{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T13:20:18Z","timestamp":1763644818582,"version":"3.45.0"},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"15","license":[{"start":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T00:00:00Z","timestamp":1757376000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T00:00:00Z","timestamp":1757376000000},"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":["Vis Comput"],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1007\/s00371-025-04173-4","type":"journal-article","created":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T15:29:48Z","timestamp":1757431788000},"page":"12577-12588","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Spiking ST-former: enhancing spatio-temporal modeling in spiking transformers via integrated self-attention mechanisms"],"prefix":"10.1007","volume":"41","author":[{"given":"Yijun","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wujian","family":"Ye","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guoliang","family":"Tan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Youfeng","family":"Cui","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,9,9]]},"reference":[{"issue":"9","key":"4173_CR1","doi-asserted-by":"publisher","first-page":"1659","DOI":"10.1016\/S0893-6080(97)00011-7","volume":"10","author":"W Maass","year":"1997","unstructured":"Maass, W.: Networks of spiking neurons: The third generation of neural network models. Neural Netw. 10(9), 1659\u20131671 (1997). https:\/\/doi.org\/10.1016\/S0893-6080(97)00011-7","journal-title":"Neural Netw."},{"key":"4173_CR2","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1007\/978-3-642-03156-4_17","volume-title":"Advances in Computational Intelligence","author":"S Ghosh-Dastidar","year":"2009","unstructured":"Ghosh-Dastidar, S., Adeli, H.: Third generation neural networks: spiking neural networks. In: Yu, W., Sanchez, E.N. (eds.) Advances in Computational Intelligence, pp. 167\u2013178. Springer, Berlin (2009)"},{"key":"4173_CR3","doi-asserted-by":"crossref","unstructured":"Zheng, H., Wu, Y., Deng, L., Hu, Y., Li, G.: Going deeper with directly-trained larger spiking neural networks. In: AAAI Conference on Artificial Intelligence (2020). https:\/\/api.semanticscholar.org\/CorpusID:226290189","DOI":"10.1609\/aaai.v35i12.17320"},{"key":"4173_CR4","doi-asserted-by":"publisher","first-page":"5200","DOI":"10.1109\/TNNLS.2021.3119238","volume":"34","author":"Y Hu","year":"2021","unstructured":"Hu, Y., Tang, H., Pan, G.: Spiking deep residual networks. IEEE Trans Neural Netw Learn Syst 34, 5200\u20135205 (2021)","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"4173_CR5","unstructured":"Vaswani, A., Shazeer, N.M., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., Polosukhin, I.: Attention is all you need. In: Neural Information Processing Systems (2017). https:\/\/api.semanticscholar.org\/CorpusID:13756489"},{"key":"4173_CR6","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., Houlsby, N.: An image is worth 16x16 words: transformers for image recognition at scale. ArXiv arXiv:2010.11929 (2020)"},{"key":"4173_CR7","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2023.119170","volume":"644","author":"G Shen","year":"2023","unstructured":"Shen, G., Zhao, D., Zeng, Y.: Eventmix: an efficient data augmentation strategy for event-based learning. Inf. Sci. 644, 119170 (2023). https:\/\/doi.org\/10.1016\/j.ins.2023.119170","journal-title":"Inf. Sci."},{"issue":"1","key":"4173_CR8","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1109\/TPAMI.2022.3152247","volume":"45","author":"K Han","year":"2020","unstructured":"Han, K., Wang, Y., Chen, H., Chen, X., Guo, J., Liu, Z., Tang, Y., Xiao, A., Xu, C., Xu, Y., Yang, Z., Zhang, Y., Tao, D.: A survey on vision transformer. IEEE Trans. Pattern Anal. Mach. Intell. 45(1), 87\u2013110 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"4173_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3505244","volume":"54","author":"SH Khan","year":"2021","unstructured":"Khan, S.H., Naseer, M., Hayat, M., Zamir, S.W., Khan, F.S., Shah, M.: Transformers in vision: a survey. ACM Comput Surv (CSUR) 54, 1\u201341 (2021)","journal-title":"ACM Comput Surv (CSUR)"},{"key":"4173_CR10","unstructured":"Wang, Q., Zhang, D., Zhang, T., Xu, B.: Attention-free spikformer: mixing spike sequences with simple linear transforms. ArXiv arXiv:2308.02557 (2023)"},{"key":"4173_CR11","unstructured":"Zhou, Z., Zhu, Y., He, C., Wang, Y., Yan, S., Tian, Y., Yuan, L.: Spikformer: When spiking neural network meets transformer. ArXiv arXiv:2209.15425 (2022)"},{"key":"4173_CR12","doi-asserted-by":"publisher","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-cam: visual explanations from deep networks via gradient-based localization. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 618\u2013626 (2017). https:\/\/doi.org\/10.1109\/ICCV.2017.74","DOI":"10.1109\/ICCV.2017.74"},{"key":"4173_CR13","first-page":"25","volume":"52","author":"H Al","year":"1952","unstructured":"Al, H., Af, H.: A quantitative description of membrane current and its application to conduction and excitation in nerve. Bull. Math. Biol. 52, 25\u201371 (1952)","journal-title":"Bull. Math. Biol."},{"issue":"6","key":"4173_CR14","doi-asserted-by":"publisher","first-page":"1569","DOI":"10.1109\/TNN.2003.820440","volume":"14","author":"EM Izhikevich","year":"2003","unstructured":"Izhikevich, E.M.: Simple model of spiking neurons. IEEE Trans. Neural Netw. 14(6), 1569\u20131572 (2003). https:\/\/doi.org\/10.1109\/TNN.2003.820440","journal-title":"IEEE Trans. Neural Netw."},{"key":"4173_CR15","doi-asserted-by":"crossref","unstructured":"Fang, W., Yu, Z., Chen, Y., Masquelier, T., Huang, T., Tian, Y.: Incorporating learnable membrane time constant to enhance learning of spiking neural networks. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), 2641\u20132651 (2020)","DOI":"10.1109\/ICCV48922.2021.00266"},{"key":"4173_CR16","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.127279","volume":"574","author":"Y Li","year":"2024","unstructured":"Li, Y., Lei, Y., Yang, X.: Spikeformer: training high-performance spiking neural network with transformer. Neurocomputing 574, 127279 (2024). https:\/\/doi.org\/10.1016\/j.neucom.2024.127279","journal-title":"Neurocomputing"},{"key":"4173_CR17","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1109\/TMM.2021.3120873","volume":"25","author":"X Lin","year":"2023","unstructured":"Lin, X., Sun, S., Huang, W., Sheng, B., Li, P., Feng, D.D.: EAPT: efficient attention pyramid transformer for image processing. IEEE Trans. Multimed 25, 50\u201361 (2023). https:\/\/doi.org\/10.1109\/TMM.2021.3120873","journal-title":"IEEE Trans. Multimed"},{"issue":"12","key":"4173_CR18","doi-asserted-by":"publisher","first-page":"9039","DOI":"10.1007\/s00371-024-03294-6","volume":"40","author":"Y Gong","year":"2024","unstructured":"Gong, Y., Wu, P., Xu, R., Zhang, X., Wang, T., Li, X.: Tripleformer: improving transformer-based image classification method using multiple self-attention inputs. Vis. Comput. 40(12), 9039\u20139050 (2024). https:\/\/doi.org\/10.1007\/s00371-024-03294-6","journal-title":"Vis. Comput."},{"key":"4173_CR19","unstructured":"Yao, M., Hu, J., Zhou, Z., Yuan, L., Tian, Y., Xu, B., Li, G.: Spike-driven Transformer (2023). arXiv:2307.01694"},{"issue":"2","key":"4173_CR20","doi-asserted-by":"publisher","first-page":"2353","DOI":"10.1109\/TNNLS.2024.3355393","volume":"36","author":"Y Hu","year":"2025","unstructured":"Hu, Y., Deng, L., Wu, Y., Yao, M., Li, G.: Advancing spiking neural networks toward deep residual learning. IEEE Trans Neural Netw Learn Syst 36(2), 2353\u20132367 (2025). https:\/\/doi.org\/10.1109\/TNNLS.2024.3355393","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"4173_CR21","unstructured":"Zhou, C., Yu, L., Zhou, Z., Zhang, H., Ma, Z., Zhou, H., Tian, Y.: Spikingformer: Spike-driven residual learning for transformer-based spiking neural network. ArXiv arXiv:2304.11954 (2023)"},{"key":"4173_CR22","doi-asserted-by":"crossref","unstructured":"Shi, X., Hao, Z., Yu, Z.: SpikingResformer: bridging ResNet and vision transformer in spiking neural networks (2024). arXiv:2403.14302","DOI":"10.1109\/CVPR52733.2024.00536"},{"key":"4173_CR23","unstructured":"Zhou, C., Zhang, H., Zhou, Z., Yu, L., Huang, L., Fan, X., Yuan, L., Ma, Z., Zhou, H., Tian, Y.: QKFormer: hierarchical spiking transformer using Q-K attention (2024). arXiv:2403.16552"},{"key":"4173_CR24","unstructured":"Yao, M., Hu, J., Hu, T., Xu, Y., Zhou, Z., Tian, Y., Xu, B., Li, G.: Spike-driven transformer V2: meta spiking neural network architecture inspiring the design of next-generation neuromorphic chips (2024). arXiv:2404.03663"},{"key":"4173_CR25","doi-asserted-by":"crossref","unstructured":"Fang, H., Shrestha, A., Zhao, Z., Qiu, Q.: Exploiting neuron and synapse filter dynamics in spatial temporal learning of deep spiking neural network. In: International Joint Conference on Artificial Intelligence (2020). https:\/\/api.semanticscholar.org\/CorpusID:220484153","DOI":"10.24963\/ijcai.2020\/388"},{"key":"4173_CR26","unstructured":"Zhao, D., Shen, G., Dong, Y., Li, Y., Zeng, Y.: Improving stability and performance of spiking neural networks through enhancing temporal consistency. ArXiv arXiv:2305.14174 (2023)"},{"key":"4173_CR27","doi-asserted-by":"crossref","unstructured":"Zhang, T., Yu, K., Zhong, X., Wang, H., Xu, Q., Zhang, Q.: STAA-SNN: spatial-temporal attention aggregator for spiking neural networks (2025). arXiv:2503.02689","DOI":"10.1109\/CVPR52734.2025.01303"},{"key":"4173_CR28","doi-asserted-by":"publisher","unstructured":"Zhou, Z., Niu, J., Zhang, Y., Yuan, L., Zhu, Y.: Spiking transformer with spatial-temporal spiking self-attention. In: ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1\u20135 (2025). https:\/\/doi.org\/10.1109\/ICASSP49660.2025.10890026","DOI":"10.1109\/ICASSP49660.2025.10890026"},{"key":"4173_CR29","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.111094","volume":"159","author":"D Zhao","year":"2025","unstructured":"Zhao, D., Shen, G., Dong, Y., Li, Y., Zeng, Y.: Improving stability and performance of spiking neural networks through enhancing temporal consistency. Pattern Recogn. 159, 111094 (2025). https:\/\/doi.org\/10.1016\/j.patcog.2024.111094","journal-title":"Pattern Recogn."},{"key":"4173_CR30","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.128268","volume":"602","author":"S Gao","year":"2024","unstructured":"Gao, S., Fan, X., Deng, X., Hong, Z., Zhou, H., Zhu, Z.: Te-spikformer:temporal-enhanced spiking neural network with transformer. Neurocomputing 602, 128268 (2024). https:\/\/doi.org\/10.1016\/j.neucom.2024.128268","journal-title":"Neurocomputing"},{"key":"4173_CR31","doi-asserted-by":"crossref","unstructured":"Liu, Y., Xiao, S., Li, B., Yu, Z.: SparseSpikformer: a co-design framework for token and weight pruning in spiking transformer (2023). arXiv:2311.08806","DOI":"10.1109\/ICASSP48485.2024.10446631"},{"key":"4173_CR32","doi-asserted-by":"crossref","unstructured":"Ding, X., Guo, Y., Ding, G., Han, J.: ACNet: Strengthening the kernel skeletons for powerful CNN via asymmetric convolution blocks (2019). arXiv:1908.03930","DOI":"10.1109\/ICCV.2019.00200"},{"key":"4173_CR33","doi-asserted-by":"publisher","unstructured":"Ding, X., Zhang, X., Ma, N., Han, J., Ding, G., Sun, J.: Repvgg: Making vgg-style convnets great again. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 13728\u201313737 (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.01352","DOI":"10.1109\/CVPR46437.2021.01352"},{"key":"4173_CR34","unstructured":"Chen, G., Peng, P., Li, G., Tian, Y.: Training full spike neural networks via auxiliary accumulation pathway (2023). arXiv:2301.11929"},{"key":"4173_CR35","doi-asserted-by":"publisher","unstructured":"Kundu, S., Pedram, M., Beerel, P.A.: Hire-snn: Harnessing the inherent robustness of energy-efficient deep spiking neural networks by training with crafted input noise. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 5189\u20135198 (2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.00516","DOI":"10.1109\/ICCV48922.2021.00516"},{"key":"4173_CR36","doi-asserted-by":"publisher","unstructured":"Horowitz, M.: 1.1 computing\u2019s energy problem (and what we can do about it). In: 2014 IEEE International Solid-State Circuits Conference Digest of Technical Papers (ISSCC), pp. 10\u201314 (2014). https:\/\/doi.org\/10.1109\/ISSCC.2014.6757323","DOI":"10.1109\/ISSCC.2014.6757323"},{"key":"4173_CR37","doi-asserted-by":"publisher","unstructured":"Kundu, S., Datta, G., Pedram, M., Beerel, P.A.: Spike-thrift: Towards energy-efficient deep spiking neural networks by limiting spiking activity via attention-guided compression. In: 2021 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 3952\u20133961 (2021). https:\/\/doi.org\/10.1109\/WACV48630.2021.00400","DOI":"10.1109\/WACV48630.2021.00400"},{"key":"4173_CR38","doi-asserted-by":"crossref","unstructured":"Yin, B., Corradi, F., Bohte, S.M.: Accurate and efficient time-domain classification with adaptive spiking recurrent neural networks (2021). arXiv:2103.12593","DOI":"10.1101\/2021.03.22.436372"},{"key":"4173_CR39","doi-asserted-by":"publisher","unstructured":"Panda, P., Aketi, S.A., Roy, K.: Toward scalable, efficient, and accurate deep spiking neural networks with backward residual connections, stochastic softmax, and hybridization. Frontiers in Neuroscience Volume 14 - 2020 (2020) https:\/\/doi.org\/10.3389\/fnins.2020.00653","DOI":"10.3389\/fnins.2020.00653"},{"issue":"8","key":"4173_CR40","doi-asserted-by":"publisher","first-page":"9393","DOI":"10.1109\/TPAMI.2023.3241201","volume":"45","author":"M Yao","year":"2023","unstructured":"Yao, M., Zhao, G., Zhang, H., Hu, Y., Deng, L., Tian, Y., Xu, B., Li, G.: Attention spiking neural networks. IEEE Trans. Pattern Anal. Mach. Intell. 45(8), 9393\u20139410 (2023). https:\/\/doi.org\/10.1109\/TPAMI.2023.3241201","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"3","key":"4173_CR41","doi-asserted-by":"publisher","first-page":"5112","DOI":"10.1109\/TNNLS.2024.3377717","volume":"36","author":"R-J Zhu","year":"2025","unstructured":"Zhu, R.-J., Zhang, M., Zhao, Q., Deng, H., Duan, Y., Deng, L.-J.: Tcja-snn: temporal-channel joint attention for spiking neural networks. IEEE Trans Neural Netw Learn Syst 36(3), 5112\u20135125 (2025). https:\/\/doi.org\/10.1109\/TNNLS.2024.3377717","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"4173_CR42","unstructured":"Deng, S., Li, Y., Zhang, S., Gu, S.: Temporal efficient training of spiking neural network via gradient re-weighting (2022). arXiv:2202.11946"},{"key":"4173_CR43","unstructured":"Zhao, D., Shen, G., Dong, Y., Li, Y., Zeng, Y.: Improving stability and performance of spiking neural networks through enhancing temporal consistency (2023). arXiv:2305.14174"},{"key":"4173_CR44","unstructured":"Zhang, H., Zhang, Y.: Memory-efficient reversible spiking neural networks (2023). arXiv:2312.07922"},{"key":"4173_CR45","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2023.1229951","author":"H Zhang","year":"2023","unstructured":"Zhang, H., Li, Y., He, B., Fan, X., Wang, Y., Zhang, Y.: Direct training high-performance spiking neural networks for object recognition and detection. Front. Neurosci. (2023). https:\/\/doi.org\/10.3389\/fnins.2023.1229951","journal-title":"Front. Neurosci."},{"key":"4173_CR46","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126485","volume":"550","author":"C Xu","year":"2023","unstructured":"Xu, C., Liu, Y., Yang, Y.: Ultra-low latency spiking neural networks with spatio-temporal compression and synaptic convolutional block. Neurocomputing 550, 126485 (2023). https:\/\/doi.org\/10.1016\/j.neucom.2023.126485","journal-title":"Neurocomputing"},{"key":"4173_CR47","doi-asserted-by":"crossref","unstructured":"Kim, M., Kim, M., Yang, X.: DTA: Dual temporal-channel-wise attention for spiking neural networks (2025). arXiv:2503.10052","DOI":"10.1109\/WACV61041.2025.00939"},{"issue":"8","key":"4173_CR48","doi-asserted-by":"publisher","first-page":"5200","DOI":"10.1109\/TNNLS.2021.3119238","volume":"34","author":"Y Hu","year":"2023","unstructured":"Hu, Y., Tang, H., Pan, G.: Spiking deep residual networks. IEEE Trans Neural Netw Learn Syst 34(8), 5200\u20135205 (2023). https:\/\/doi.org\/10.1109\/TNNLS.2021.3119238","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"4173_CR49","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition (2015). arXiv:1512.03385","DOI":"10.1109\/CVPR.2016.90"},{"key":"4173_CR50","unstructured":"Fang, W., Yu, Z., Chen, Y., Huang, T., Masquelier, T., Tian, Y.: Deep residual learning in spiking neural networks. In: Neural Information Processing Systems (2021). https:\/\/api.semanticscholar.org\/CorpusID:235359262"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-025-04173-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-025-04173-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-025-04173-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T13:14:21Z","timestamp":1763644461000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-025-04173-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,9]]},"references-count":50,"journal-issue":{"issue":"15","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["4173"],"URL":"https:\/\/doi.org\/10.1007\/s00371-025-04173-4","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"type":"print","value":"0178-2789"},{"type":"electronic","value":"1432-2315"}],"subject":[],"published":{"date-parts":[[2025,9,9]]},"assertion":[{"value":"16 June 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 August 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 September 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}