote Sens."}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-2054-8_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,23]],"date-time":"2025-03-23T01:42:17Z","timestamp":1742694137000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-2054-8_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819620531","9789819620548"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-2054-8_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"3 January 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Nara","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 January 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 January 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/mmm2025.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}