{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T13:19:06Z","timestamp":1775135946433,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":33,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819584161","type":"print"},{"value":"9789819584178","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-981-95-8417-8_42","type":"book-chapter","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T12:30:03Z","timestamp":1775133003000},"page":"583-595","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DF-DETR: An Algorithm for\u00a0Small Object Detection in\u00a0UAV Aerial Images"],"prefix":"10.1007","author":[{"given":"Liangyao","family":"Bu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hui","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,4,3]]},"reference":[{"issue":"1","key":"42_CR1","doi-asserted-by":"publisher","first-page":"134","DOI":"10.3390\/s24010134","volume":"24","author":"J Zhou","year":"2023","unstructured":"Zhou, J., Su, T., Li, K., et al.: Small Target-YOLOv5: enhancing the algorithm for small object detection in drone aerial imagery based on YOLOv5. Sensors 24(1), 134 (2023)","journal-title":"Sensors"},{"issue":"16","key":"42_CR2","doi-asserted-by":"publisher","first-page":"3277","DOI":"10.3390\/electronics13163277","volume":"13","author":"J Qin","year":"2024","unstructured":"Qin, J., Wang, H., Liu, Y., et al.: A UAV aerial image target detection algorithm based on YOLOv7 improved model. Electronics 13(16), 3277 (2024)","journal-title":"Electronics"},{"issue":"1","key":"42_CR3","doi-asserted-by":"publisher","first-page":"149","DOI":"10.3390\/rs16010149","volume":"16","author":"G Tang","year":"2023","unstructured":"Tang, G., Li, Y., Zhang, M., et al.: A survey of object detection for UAVs based on deep learning. Remote Sens. 16(1), 149 (2023)","journal-title":"Remote Sens."},{"issue":"11","key":"42_CR4","first-page":"13467","volume":"45","author":"G Cheng","year":"2023","unstructured":"Cheng, G., Han, J., Zhou, P., et al.: Towards large-scale small object detection: survey and benchmarks. IEEE Trans. Pattern Anal. Mach. Intell. 45(11), 13467\u201313488 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"42_CR5","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 (CVPR), pp. 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"42_CR6","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems 30, pp. 5998\u20136008 (2017)"},{"key":"42_CR7","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., et al.: End-to-end object detection with transformers. In: European Conference on Computer Vision (ECCV) 2020. Lecture Notes in Computer Science, vol. 12346, pp. 213\u2013229. Springer, Cham (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"42_CR8","doi-asserted-by":"crossref","unstructured":"Zhao, Y., et al.: DETRs beat YOLOs on real-time object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 16965\u201316974 (2024)","DOI":"10.1109\/CVPR52733.2024.01605"},{"key":"42_CR9","doi-asserted-by":"crossref","unstructured":"Wang, C.-Y., Liao, H.-Y.M., Wu, Y.-H., et al.: CSPNet: a new backbone that can enhance learning capability of CNN. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 390\u2013391 (2020)","DOI":"10.1109\/CVPRW50498.2020.00203"},{"issue":"2","key":"42_CR10","doi-asserted-by":"publisher","first-page":"896","DOI":"10.1109\/TPAMI.2023.3329173","volume":"46","author":"W Yu","year":"2023","unstructured":"Yu, W., Xie, E., Fan, H., et al.: Metaformer baselines for vision. IEEE Trans. Pattern Anal. Mach. Intell. 46(2), 896\u2013912 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"42_CR11","doi-asserted-by":"crossref","unstructured":"Yu, W., Zhou, P., Yan, S., et al.: InceptionNeXt: when inception meets ConvNeXt. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5672\u20135683 (2024)","DOI":"10.1109\/CVPR52733.2024.00542"},{"key":"42_CR12","doi-asserted-by":"crossref","unstructured":"Li, W., Guo, H., Liu, X., et al.: Efficient face super-resolution via wavelet-based feature enhancement network. In: Proceedings of the 32nd ACM International Conference on Multimedia (ACM MM), pp. 4515\u20134523 (2024)","DOI":"10.1145\/3664647.3681088"},{"key":"42_CR13","doi-asserted-by":"crossref","unstructured":"Tang, F., Xu, Z., Huang, Q., et al.: DuAT: dual-aggregation transformer network for medical image segmentation. In: Chinese Conference on Pattern Recognition and Computer Vision (PRCV), pp. 343\u2013356. Springer, Singapore (2023)","DOI":"10.1007\/978-981-99-8469-5_27"},{"key":"42_CR14","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Doll\u00e1r, P., Girshick, R., et al.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"42_CR15","doi-asserted-by":"crossref","unstructured":"Liu, S., Qi, L., Qin, H., et al.: Path aggregation network for instance segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8759\u20138768 (2018)","DOI":"10.1109\/CVPR.2018.00913"},{"key":"42_CR16","doi-asserted-by":"crossref","unstructured":"Tan, M., Pang, R., Le, Q.V.: EfficientDet: scalable and efficient object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10781\u201310790 (2020)","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"42_CR17","doi-asserted-by":"crossref","unstructured":"Ghiasi, G., Lin, T.-Y., Le, Q. V.: NAS-FPN: learning scalable feature pyramid architecture for object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7036\u20137045 (2019)","DOI":"10.1109\/CVPR.2019.00720"},{"key":"42_CR18","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"42_CR19","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"42_CR20","unstructured":"Zhu, X., Su, W., Lu, L., et al.: Deformable DETR: deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159 (2020)"},{"key":"42_CR21","unstructured":"Zhang, H., Li, F., Liu, S., et al.: DINO: DETR with improved denoising anchor boxes for end-to-end object detection. arXiv preprint arXiv:2203.03605 (2022)"},{"key":"42_CR22","unstructured":"Choromanski, K., Likhosherstov, V., Dohan, D., et al.: Rethinking attention with performers. arXiv preprint arXiv:2009.14794 (2020)"},{"key":"42_CR23","doi-asserted-by":"crossref","unstructured":"Dao, T., Fu, D., Ermon, S., et al.: FlashAttention: fast and memory-efficient exact attention with IO-awareness. In: Advances in Neural Information Processing Systems (NeurIPS) 35, pp. 16344\u201316359 (2022)","DOI":"10.52202\/068431-1189"},{"key":"42_CR24","doi-asserted-by":"crossref","unstructured":"Shi, D.: TransNeXt: robust foveal visual perception for vision transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 17773\u201317783 (2024)","DOI":"10.1109\/CVPR52733.2024.01683"},{"issue":"3","key":"42_CR25","doi-asserted-by":"publisher","first-page":"75","DOI":"10.55524\/ijircst.2024.12.3.12","volume":"12","author":"SK Jaiswal","year":"2024","unstructured":"Jaiswal, S.K., Agrawal, R.: A comprehensive review of YOLOv5: advances in real-time object detection. Int. J. Innov. Res. Comput. Sci. Technol. 12(3), 75\u201380 (2024)","journal-title":"Int. J. Innov. Res. Comput. Sci. Technol."},{"key":"42_CR26","unstructured":"Li, C., Li, L., Jiang, H., et al.: YOLOv6: a single-stage object detection framework for industrial applications. arXiv preprint arXiv:2209.02976 (2022)"},{"issue":"4","key":"42_CR27","doi-asserted-by":"publisher","first-page":"1680","DOI":"10.3390\/make5040083","volume":"5","author":"J Terven","year":"2023","unstructured":"Terven, J., C\u00f3rdova-Esparza, D.M., Romero-Gonz\u00e1lez, J.A.: A comprehensive review of YOLO architectures in computer vision: from YOLOv1 to YOLOv8 and YOLO-NAS. Mach. Learn. Knowl. Extr. 5(4), 1680\u20131716 (2023)","journal-title":"Mach. Learn. Knowl. Extr."},{"key":"42_CR28","doi-asserted-by":"crossref","unstructured":"Sapkota, R., Qureshi, R., Flores-Calero, M., et al.: YOLOv10 to its genesis: a decadal and comprehensive review of the you only look once series. arXiv preprint (2024)","DOI":"10.36227\/techrxiv.171995313.38075268\/v1"},{"key":"42_CR29","first-page":"107984","volume":"37","author":"A Wang","year":"2024","unstructured":"Wang, A., Chen, H., Liu, L., et al.: YOLOv10: real-time end-to-end object detection. Adv. Neural. Inf. Process. Syst. 37, 107984\u2013108011 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"42_CR30","unstructured":"Khanam, R., Hussain, M.: YOLOv11: an overview of the key architectural enhancements. arXiv preprint arXiv:2410.17725 (2024)"},{"key":"42_CR31","unstructured":"Hidayatullah, P., Syakrani, N., Sholahuddin, M.R., et al.: YOLOv8 to YOLO11: a comprehensive architecture in-depth comparative review. arXiv preprint arXiv:2501.13400 (2025)"},{"key":"42_CR32","unstructured":"Alif, M.A.R., Hussain, M.: YOLOv12: a breakdown of the key architectural features. arXiv preprint arXiv:2502.14740 (2025)"},{"key":"42_CR33","unstructured":"Lv, W., et al.: Rt-detrv2: improved baseline with bag-of-freebies for real-time detection transformer, arXiv preprint arXiv:2407.17140 (2024)"}],"container-title":["Lecture Notes in Computer Science","Algorithms and Architectures for Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-8417-8_42","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T12:30:09Z","timestamp":1775133009000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-8417-8_42"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819584161","9789819584178"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-8417-8_42","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"3 April 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICA3PP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Algorithms and Architectures for Parallel Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Zhengzhou","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"30 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ica3pp2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ieee-cybermatics.org\/2025\/ica3pp\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}