{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:10:23Z","timestamp":1765339823542,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":52,"publisher":"ACM","funder":[{"name":"National Science Foundation of China","award":["92470126"],"award-info":[{"award-number":["92470126"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755380","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:38:54Z","timestamp":1761377934000},"page":"479-488","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["An Event-tailored State-Space Based Model for Pedestrian Detection"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-3084-9384","authenticated-orcid":false,"given":"Liuyi","family":"Li","sequence":"first","affiliation":[{"name":"Jiangsu Key Laboratory of Intelligent Information Processing and Communication Technology, School of Communications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0328-4171","authenticated-orcid":false,"given":"Feng","family":"Shi","sequence":"additional","affiliation":[{"name":"Jiangsu Key Laboratory of Intelligent Information Processing and Communication Technology, School of Communications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6727-5109","authenticated-orcid":false,"given":"Jian","family":"Wang","sequence":"additional","affiliation":[{"name":"Jiangsu Key Laboratory of Intelligent Information Processing and Communication Technology, School of Communications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-0119-7446","authenticated-orcid":false,"given":"Jinjing","family":"Zhu","sequence":"additional","affiliation":[{"name":"Jiangsu Key Laboratory of Intelligent Information Processing and Communication Technology, School of Communications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6869-7789","authenticated-orcid":false,"given":"Wenze","family":"Shao","sequence":"additional","affiliation":[{"name":"Jiangsu Key Laboratory of Intelligent Information Processing and Communication Technology, School of Communications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"A solution to the learning dilemma for recurrent networks of spiking neurons. Nature communications","author":"Bellec Guillaume","year":"2020","unstructured":"Guillaume Bellec, Franz Scherr, Anand Subramoney, Elias Hajek, Darjan Salaj, Robert Legenstein, and Wolfgang Maass. 2020. A solution to the learning dilemma for recurrent networks of spiking neurons. Nature communications, Vol. 11, 1 (2020), 3625."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00426"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00209"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00107"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27914"},{"key":"e_1_3_2_1_7_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_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01627"},{"key":"e_1_3_2_1_9_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_1_10_1","volume-title":"Yolox: Exceeding yolo series in","author":"Ge Zheng","year":"2021","unstructured":"Zheng Ge, Songtao Liu, Feng Wang, Zeming Li, and Jian Sun. 2021. Yolox: Exceeding yolo series in 2021. arXiv preprint arXiv:2107.08430 (2021)."},{"key":"e_1_3_2_1_11_1","volume-title":"Pushing the limits of asynchronous graph-based object detection with event cameras. arXiv preprint arXiv:2211.12324","author":"Gehrig Daniel","year":"2022","unstructured":"Daniel Gehrig and Davide Scaramuzza. 2022. Pushing the limits of asynchronous graph-based object detection with event cameras. arXiv preprint arXiv:2211.12324 (2022)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01334"},{"key":"e_1_3_2_1_13_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_1_14_1","first-page":"35971","article-title":"On the parameterization and initialization of diagonal state space models","volume":"35","author":"Gu Albert","year":"2022","unstructured":"Albert Gu, Karan Goel, Ankit Gupta, and Christopher R\u00e9. 2022. On the parameterization and initialization of diagonal state space models. Advances in Neural Information Processing Systems, Vol. 35 (2022), 35971-35983.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_15_1","volume-title":"Efficiently modeling long sequences with structured state spaces. arXiv preprint arXiv:2111.00396","author":"Gu Albert","year":"2021","unstructured":"Albert Gu, Karan Goel, and Christopher R\u00e9. 2021a. Efficiently modeling long sequences with structured state spaces. arXiv preprint arXiv:2111.00396 (2021)."},{"key":"e_1_3_2_1_16_1","volume-title":"Combining recurrent, convolutional, and continuous-time models with linear state space layers. Advances in neural information processing systems","author":"Gu Albert","year":"2021","unstructured":"Albert Gu, Isys Johnson, Karan Goel, Khaled Saab, Tri Dao, Atri Rudra, and Christopher R\u00e9. 2021b. Combining recurrent, convolutional, and continuous-time models with linear state space layers. Advances in neural information processing systems, Vol. 34 (2021), 572-585."},{"key":"e_1_3_2_1_17_1","first-page":"22982","article-title":"Diagonal state spaces are as effective as structured state spaces","volume":"35","author":"Gupta Ankit","year":"2022","unstructured":"Ankit Gupta, Albert Gu, and Jonathan Berant. 2022. Diagonal state spaces are as effective as structured state spaces. Advances in Neural Information Processing Systems, Vol. 35 (2022), 22982-22994.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02190"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8594119"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793924"},{"key":"e_1_3_2_1_21_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_22_1","volume-title":"Hots: a hierarchy of event-based time-surfaces for pattern recognition","author":"Lagorce Xavier","year":"2016","unstructured":"Xavier Lagorce, Garrick Orchard, Francesco Galluppi, Bertram E Shi, and Ryad B Benosman. 2016. Hots: a hierarchy of event-based time-surfaces for pattern recognition. IEEE transactions on pattern analysis and machine intelligence, Vol. 39, 7 (2016), 1346-1359."},{"key":"e_1_3_2_1_23_1","volume-title":"Priyadarshini Panda, Gopalakrishnan Srinivasan, and Kaushik Roy.","author":"Lee Chankyu","year":"2020","unstructured":"Chankyu Lee, Syed Shakib Sarwar, Priyadarshini Panda, Gopalakrishnan Srinivasan, and Kaushik Roy. 2020. Enabling spike-based backpropagation for training deep neural network architectures. Frontiers in neuroscience, Vol. 14 (2020), 497482."},{"key":"e_1_3_2_1_24_1","volume-title":"Training deep spiking neural networks using backpropagation. Frontiers in neuroscience","author":"Lee Jun Haeng","year":"2016","unstructured":"Jun Haeng Lee, Tobi Delbruck, and Michael Pfeiffer. 2016. Training deep spiking neural networks using backpropagation. Frontiers in neuroscience, Vol. 10 (2016), 508."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3162962"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00097"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00643"},{"key":"e_1_3_2_1_28_1","first-page":"740","volume-title":"Switzerland","author":"Lin Tsung-Yi","year":"2014","unstructured":"Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Doll\u00e1r, and C Lawrence Zitnick. 2014. Microsoft coco: Common objects in context. In Computer vision-ECCV 2014: 13th European conference, zurich, Switzerland, September 6-12, 2014, proceedings, part v 13. Springer, 740-755."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"e_1_3_2_1_30_1","volume-title":"Event-based monocular dense depth estimation with recurrent transformers. arXiv preprint arXiv:2212.02791","author":"Liu Xu","year":"2022","unstructured":"Xu Liu, Jianing Li, Xiaopeng Fan, and Yonghong Tian. 2022. Event-based monocular dense depth estimation with recurrent transformers. arXiv preprint arXiv:2212.02791 (2022)."},{"key":"e_1_3_2_1_31_1","volume-title":"Vision mamba: A comprehensive survey and taxonomy. arXiv preprint arXiv:2405.04404","author":"Liu Xiao","year":"2024","unstructured":"Xiao Liu, Chenxu Zhang, and Lei Zhang. 2024b. Vision mamba: A comprehensive survey and taxonomy. arXiv preprint arXiv:2405.04404 (2024)."},{"key":"e_1_3_2_1_32_1","volume-title":"Vmamba: Visual state space model. Advances in neural information processing systems","author":"Liu Yue","year":"2024","unstructured":"Yue Liu, Yunjie Tian, Yuzhong Zhao, Hongtian Yu, Lingxi Xie, Yaowei Wang, Qixiang Ye, Jianbin Jiao, and Yunfan Liu. 2024a. Vmamba: Visual state space model. Advances in neural information processing systems, Vol. 37 (2024), 103031-103063."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58598-3_25"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01442"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/EBCCSP.2016.7605233"},{"key":"e_1_3_2_1_36_1","volume-title":"S4nd: Modeling images and videos as multidimensional signals with state spaces. Advances in neural information processing systems","author":"Nguyen Eric","year":"2022","unstructured":"Eric Nguyen, Karan Goel, Albert Gu, Gordon Downs, Preey Shah, Tri Dao, Stephen Baccus, and Christopher R\u00e9. 2022. S4nd: Modeling images and videos as multidimensional signals with state spaces. Advances in neural information processing systems, Vol. 35 (2022), 2846-2861."},{"key":"e_1_3_2_1_37_1","volume-title":"HFirst: A temporal approach to object recognition","author":"Orchard Garrick","year":"2015","unstructured":"Garrick Orchard, Cedric Meyer, Ralph Etienne-Cummings, Christoph Posch, Nitish Thakor, and Ryad Benosman. 2015. HFirst: A temporal approach to object recognition. IEEE transactions on pattern analysis and machine intelligence, Vol. 37, 10 (2015), 2028-2040."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01589"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00555"},{"key":"e_1_3_2_1_40_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_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01205"},{"key":"e_1_3_2_1_43_1","volume-title":"Slayer: Spike layer error reassignment in time. Advances in neural information processing systems","author":"Shrestha Sumit B","year":"2018","unstructured":"Sumit B Shrestha and Garrick Orchard. 2018. Slayer: Spike layer error reassignment in time. Advances in neural information processing systems, Vol. 31 (2018)."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00186"},{"key":"e_1_3_2_1_45_1","volume-title":"Simplified state space layers for sequence modeling. arXiv preprint arXiv:2208.04933","author":"Smith Jimmy TH","year":"2022","unstructured":"Jimmy TH Smith, Andrew Warrington, and Scott W Linderman. 2022. Simplified state space layers for sequence modeling. arXiv preprint arXiv:2208.04933 (2022)."},{"key":"e_1_3_2_1_46_1","volume-title":"Super-convergence: Very fast training of neural networks using large learning rates. In Artificial intelligence and machine learning for multi-domain operations applications","author":"Smith Leslie N","year":"2019","unstructured":"Leslie N Smith and Nicholay Topin. 2019. Super-convergence: Very fast training of neural networks using large learning rates. In Artificial intelligence and machine learning for multi-domain operations applications, Vol. 11006. SPIE, 369-386."},{"key":"e_1_3_2_1_47_1","volume-title":"Mamba YOLO: SSMs-based YOLO for object detection. arXiv preprint arXiv:2406.05835","author":"Wang Zeyu","year":"2024","unstructured":"Zeyu Wang, Chen Li, Huiying Xu, and Xinzhong Zhu. 2024. Mamba YOLO: SSMs-based YOLO for object detection. arXiv preprint arXiv:2406.05835 (2024)."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01006"},{"key":"e_1_3_2_1_49_1","volume-title":"Meta-transformer: A unified framework for multimodal learning. arXiv preprint arXiv:2307.10802","author":"Zhang Yiyuan","year":"2023","unstructured":"Yiyuan Zhang, Kaixiong Gong, Kaipeng Zhang, Hongsheng Li, Yu Qiao, Wanli Ouyang, and Xiangyu Yue. 2023. Meta-transformer: A unified framework for multimodal learning. arXiv preprint arXiv:2307.10802 (2023)."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00108"},{"key":"e_1_3_2_1_51_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."},{"key":"e_1_3_2_1_52_1","first-page":"309","volume-title":"AIAI 2021, Hersonissos, Crete, Greece, June 25-27, 2021, Proceedings 17","author":"Zubi\u0107 Nikola","year":"2021","unstructured":"Nikola Zubi\u0107 and Pietro Li\u00f2. 2021. An effective loss function for generating 3D models from single 2D image without rendering. In Artificial Intelligence Applications and Innovations: 17th IFIP WG 12.5 International Conference, AIAI 2021, Hersonissos, Crete, Greece, June 25-27, 2021, Proceedings 17. Springer, 309-322."}],"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\/3746027.3755380","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:08:21Z","timestamp":1765339701000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755380"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":52,"alternative-id":["10.1145\/3746027.3755380","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755380","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"}}]}}