{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T08:58:12Z","timestamp":1785488292532,"version":"3.56.0"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,12,17]],"date-time":"2025-12-17T00:00:00Z","timestamp":1765929600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,17]]},"DOI":"10.1145\/3774521.3774563","type":"proceedings-article","created":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T07:34:24Z","timestamp":1785483264000},"page":"1-10","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Rethinking Detection Heads: Enhancing YOLO for Drone Image Object Detection"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-1909-0629","authenticated-orcid":false,"given":"Rutvik","family":"Patel","sequence":"first","affiliation":[{"name":"Indian Institute of Technology Delhi, Delhi, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8123-4359","authenticated-orcid":false,"given":"Anureet","family":"Chhabra","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology Delhi, Delhi, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1068-9406","authenticated-orcid":false,"given":"Ankita","family":"Raj","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology Delhi, Delhi, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0155-0250","authenticated-orcid":false,"given":"Chetan","family":"Arora","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology Delhi, Delhi, India"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,31]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"crossref","unstructured":"Nicolas Audebert Bertrand Le\u00a0Saux and S\u00e9bastien Lef\u00e8vre. 2018. Beyond RGB: Very high resolution urban remote sensing with multimodal deep networks. ISPRS journal of photogrammetry and remote sensing 140 (2018) 20\u201332.","DOI":"10.1016\/j.isprsjprs.2017.11.011"},{"key":"e_1_3_3_1_3_2","unstructured":"Alexey Bochkovskiy Chien-Yao Wang and Hong-Yuan\u00a0Mark Liao. 2020. Yolov4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2004.10934 (2020)."},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"crossref","unstructured":"Dario Cazzato Claudio Cimarelli Jose\u00a0Luis Sanchez-Lopez Holger Voos and Marco Leo. 2020. A survey of computer vision methods for 2d object detection from unmanned aerial vehicles. Journal of Imaging 6 8 (2020) 78.","DOI":"10.3390\/jimaging6080078"},{"key":"e_1_3_3_1_7_2","unstructured":"Qiang Chen Jian Wang Chuchu Han Shan Zhang Zexian Li Xiaokang Chen Jiahui Chen Xiaodi Wang Shuming Han Gang Zhang et\u00a0al. 2022. Group detr v2: Strong object detector with encoder-decoder pretraining. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2211.03594 (2022)."},{"key":"e_1_3_3_1_8_2","unstructured":"Bowei Du Yecheng Huang Jiaxin Chen and Di Huang. [n. d.]. Adaptive Sparse Convolutional Networks with Global Context Enhancement for Faster Object Detection on Drone Images Supplementary Material. ([n. d.])."},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00294"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"crossref","unstructured":"Jennifer\u00a0N Hird Alessandro Montaghi Gregory\u00a0J McDermid Jahan Kariyeva Brian\u00a0J Moorman Scott\u00a0E Nielsen and Anne\u00a0CS McIntosh. 2017. Use of unmanned aerial vehicles for monitoring recovery of forest vegetation on petroleum well sites. Remote Sensing 9 5 (2017) 413.","DOI":"10.3390\/rs9050413"},{"key":"e_1_3_3_1_11_2","first-page":"1026","volume-title":"Proceedings of the AAAI conference on artificial intelligence","volume":"36","author":"Huang Yecheng","year":"2022","unstructured":"Yecheng Huang, Jiaxin Chen, and Di Huang. 2022. UFPMP-Det: Toward accurate and efficient object detection on drone imagery. In Proceedings of the AAAI conference on artificial intelligence , Vol.\u00a036. 1026\u20131033."},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73116-7_17"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.3908559"},{"key":"e_1_3_3_1_14_2","volume-title":"Ultralytics YOLO11","author":"Jocher Glenn","year":"2024","unstructured":"Glenn Jocher and Jing Qiu. 2024. Ultralytics YOLO11. https:\/\/github.com\/ultralytics\/ultralytics"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS.2017.8127090"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00103"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i17.34026"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"crossref","unstructured":"Chenguang Liu Guangshuai Gao Ziyue Huang Zhenghui Hu Qingjie Liu and Yunhong Wang. 2024. YOLC: You Only Look Clusters for Tiny Object Detection in Aerial Images. IEEE Transactions on Intelligent Transportation Systems 25 10 (2024) 13863\u201313875.","DOI":"10.1109\/TITS.2024.3386928"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"crossref","unstructured":"Hou-I Liu Yu-Wen Tseng Kai-Cheng Chang Pin-Jyun Wang Hong-Han Shuai and Wen-Huang Cheng. 2024. A denoising fpn with transformer r-cnn for tiny object detection. IEEE Transactions on Geoscience and Remote Sensing (2024).","DOI":"10.1109\/TGRS.2024.3396489"},{"key":"e_1_3_3_1_22_2","unstructured":"Shilong Liu Feng Li Hao Zhang Xiao Yang Xianbiao Qi Hang Su Jun Zhu and Lei Zhang. 2022. Dab-detr: Dynamic anchor boxes are better queries for detr. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2201.12329 (2022)."},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"crossref","unstructured":"You Ma Lin Chai and Lizuo Jin. 2023. Scale decoupled pyramid for object detection in aerial images. IEEE Transactions on Geoscience and Remote Sensing 61 (2023) 1\u201314.","DOI":"10.1109\/TGRS.2023.3298852"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00198"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00363"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"e_1_3_3_1_28_2","unstructured":"Shaoqing Ren Kaiming He Ross Girshick and Jian Sun. 2015. Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems 28 (2015)."},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"publisher","unstructured":"Yiming Sun Bing Cao Pengfei Zhu and Qinghua Hu. 2022. Drone-based RGB-Infrared Cross-Modality Vehicle Detection via Uncertainty-Aware Learning. IEEE Transactions on Circuits and Systems for Video Technology (2022) 1\u20131. 10.1109\/TCSVT.2022.3168279","DOI":"10.1109\/TCSVT.2022.3168279"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/ADICS58448.2024.10533619"},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"crossref","unstructured":"Ao Wang Hui Chen Lihao Liu Kai Chen Zijia Lin Jungong Han et\u00a0al. 2024. Yolov10: Real-time end-to-end object detection. Advances in Neural Information Processing Systems 37 (2024) 107984\u2013108011.","DOI":"10.52202\/079017-3429"},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"crossref","unstructured":"Jinwang Wang Wen Yang Haowen Guo Ruixiang Zhang and Gui-Song Xia. 2021. Tiny Object Detection in Aerial Images. 3791\u20133798.","DOI":"10.1109\/ICPR48806.2021.9413340"},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00418"},{"key":"e_1_3_3_1_34_2","unstructured":"Hongyi Zhang Moustapha Cisse Yann\u00a0N Dauphin and David Lopez-Paz. 2017. mixup: Beyond empirical risk minimization. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1710.09412 (2017)."},{"key":"e_1_3_3_1_35_2","unstructured":"Hao Zhang Feng Li Shilong Liu Lei Zhang Hang Su Jun Zhu Lionel\u00a0M. Ni and Heung-Yeung Shum. 2022. DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection. arxiv:https:\/\/arXiv.org\/abs\/2203.03605\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2203.03605"},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"publisher","unstructured":"Qi Zhao Binghao Liu Shuchang Lyu Chunlei Wang and Hong Zhang. 2023. TPH-YOLOv5++: Boosting Object Detection on Drone-Captured Scenarios with Cross-Layer Asymmetric Transformer. Remote Sensing 15 6 (2023). 10.3390\/rs15061687","DOI":"10.3390\/rs15061687"},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"crossref","unstructured":"Pengfei Zhu Longyin Wen Dawei Du Xiao Bian Heng Fan Qinghua Hu and Haibin Ling. 2021. Detection and tracking meet drones challenge. IEEE Transactions on Pattern Analysis and Machine Intelligence 44 11 (2021) 7380\u20137399.","DOI":"10.1109\/TPAMI.2021.3119563"},{"key":"e_1_3_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00312"},{"key":"e_1_3_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00312"},{"key":"e_1_3_3_1_40_2","unstructured":"Xizhou Zhu Weijie Su Lewei Lu Bin Li Xiaogang Wang and Jifeng Dai. 2020. Deformable detr: Deformable transformers for end-to-end object detection. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2010.04159 (2020)."},{"key":"e_1_3_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00621"}],"event":{"name":"ICVGIP 2025: Indian Conference on Computer Vision, Graphics, and Image Processing","location":"Mandi Himachal Pradesh India","acronym":"ICVGIP 2025"},"container-title":["Proceedings of the Sixteen Indian Conference on Computer Vision, Graphics and Image Processing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3774521.3774563","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T08:08:07Z","timestamp":1785485287000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3774521.3774563"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,17]]},"references-count":40,"alternative-id":["10.1145\/3774521.3774563","10.1145\/3774521"],"URL":"https:\/\/doi.org\/10.1145\/3774521.3774563","relation":{},"subject":[],"published":{"date-parts":[[2025,12,17]]},"assertion":[{"value":"2026-07-31","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}