{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:20:54Z","timestamp":1765308054229,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":69,"publisher":"ACM","funder":[{"name":"Guangdong Basic and Applied Basic Research Foundation under Grant","award":["2025A1515011485"],"award-info":[{"award-number":["2025A1515011485"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62027804"],"award-info":[{"award-number":["62027804"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Major Key Project of Pengcheng Laboratory","award":["PCL2025A02"],"award-info":[{"award-number":["PCL2025A02"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755486","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T05:47:42Z","timestamp":1761371262000},"page":"518-527","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["ESOD: Event-Based Small Object Detection"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9935-5167","authenticated-orcid":false,"given":"Quanmin","family":"Liang","sequence":"first","affiliation":[{"name":"Sun Yat-Sen University, Guangzhou, China and Pengcheng Laboratory, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6367-8067","authenticated-orcid":false,"given":"Jinyi","family":"Lu","sequence":"additional","affiliation":[{"name":"Sun Yat-Sen University, Guangzhou, China and Pengcheng Laboratory, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2563-6577","authenticated-orcid":false,"given":"Qiang","family":"Li","sequence":"additional","affiliation":[{"name":"Xpeng Motors Technology Co Ltd, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5002-4754","authenticated-orcid":false,"given":"Shuai","family":"Liu","sequence":"additional","affiliation":[{"name":"Sun Yat-Sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3871-1324","authenticated-orcid":false,"given":"Zhihao","family":"Zhao","sequence":"additional","affiliation":[{"name":"Technical University of Munich, Munich, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4556-4261","authenticated-orcid":false,"given":"Yinzheng","family":"Zhao","sequence":"additional","affiliation":[{"name":"Technical University of Munich, Munich, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2358-0779","authenticated-orcid":false,"given":"Wei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Pengcheng Laboratory, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0359-7810","authenticated-orcid":false,"given":"Kai","family":"Huang","sequence":"additional","affiliation":[{"name":"Sun Yat-Sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2978-5935","authenticated-orcid":false,"given":"Yonghong","family":"Tian","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China and Pengcheng Laboratory, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00699"},{"key":"e_1_3_2_2_2_1","volume-title":"Yolov4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934","author":"Bochkovskiy Alexey","year":"2020","unstructured":"Alexey Bochkovskiy, Chien-Yao Wang, and Hong-Yuan Mark Liao. 2020. Yolov4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934 (2020)."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2014.2342715"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_22"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"e_1_3_2_2_6_1","volume-title":"Asian conference on computer vision. Springer, 214-230","author":"Chen Chenyi","year":"2016","unstructured":"Chenyi Chen, Ming-Yu Liu, Oncel Tuzel, and Jianxiong Xiao. 2016. R-CNN for small object detection. In Asian conference on computer vision. Springer, 214-230."},{"key":"e_1_3_2_2_7_1","volume-title":"Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs","author":"Chen Liang-Chieh","year":"2017","unstructured":"Liang-Chieh Chen, George Papandreou, Iasonas Kokkinos, Kevin Murphy, and Alan L Yuille. 2017. Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE transactions on pattern analysis and machine intelligence, Vol. 40, 4 (2017), 834-848."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3290594"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00298"},{"key":"e_1_3_2_2_10_1","volume-title":"A large scale event-based detection dataset for automotive. arXiv preprint arXiv:2001.08499","author":"Tournemire Pierre De","year":"2020","unstructured":"Pierre De Tournemire, Davide Nitti, Etienne Perot, Davide Migliore, and Amos Sironi. 2020. A large scale event-based detection dataset for automotive. arXiv preprint arXiv:2001.08499 (2020)."},{"key":"e_1_3_2_2_11_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.316"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01291"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aaz9712"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01627"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS39084.2020.9323690"},{"key":"e_1_3_2_2_17_1","volume-title":"Dssd: Deconvolutional single shot detector. arXiv preprint arXiv:1701.06659","author":"Fu Cheng-Yang","year":"2017","unstructured":"Cheng-Yang Fu, Wei Liu, Ananth Ranga, Ambrish Tyagi, and Alexander C Berg. 2017. Dssd: Deconvolutional single shot detector. arXiv preprint arXiv:1701.06659 (2017)."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"crossref","unstructured":"Guillermo Gallego Tobi Delbr\u00fcck Garrick Orchard Chiara Bartolozzi Brian Taba Andrea Censi Stefan Leutenegger Andrew J Davison J\u00f6rg Conradt Kostas Daniilidis et al. 2020. Event-based vision: A survey. IEEE transactions on pattern analysis and machine intelligence Vol. 44 1 (2020) 154-180.","DOI":"10.1109\/TPAMI.2020.3008413"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-024-07409-w"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3068942"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01334"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"e_1_3_2_2_23_1","volume-title":"Mamba: Linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.00752","author":"Gu Albert","year":"2023","unstructured":"Albert Gu and Tri Dao. 2023. Mamba: Linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.00752 (2023)."},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00012"},{"key":"e_1_3_2_2_27_1","unstructured":"Glenn Jocher Jing Qiu and Ayush Chaurasia. 2023. Ultralytics YOLO. https:\/\/github.com\/ultralytics\/ultralytics"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6787"},{"key":"e_1_3_2_2_29_1","volume-title":"Wei Tsang Ooi, and Benoit R Cottereau.","author":"Kong Lingdong","year":"2025","unstructured":"Lingdong Kong, Dongyue Lu, Xiang Xu, Lai Xing Ng, Wei Tsang Ooi, and Benoit R Cottereau. 2025. EventFly: Event Camera Perception from Ground to the Sky. arXiv preprint arXiv:2503.19916 (2025)."},{"key":"e_1_3_2_2_30_1","unstructured":"Chuyi Li Lulu Li Hongliang Jiang Kaiheng Weng Yifei Geng Liang Li Zaidan Ke Qingyuan Li Meng Cheng Weiqiang Nie et al. 2022. YOLOv6: A single-stage object detection framework for industrial applications. arXiv preprint arXiv:2209.02976 (2022)."},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.211"},{"key":"e_1_3_2_2_32_1","unstructured":"Quanmin Liang Zhilin Huang Xiawu Zheng Feidiao Yang Jun Peng Kai Huang and Yonghong Tian. [n.d.]. Efficient Event Stream Super-Resolution with Recursive Multi-Branch Fusion. ([n.d.])."},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612462"},{"key":"e_1_3_2_2_34_1","volume-title":"IEEE journal of solid-state circuits","author":"Lichtsteiner Patrick","year":"2008","unstructured":"Patrick Lichtsteiner, Christoph Posch, and Tobi Delbruck. 2008. A 128$ times $128 120 dB 15 \u03bc s latency asynchronous temporal contrast vision sensor. IEEE journal of solid-state circuits, Vol. 43, 2 (2008), 566-576."},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"e_1_3_2_2_36_1","first-page":"1","article-title":"Motion robust high-speed light-weighted object detection with event camera","volume":"72","author":"Liu Bingde","year":"2023","unstructured":"Bingde Liu, Chang Xu, Wen Yang, Huai Yu, and Lei Yu. 2023. Motion robust high-speed light-weighted object detection with event camera. IEEE Transactions on Instrumentation and Measurement, Vol. 72 (2023), 1-13.","journal-title":"IEEE Transactions on Instrumentation and Measurement"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"e_1_3_2_2_38_1","volume-title":"European Conference on Computer Vision. Springer, 253-272","author":"Luo Xinhao","year":"2024","unstructured":"Xinhao Luo, Man Yao, Yuhong Chou, Bo Xu, and Guoqi Li. 2024. Integer-valued training and spike-driven inference spiking neural network for high-performance and energy-efficient object detection. In European Conference on Computer Vision. Springer, 253-272."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00568"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00546"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00103"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00982"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00555"},{"key":"e_1_3_2_2_44_1","first-page":"16639","article-title":"Learning to detect objects with a 1 megapixel event camera","volume":"33","author":"Perot Etienne","year":"2020","unstructured":"Etienne Perot, Pierre De Tournemire, Davide Nitti, Jonathan Masci, and Amos Sironi. 2020. Learning to detect objects with a 1 megapixel event camera. Advances in Neural Information Processing Systems, Vol. 33 (2020), 16639-16652.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_45_1","volume-title":"High speed and high dynamic range video with an event camera","author":"Rebecq Henri","year":"2019","unstructured":"Henri Rebecq, Ren\u00e9 Ranftl, Vladlen Koltun, and Davide Scaramuzza. 2019. High speed and high dynamic range video with an event camera. IEEE transactions on pattern analysis and machine intelligence, Vol. 43, 6 (2019), 1964-1980."},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"e_1_3_2_2_47_1","volume-title":"Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems","author":"Ren Shaoqing","year":"2015","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, Vol. 28 (2015)."},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00603"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812059"},{"key":"e_1_3_2_2_50_1","first-page":"107984","article-title":"Yolov10: Real-time end-to-end object detection","volume":"37","author":"Wang Ao","year":"2024","unstructured":"Ao Wang, Hui Chen, Lihao Liu, Kai Chen, Zijia Lin, Jungong Han, et al., 2024. Yolov10: Real-time end-to-end object detection. Advances in Neural Information Processing Systems, Vol. 37 (2024), 107984-108011.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_42"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_33"},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00931"},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01602"},{"key":"e_1_3_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01404"},{"key":"e_1_3_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00828"},{"key":"e_1_3_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01330"},{"key":"e_1_3_2_2_58_1","volume-title":"Multi-scale context aggregation by dilated convolutions. arXiv preprint arXiv:1511.07122","author":"Yu Fisher","year":"2015","unstructured":"Fisher Yu and Vladlen Koltun. 2015. Multi-scale context aggregation by dilated convolutions. arXiv preprint arXiv:1511.07122 (2015)."},{"key":"e_1_3_2_2_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00581"},{"key":"e_1_3_2_2_60_1","volume-title":"Dino: Detr with improved denoising anchor boxes for end-to-end object detection. arXiv preprint arXiv:2203.03605","author":"Zhang Hao","year":"2022","unstructured":"Hao Zhang, Feng Li, Shilong Liu, Lei Zhang, Hang Su, Jun Zhu, Lionel M Ni, and Heung-Yeung Shum. 2022. Dino: Detr with improved denoising anchor boxes for end-to-end object detection. arXiv preprint arXiv:2203.03605 (2022)."},{"key":"e_1_3_2_2_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01605"},{"key":"e_1_3_2_2_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00614"},{"key":"e_1_3_2_2_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3223955"},{"key":"e_1_3_2_2_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161563"},{"key":"e_1_3_2_2_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00108"},{"key":"e_1_3_2_2_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00753"},{"key":"e_1_3_2_2_67_1","volume-title":"Deformable detr: Deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159","author":"Zhu Xizhou","year":"2020","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:2010.04159 (2020)."},{"key":"e_1_3_2_2_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01889"},{"key":"e_1_3_2_2_69_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 5819-5828","author":"Zubic Nikola","year":"2024","unstructured":"Nikola Zubic, Mathias Gehrig, and Davide Scaramuzza. 2024. State space models for event cameras. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 5819-5828."}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755486","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:18:08Z","timestamp":1765307888000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755486"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":69,"alternative-id":["10.1145\/3746027.3755486","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755486","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}