{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T15:54:57Z","timestamp":1781538897104,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":51,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T00:00:00Z","timestamp":1781481600000},"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":[[2026,6,16]]},"DOI":"10.1145\/3805622.3810592","type":"proceedings-article","created":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T14:42:57Z","timestamp":1781534577000},"page":"1270-1278","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Time-Surface Self-Attention: Restoring Temporal Connectivity in Spiking Transformers"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-3496-0962","authenticated-orcid":false,"given":"Tiantian","family":"Xiao","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, Beijing Normal University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2542-360X","authenticated-orcid":false,"given":"Xi","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beijing Normal University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9230-8073","authenticated-orcid":false,"given":"Hongbin","family":"Lv","sequence":"additional","affiliation":[{"name":"School of Biological Science and Medical Engineering, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8463-4104","authenticated-orcid":false,"given":"Daoyuan","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Central South University, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,15]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"crossref","unstructured":"Filipp Akopyan Jun Sawada Andrew Cassidy Rodrigo Alvarez-Icaza John Arthur Paul Merolla Nabil Imam Yutaka Nakamura Pallab Datta Gi-Joon Nam et\u00a0al. 2015. Truenorth: Design and tool flow of a 65 mw 1 million neuron programmable neurosynaptic chip. IEEE transactions on computer-aided design of integrated circuits and systems 34 10 (2015) 1537\u20131557.","DOI":"10.1109\/TCAD.2015.2474396"},{"key":"e_1_3_3_1_3_2","unstructured":"Guillaume Bellec Darjan Salaj Anand Subramoney Robert Legenstein and Wolfgang Maass. 2018. Long short-term memory and learning-to-learn in networks of spiking neurons. Advances in neural information processing systems 31 (2018)."},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"crossref","unstructured":"Anas Bilal Xiaowen Liu Muhammad Shafiq Zohaib Ahmed and Haixia Long. 2024. NIMEQ-SACNet: A novel self-attention precision medicine model for vision-threatening diabetic retinopathy using image data. Computers in Biology and Medicine 171 (2024) 108099.","DOI":"10.1016\/j.compbiomed.2024.108099"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"crossref","unstructured":"Sander\u00a0M Bohte. 2004. The evidence for neural information processing with precise spike-times: A survey. Natural Computing 3 2 (2004) 195\u2013206.","DOI":"10.1023\/B:NACO.0000027755.02868.60"},{"key":"e_1_3_3_1_6_2","unstructured":"Honglin Cao Zijian Zhou Wenjie Wei Ammar Belatreche Yu Liang Dehao Zhang Malu Zhang Yang Yang and Haizhou Li. 2025. Binary event-driven spiking transformer. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2501.05904 (2025)."},{"key":"e_1_3_3_1_7_2","first-page":"74","volume-title":"European Conference on Computer Vision","author":"Chen Junsong","year":"2024","unstructured":"Junsong Chen, Chongjian Ge, Enze Xie, Yue Wu, Lewei Yao, Xiaozhe Ren, Zhongdao Wang, Ping Luo, Huchuan Lu, and Zhenguo Li. 2024. Pixart-\u03c3 : Weak-to-strong training of diffusion transformer for 4k text-to-image generation. In European Conference on Computer Vision. 74\u201391."},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"crossref","unstructured":"Yuwei Chen Jiawei Chen Zhefei Cai Yingle Fan Yanming Wang and Minwei Zhu. 2025. WEI-SNNs: Spiking neural networks based on excitation-inhibition neurons and widening learnable time constants. Neurocomputing 654 (2025) 131386.","DOI":"10.1016\/j.neucom.2025.131386"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i10.29066"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"crossref","unstructured":"Chuan Fu Tianyuan Zhou Tan Guo Qikui Zhu Fulin Luo and Bo Du. 2025. CNN-Transformer and Channel-Spatial Attention based network for hyperspectral image classification with few samples. Neural Networks 186 (2025) 107283.","DOI":"10.1016\/j.neunet.2025.107283"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00463"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511815706"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"crossref","unstructured":"Xiayu Guo Xian Lin Xin Yang Li Yu Kwang-Ting Cheng and Zengqiang Yan. 2024. UCTNet: Uncertainty-guided CNN-Transformer hybrid networks for medical image segmentation. Pattern Recognition 152 (2024) 110491.","DOI":"10.1016\/j.patcog.2024.110491"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02272"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"crossref","unstructured":"Yufei Guo Weihang Peng Xiaode Liu Yuanpei Chen Yuhan Zhang Xin Tong Zhou Jie and Zhe Ma. 2024. Enof-snn: Training accurate spiking neural networks via enhancing the output feature. Advances in Neural Information Processing Systems 37 (2024) 51708\u201351726.","DOI":"10.52202\/079017-1638"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN60899.2024.10650320"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02352"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2014.6757323"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"crossref","unstructured":"Yifan Hu Lei Deng Yujie Wu Man Yao and Guoqi Li. 2024. Advancing spiking neural networks toward deep residual learning. IEEE transactions on neural networks and learning systems 36 2 (2024) 2353\u20132367.","DOI":"10.1109\/TNNLS.2024.3355393"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_3"},{"key":"e_1_3_3_1_22_2","unstructured":"Alex Krizhevsky Geoffrey Hinton et\u00a0al. 2009. Learning multiple layers of features from tiny images. (2009)."},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01302"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"crossref","unstructured":"Hongmin Li Hanchao Liu Xiangyang Ji Guoqi Li and Luping Shi. 2017. Cifar10-dvs: an event-stream dataset for object classification. Frontiers in neuroscience 11 (2017) 244131.","DOI":"10.3389\/fnins.2017.00309"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755030"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"crossref","unstructured":"Chengzhuo Lu Huilin Du Wenjie Wei Qian Sun Yuchen Wang Dingyi Zeng Wenyu Chen Malu Zhang and Yang Yang. 2025. ESTSformer: Efficient spatio-temporal spiking transformer. Neural Networks 191 (2025) 107786.","DOI":"10.1016\/j.neunet.2025.107786"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"crossref","unstructured":"Wolfgang Maass. 1997. Networks of spiking neurons: the third generation of neural network models. Neural networks 10 9 (1997) 1659\u20131671.","DOI":"10.1016\/S0893-6080(97)00011-7"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"crossref","unstructured":"Emre\u00a0O Neftci Hesham Mostafa and Friedemann Zenke. 2019. Surrogate gradient learning in spiking neural networks: Bringing the power of gradient-based optimization to spiking neural networks. IEEE Signal Processing Magazine 36 6 (2019) 51\u201363.","DOI":"10.1109\/MSP.2019.2931595"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"crossref","unstructured":"Garrick Orchard Ajinkya Jayawant Gregory\u00a0K Cohen and Nitish Thakor. 2015. Converting static image datasets to spiking neuromorphic datasets using saccades. Frontiers in neuroscience 9 (2015) 437.","DOI":"10.3389\/fnins.2015.00437"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"crossref","unstructured":"Daniel\u00a0S Reich Ferenc Mechler and Jonathan\u00a0D Victor. 2001. Temporal coding of contrast in primary visual cortex: when what and why. Journal of neurophysiology 85 3 (2001) 1039\u20131050.","DOI":"10.1152\/jn.2001.85.3.1039"},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"crossref","unstructured":"Kaushik Roy Akhilesh Jaiswal and Priyadarshini Panda. 2019. Towards spike-based machine intelligence with neuromorphic computing. Nature 575 7784 (2019) 607\u2013617.","DOI":"10.1038\/s41586-019-1677-2"},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00891"},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"crossref","unstructured":"Abhronil Sengupta Yuting Ye Robert Wang Chiao Liu and Kaushik Roy. 2019. Going deeper in spiking neural networks: VGG and residual architectures. Frontiers in neuroscience 13 (2019) 95.","DOI":"10.3389\/fnins.2019.00095"},{"key":"e_1_3_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00536"},{"key":"e_1_3_3_1_35_2","unstructured":"Xiaotian Song Zeqiong Lv Jiaohao Fan Xiong Deng Jiancheng Lv Jiyuan Liu and Yanan Sun. 2025. Evolutionary multi-objective spiking neural architecture search for image classification. IEEE Transactions on Evolutionary Computation (2025)."},{"key":"e_1_3_3_1_36_2","unstructured":"Jianxiong Tang Jianhuang Lai Xiaohua Xie Lingxiao Yang and Wei-Shi Zheng. 2022. Snn2ann: A fast and memory-efficient training framework for spiking neural networks. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2206.09449 (2022)."},{"key":"e_1_3_3_1_37_2","first-page":"315","volume-title":"European Conference on Computer Vision","author":"Wang Feng","year":"2024","unstructured":"Feng Wang, Jieru Mei, and Alan Yuille. 2024. Sclip: Rethinking self-attention for dense vision-language inference. In European Conference on Computer Vision. 315\u2013332."},{"key":"e_1_3_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i2.32150"},{"key":"e_1_3_3_1_39_2","doi-asserted-by":"crossref","unstructured":"Shuang Wu Youtian Lin Feihu Zhang Yifei Zeng Jingxi Xu Philip Torr Xun Cao and Yao Yao. 2024. Direct3d: Scalable image-to-3d generation via 3d latent diffusion transformer. Advances in Neural Information Processing Systems 37 (2024) 121859\u2013121881.","DOI":"10.52202\/079017-3873"},{"key":"e_1_3_3_1_40_2","doi-asserted-by":"crossref","unstructured":"Yujie Wu Lei Deng Guoqi Li Jun Zhu and Luping Shi. 2018. Spatio-temporal backpropagation for training high-performance spiking neural networks. Frontiers in neuroscience 12 (2018) 331.","DOI":"10.3389\/fnins.2018.00331"},{"key":"e_1_3_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33011311"},{"key":"e_1_3_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680655"},{"key":"e_1_3_3_1_43_2","doi-asserted-by":"crossref","unstructured":"Man Yao Jiakui Hu Zhaokun Zhou Li Yuan Yonghong Tian Bo Xu and Guoqi Li. 2023. Spike-driven transformer. Advances in neural information processing systems 36 (2023) 64043\u201364058.","DOI":"10.52202\/075280-2798"},{"key":"e_1_3_3_1_44_2","doi-asserted-by":"crossref","unstructured":"Friedemann Zenke and Surya Ganguli. 2018. Superspike: Supervised learning in multilayer spiking neural networks. Neural computation 30 6 (2018) 1514\u20131541.","DOI":"10.1162\/neco_a_01086"},{"key":"e_1_3_3_1_45_2","doi-asserted-by":"crossref","unstructured":"Hangming Zhang Alexander Sboev Roman Rybka and Qiang Yu. 2025. Combining aggregated attention and transformer architecture for accurate and efficient performance of Spiking Neural Networks. Neural Networks 191 (2025) 107789.","DOI":"10.1016\/j.neunet.2025.107789"},{"key":"e_1_3_3_1_46_2","doi-asserted-by":"crossref","unstructured":"Weidong Zhang Gongchao Chen Peixian Zhuang Wenyi Zhao and Ling Zhou. 2024. CATNet: Cascaded attention transformer network for marine species image classification. Expert Systems with Applications 256 (2024) 124932.","DOI":"10.1016\/j.eswa.2024.124932"},{"key":"e_1_3_3_1_47_2","doi-asserted-by":"crossref","unstructured":"Xiangyu Zhang Qiquan Zhang Hexin Liu Tianyi Xiao Xinyuan Qian Beena Ahmed Eliathamby Ambikairajah Haizhou Li and Julien Epps. 2025. Mamba in speech: Towards an alternative to self-attention. IEEE Transactions on Audio Speech and Language Processing 33 (2025) 1933\u20131948.","DOI":"10.1109\/TASLPRO.2025.3566210"},{"key":"e_1_3_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17320"},{"key":"e_1_3_3_1_49_2","unstructured":"Chenlin Zhou Liutao Yu Zhaokun Zhou Zhengyu Ma Han Zhang Huihui Zhou and Yonghong Tian. 2023. Spikingformer: Spike-driven residual learning for transformer-based spiking neural network. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2304.11954 (2023)."},{"key":"e_1_3_3_1_50_2","doi-asserted-by":"crossref","unstructured":"Chenlin Zhou Han Zhang Zhaokun Zhou Liutao Yu Liwei Huang Xiaopeng Fan Li Yuan Zhengyu Ma Huihui Zhou and Yonghong Tian. 2024. Qkformer: Hierarchical spiking transformer using qk attention. Advances in Neural Information Processing Systems 37 (2024) 13074\u201313098.","DOI":"10.52202\/079017-0416"},{"key":"e_1_3_3_1_51_2","unstructured":"Zhaokun Zhou Yuesheng Zhu Chao He Yaowei Wang Shuicheng Yan Yonghong Tian and Li Yuan. 2022. Spikformer: When spiking neural network meets transformer. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2209.15425 (2022)."},{"key":"e_1_3_3_1_52_2","doi-asserted-by":"crossref","unstructured":"Rui-Jie Zhu Malu Zhang Qihang Zhao Haoyu Deng Yule Duan and Liang-Jian Deng. 2024. Tcja-snn: Temporal-channel joint attention for spiking neural networks. IEEE Transactions on Neural Networks and Learning Systems 36 3 (2024) 5112\u20135125.","DOI":"10.1109\/TNNLS.2024.3377717"}],"event":{"name":"ICMR '26: International Conference on Multimedia Retrieval","location":"Amsterdam The Netherlands","acronym":"ICMR '26","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 2026 International Conference on Multimedia Retrieval"],"original-title":[],"deposited":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T15:03:02Z","timestamp":1781535782000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805622.3810592"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,15]]},"references-count":51,"alternative-id":["10.1145\/3805622.3810592","10.1145\/3805622"],"URL":"https:\/\/doi.org\/10.1145\/3805622.3810592","relation":{},"subject":[],"published":{"date-parts":[[2026,6,15]]},"assertion":[{"value":"2026-06-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}