{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T20:06:13Z","timestamp":1782763573953,"version":"3.54.5"},"reference-count":108,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T00:00:00Z","timestamp":1773014400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T00:00:00Z","timestamp":1773014400000},"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":["Int J Comput Vis"],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1007\/s11263-026-02769-4","type":"journal-article","created":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T17:33:36Z","timestamp":1773077616000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Event Stream based Human Action Recognition: A High-Definition Benchmark Dataset and Algorithms"],"prefix":"10.1007","volume":"134","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6117-6745","authenticated-orcid":false,"given":"Xiao","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shiao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pengpeng","family":"Shao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lin","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yonghong","family":"Tian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,3,9]]},"reference":[{"key":"2769_CR1","doi-asserted-by":"crossref","unstructured":"Ahmad, T., Jin, L., Zhang, X., Lin, L., & Tang, G. (2021). Graph convolutional neural network for action recognition: A comprehensive survey. IEEE Transactions on Artificial Intelligence,","DOI":"10.1109\/TAI.2021.3076974"},{"key":"2769_CR2","doi-asserted-by":"crossref","unstructured":"Amir, A., Taba, B., Berg, D., Melano, T., McKinstry, J., Di\u00a0Nolfo, C., Nayak, T., Andreopoulos, A., Garreau, G., Mendoza, M. et al. (2017). A low power, fully event-based gesture recognition system. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7243\u20137252 .","DOI":"10.1109\/CVPR.2017.781"},{"key":"2769_CR3","doi-asserted-by":"crossref","unstructured":"Baldwin, R., Liu, R., Almatrafi, M.M., Asari, V.K., & Hirakawa, K. (2022). Time-ordered recent event (tore) volumes for event cameras. IEEE Transactions on Pattern Analysis and Machine Intelligence .","DOI":"10.1109\/TPAMI.2022.3172212"},{"key":"2769_CR4","doi-asserted-by":"crossref","unstructured":"Becattini, F., Cultrera, L., Berlincioni, L., Ferrari, C., Leonardo, A., & Del\u00a0Bimbo, A. (2024). Neuromorphic facial analysis with cross-modal supervision. In: European Conference on Computer Vision, pp. 205\u2013223 Springer.","DOI":"10.1007\/978-3-031-92460-6_13"},{"key":"2769_CR5","unstructured":"Bertasius, G., Wang, H., & Torresani, L. (2021). Is space-time attention all you need for video understanding? In: ICML, 2 4 ."},{"key":"2769_CR6","doi-asserted-by":"crossref","unstructured":"Bi, Y., Chadha, A., Abbas, A., Bourtsoulatze, E., & Andreopoulos, Y. (2019). Graph-based object classification for neuromorphic vision sensing. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 491\u2013501 .","DOI":"10.1109\/ICCV.2019.00058"},{"key":"2769_CR7","doi-asserted-by":"publisher","first-page":"9084","DOI":"10.1109\/TIP.2020.3023597","volume":"29","author":"Y Bi","year":"2020","unstructured":"Bi, Y., Chadha, A., Abbas, A., Bourtsoulatze, E., & Andreopoulos, Y. (2020). Graph-based spatio-temporal feature learning for neuromorphic vision sensing. IEEE Transactions on Image Processing, 29, 9084\u20139098.","journal-title":"IEEE Transactions on Image Processing"},{"key":"2769_CR8","doi-asserted-by":"crossref","unstructured":"Cannici, M., Plizzari, C., Planamente, M., Ciccone, M., Bottino, A., Caputo, B., & Matteucci, M. (2021). N-rod: A neuromorphic dataset for synthetic-to-real domain adaptation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1342\u20131347 .","DOI":"10.1109\/CVPRW53098.2021.00148"},{"key":"2769_CR9","doi-asserted-by":"crossref","unstructured":"Chen, S., Guo, M. (2019). Live demonstration: Celex-v: a 1m pixel multi-mode event-based sensor. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 1682\u20131683 IEEE.","DOI":"10.1109\/CVPRW.2019.00214"},{"key":"2769_CR10","doi-asserted-by":"crossref","unstructured":"Chen, L., Li, D., Wang, X., Shao, P., Zhang, W., Wang, Y., Tian, Y., & Tang, J. (2024). Retain, Blend, and Exchange: A Quality-aware Spatial-Stereo Fusion Approach for Event Stream Recognition .","DOI":"10.1109\/TMM.2025.3607771"},{"key":"2769_CR11","doi-asserted-by":"crossref","unstructured":"Chen, L., Li, D., Wang, X., Shao, P., Zhang, W., Wang, Y., Tian, Y., & Tang, J. (2024). Retain, blend, and exchange: A quality-aware spatial-stereo fusion approach for event stream recognition. arXiv preprint arXiv:2406.18845 .","DOI":"10.1109\/TMM.2025.3607771"},{"key":"2769_CR12","doi-asserted-by":"crossref","unstructured":"Chen, J., Yang, Y., Deng, S., Teng, D., & Pan, L. (2024). Spikmamba: When snn meets mamba in event-based human action recognition. In: Proceedings of the 6th ACM International Conference on Multimedia in Asia, pp. 1\u20138 .","DOI":"10.1145\/3696409.3700204"},{"key":"2769_CR13","doi-asserted-by":"crossref","unstructured":"Chen, T., Yu, H., Yang, Z., Li, Z., Sun, W., & Chen, C. (2024). Ost: Refining text knowledge with optimal spatio-temporal descriptor for general video recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18888\u201318898 .","DOI":"10.1109\/CVPR52733.2024.01787"},{"key":"2769_CR14","doi-asserted-by":"crossref","unstructured":"Diehl, P.U., Neil, D., Binas, J., Cook, M., Liu, S.-C., & Pfeiffer, M. (2015). Fast-classifying, high-accuracy spiking deep networks through weight and threshold balancing. In: 2015 International Joint Conference on Neural Networks (IJCNN), pp. 1\u20138 ieee.","DOI":"10.1109\/IJCNN.2015.7280696"},{"key":"2769_CR15","doi-asserted-by":"crossref","unstructured":"Dong, Y., Li, Y., Zhao, D., Shen, G., & Zeng, Y. (2024). Bullying10k: a large-scale neuromorphic dataset towards privacy-preserving bullying recognition. Advances in Neural Information Processing Systems 36","DOI":"10.52202\/075280-0093"},{"key":"2769_CR16","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S. et al.: (2020).An image is worth 16x16 words: Transformers for image recognition at scale. In: International Conference on Learning Representations ."},{"key":"2769_CR17","unstructured":"Duan, Y., Wang, W., Chen, Z., Zhu, X., Lu, L., Lu, T., Qiao, Y., Li, H., Dai, J., & Wang, W. (2024). Vision-rwkv: Efficient and scalable visual perception with rwkv-like architectures. arXiv preprint arXiv:2403.02308 ."},{"key":"2769_CR18","doi-asserted-by":"crossref","unstructured":"Fang, H., Shrestha, A., Zhao, Z., & Qiu, Q. (2021). Exploiting neuron and synapse filter dynamics in spatial temporal learning of deep spiking neural network. In: Proceedings of the Twenty-Ninth International Conference on International Joint Conferences on Artificial Intelligence, pp. 2799\u20132806 .","DOI":"10.24963\/ijcai.2020\/388"},{"key":"2769_CR19","unstructured":"Fang, W., Yu, Z., Chen, Y., Huang, T., Masquelier, T., & Tian, Y. (2021). Deep residual learning in spiking neural networks. NeurIPS ."},{"key":"2769_CR20","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: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00266"},{"key":"2769_CR21","first-page":"21056","volume":"34","author":"W Fang","year":"2021","unstructured":"Fang, W., Yu, Z., Chen, Y., Huang, T., Masquelier, T., & Tian, Y. (2021). Deep residual learning in spiking neural networks. Advances in Neural Information Processing Systems, 34, 21056\u201321069.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2769_CR22","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C. (2020). X3d: Expanding architectures for efficient video recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 203\u2013213 .","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"2769_CR23","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., & He, K. (2019). Slowfast networks for video recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6202\u20136211 .","DOI":"10.1109\/ICCV.2019.00630"},{"key":"2769_CR24","doi-asserted-by":"crossref","unstructured":"Finateu, T., Niwa, A., Matolin, D., Tsuchimoto, K., Mascheroni, A., Reynaud, E., Mostafalu, P., Brady, F., Chotard, L., LeGoff, F., et al. (2020). 5.10 a 1280$$\\times $$ 720 back-illuminated stacked temporal contrast event-based vision sensor with 4.86 $$\\mu $$m pixels, 1.066 geps readout, programmable event-rate controller and compressive data-formatting pipeline. In: 2020 IEEE International Solid-State Circuits Conference-(ISSCC), pp. 112\u2013114 IEEE.","DOI":"10.1109\/ISSCC19947.2020.9063149"},{"issue":"1","key":"2769_CR25","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1109\/TPAMI.2020.3008413","volume":"44","author":"G Gallego","year":"2020","unstructured":"Gallego, G., Delbr\u00fcck, T., Orchard, G., Bartolozzi, C., Taba, B., Censi, A., Leutenegger, S., Davison, A. J., Conradt, J., Daniilidis, K., et al. (2020). Event-based vision: A survey. IEEE transactions on pattern analysis and machine intelligence, 44(1), 154\u2013180.","journal-title":"IEEE transactions on pattern analysis and machine intelligence"},{"key":"2769_CR26","doi-asserted-by":"crossref","unstructured":"Gao, Y., Lu, J., Li, S., Li, Y., & Du, S. (2024). Hypergraph-based multi-view action recognition using event cameras. IEEE Transactions on Pattern Analysis and Machine Intelligence .","DOI":"10.1109\/TPAMI.2024.3382117"},{"key":"2769_CR27","doi-asserted-by":"crossref","unstructured":"Gao, Y., Lu, J., Li, S., Ma, N., Du, S., Li, Y., & Dai, Q. (2023). Action recognition and benchmark using event cameras. IEEE Transactions on Pattern Analysis and Machine Intelligence .","DOI":"10.1109\/TPAMI.2023.3300741"},{"key":"2769_CR28","doi-asserted-by":"crossref","unstructured":"Gehrig, D., Loquercio, A., Derpanis, K.G., & Scaramuzza, D. (2019). End-to-end learning of representations for asynchronous event-based data. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5633\u20135643 .","DOI":"10.1109\/ICCV.2019.00573"},{"key":"2769_CR29","unstructured":"Gehrig, D., Scaramuzza, D. (2022). Are high-resolution event cameras really needed? arXiv preprint arXiv:2203.14672 ."},{"key":"2769_CR30","unstructured":"Gu, A., Dao, T. (2023). Mamba: Linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.00752 ."},{"key":"2769_CR31","unstructured":"Gu, A., Goel, K., & Re, C. (2021). Efficiently modeling long sequences with structured state spaces. In: International Conference on Learning Representations ."},{"key":"2769_CR32","first-page":"572","volume":"34","author":"A Gu","year":"2021","unstructured":"Gu, A., Johnson, I., Goel, K., Saab, K., Dao, T., Rudra, A., & R\u00e9, C. (2021). Combining recurrent, convolutional, and continuous-time models with linear state space layers. Advances in neural information processing systems, 34, 572\u2013585.","journal-title":"Advances in neural information processing systems"},{"key":"2769_CR33","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 .","DOI":"10.1109\/CVPR.2016.90"},{"key":"2769_CR34","doi-asserted-by":"crossref","unstructured":"Huang, J., Wang, S., Wang, S., Wu, Z., Wang, X., & Jiang, B. (2024). Mamba-fetrack: Frame-event tracking via state space model. In: Chinese Conference on Pattern Recognition and Computer Vision (PRCV), pp. 3\u201318 Springer.","DOI":"10.1007\/978-981-97-8858-3_1"},{"key":"2769_CR35","doi-asserted-by":"crossref","unstructured":"Innocenti, S.U., Becattini, F., Pernici, F., & Del\u00a0Bimbo, A. (2021). Temporal binary representation for event-based action recognition. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 10426\u201310432 IEEE.","DOI":"10.1109\/ICPR48806.2021.9412991"},{"key":"2769_CR36","doi-asserted-by":"crossref","unstructured":"Islam, M.M., Bertasius, G. (2022). Long movie clip classification with state-space video models. In: European Conference on Computer Vision, pp. 87\u2013104 Springer.","DOI":"10.1007\/978-3-031-19833-5_6"},{"issue":"1","key":"2769_CR37","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1109\/TPAMI.2012.59","volume":"35","author":"S Ji","year":"2012","unstructured":"Ji, S., Xu, W., Yang, M., & Yu, K. (2012). 3d convolutional neural networks for human action recognition. IEEE transactions on pattern analysis and machine intelligence, 35(1), 221\u2013231.","journal-title":"IEEE transactions on pattern analysis and machine intelligence"},{"key":"2769_CR38","doi-asserted-by":"crossref","unstructured":"Kahatapitiya, K., Arnab, A., Nagrani, A., Ryoo, & M.S. (2024). Victr: Video-conditioned text representations for activity recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18547\u201318558 .","DOI":"10.1109\/CVPR52733.2024.01755"},{"key":"2769_CR39","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1115\/1.3662552","volume":"82D","author":"RE Kalman","year":"1960","unstructured":"Kalman, R. E. (1960). A new approach to linear filtering and prediction problems. Journal of Basic Engineering, 82D, 35\u201345.","journal-title":"Journal of Basic Engineering"},{"key":"2769_CR40","doi-asserted-by":"crossref","unstructured":"Kim, J., Bae, J., Park, G., Zhang, D., & Kim, Y. M. (2021). N-imagenet: Towards robust, fine-grained object recognition with event cameras. Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2146\u20132156.","DOI":"10.1109\/ICCV48922.2021.00215"},{"key":"2769_CR41","unstructured":"Kong, Y., Fu, Y. (2018). Human action recognition and prediction: A survey. arXiv preprint arXiv:1806.11230"},{"issue":"5","key":"2769_CR42","doi-asserted-by":"publisher","first-page":"1366","DOI":"10.1007\/s11263-022-01594-9","volume":"130","author":"Y Kong","year":"2022","unstructured":"Kong, Y., & Fu, Y. (2022). Human action recognition and prediction: A survey. International Journal of Computer Vision, 130(5), 1366\u20131401.","journal-title":"International Journal of Computer Vision"},{"key":"2769_CR43","doi-asserted-by":"crossref","unstructured":"Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., & Serre, T. (2011). Hmdb: a large video database for human motion recognition. In: 2011 International Conference on Computer Vision, pp. 2556\u20132563 IEEE.","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"2769_CR44","unstructured":"Li, Z., Asif, M.S., & Ma, Z. (2022). Event transformer. arXiv preprint arXiv:2204.05172 ."},{"key":"2769_CR45","unstructured":"Li, D., Jin, J., Zhang, Y., Zhong, Y., Wu, Y., Chen, L., Wang, X., & Luo, B. (2023). Semantic-aware frame-event fusion based pattern recognition via large vision-language models. arXiv preprint arXiv:2311.18592 ."},{"key":"2769_CR46","doi-asserted-by":"crossref","unstructured":"Li, K., Li, X., Wang, Y., He, Y., Wang, Y., Wang, L., & Qiao, Y. (2024). Videomamba: State space model for efficient video understanding. arXiv preprint arXiv:2403.06977 .","DOI":"10.1007\/978-3-031-73347-5_14"},{"key":"2769_CR47","doi-asserted-by":"crossref","unstructured":"Li, Y., Zhou, H., Yang, B., Zhang, Y., Cui, Z., Bao, H., & Zhang, G. (2021). Graph-based asynchronous event processing for rapid object recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 934\u2013943.","DOI":"10.1109\/ICCV48922.2021.00097"},{"issue":"5","key":"2769_CR48","doi-asserted-by":"publisher","first-page":"624","DOI":"10.1109\/LSP.2017.2678539","volume":"24","author":"C Li","year":"2017","unstructured":"Li, C., Hou, Y., Wang, P., & Li, W. (2017). Joint distance maps based action recognition with convolutional neural networks. IEEE Signal Processing Letters, 24(5), 624\u2013628.","journal-title":"IEEE Signal Processing Letters"},{"key":"2769_CR49","doi-asserted-by":"publisher","first-page":"309","DOI":"10.3389\/fnins.2017.00309","volume":"11","author":"H Li","year":"2017","unstructured":"Li, H., Liu, H., Ji, X., Li, G., & Shi, L. (2017). Cifar10-dvs: an event-stream dataset for object classification. Frontiers in neuroscience, 11, 309.","journal-title":"Frontiers in neuroscience"},{"key":"2769_CR50","doi-asserted-by":"crossref","unstructured":"Lin, Y., Ding, W., Qiang, S., Deng, L., & Li, G. (2021). Es-imagenet: A million event-stream classification dataset for spiking neural networks. Frontiers in neuroscience,1546.","DOI":"10.3389\/fnins.2021.726582"},{"key":"2769_CR51","unstructured":"Lin, J., Gan, C., & Han, S. (1811). Temporal shift module for efficient video understanding. arXiv preprint arXiv:1811.08383 ."},{"key":"2769_CR52","doi-asserted-by":"crossref","unstructured":"Lin, J., Gan, C., & Han, S. (2019). Tsm: Temporal shift module for efficient video understanding. In: Proceedings of the IEEE International Conference on Computer Vision .","DOI":"10.1109\/ICCV.2019.00718"},{"key":"2769_CR53","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2021.726582","volume":"15","author":"Y Lin","year":"2021","unstructured":"Lin, Y., Ding, W., Qiang, S., Deng, L., & Li, G. (2021). Es-imagenet: A million event-stream classification dataset for spiking neural networks. Frontiers in neuroscience, 15, Article 726582.","journal-title":"Frontiers in neuroscience"},{"key":"2769_CR54","doi-asserted-by":"crossref","unstructured":"Liu, Z., Ning, J., Cao, Y., Wei, Y., Zhang, Z., Lin, S., & Hu, H. (2022). Video swin transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3202\u20133211 .","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"2769_CR55","doi-asserted-by":"crossref","unstructured":"Liu, Z., Wang, L., Wu, W., Qian, C., & Lu, T. (2021). Tam: Temporal adaptive module for video recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13708\u201313718 .","DOI":"10.1109\/ICCV48922.2021.01345"},{"key":"2769_CR56","doi-asserted-by":"crossref","unstructured":"Liu, Q., Xing, D., Tang, H., Ma, D., & Pan, G. (2021). Event-based action recognition using motion information and spiking neural networks. In: IJCAI, pp. 1743\u20131749 .","DOI":"10.24963\/ijcai.2021\/240"},{"key":"2769_CR57","first-page":"103031","volume":"37","author":"Y Liu","year":"2024","unstructured":"Liu, Y., Tian, Y., Zhao, Y., Yu, H., Xie, L., Wang, Y., Ye, Q., Jiao, J., & Liu, Y. (2024). Vmamba: Visual state space model. Advances in neural information processing systems, 37, 103031\u2013103063.","journal-title":"Advances in neural information processing systems"},{"key":"2769_CR58","unstructured":"Lu, H., Salah, A.A., & Poppe, R. (2024). Videomambapro: A leap forward for mamba in video understanding. arXiv preprint arXiv:2406.19006 ."},{"key":"2769_CR59","doi-asserted-by":"crossref","unstructured":"Magrini, G., Becattini, F., Pala, P., Del\u00a0Bimbo, A., & Porta, A. (2024). Neuromorphic drone detection: an event-rgb multimodal approach. In: European Conference on Computer Vision, pp. 259\u2013275 Springer.","DOI":"10.1007\/978-3-031-92460-6_16"},{"key":"2769_CR60","doi-asserted-by":"crossref","unstructured":"Meng, Q., Xiao, M., Yan, S., Wang, Y., Lin, Z., & Luo, Z.-Q. (2022). Training high-performance low-latency spiking neural networks by differentiation on spike representation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12444\u201312453 .","DOI":"10.1109\/CVPR52688.2022.01212"},{"key":"2769_CR61","doi-asserted-by":"publisher","first-page":"38","DOI":"10.3389\/fnbot.2019.00038","volume":"13","author":"S Miao","year":"2019","unstructured":"Miao, S., Chen, G., Ning, X., Zi, Y., Ren, K., Bing, Z., & Knoll, A. (2019). Neuromorphic vision datasets for pedestrian detection, action recognition, and fall detection. Frontiers in neurorobotics, 13, 38.","journal-title":"Frontiers in neurorobotics"},{"key":"2769_CR62","first-page":"2846","volume":"35","author":"E Nguyen","year":"2022","unstructured":"Nguyen, E., Goel, K., Gu, A., Downs, G., Shah, P., Dao, T., Baccus, S., & R\u00e9, C. (2022). S4nd: Modeling images and videos as multidimensional signals with state spaces. Advances in neural information processing systems, 35, 2846\u20132861.","journal-title":"Advances in neural information processing systems"},{"key":"2769_CR63","doi-asserted-by":"publisher","first-page":"437","DOI":"10.3389\/fnins.2015.00437","volume":"9","author":"G Orchard","year":"2015","unstructured":"Orchard, G., Jayawant, A., Cohen, G. K., & Thakor, N. (2015). Converting static image datasets to spiking neuromorphic datasets using saccades. Frontiers in neuroscience, 9, 437.","journal-title":"Frontiers in neuroscience"},{"key":"2769_CR64","first-page":"8026","volume":"32","author":"A Paszke","year":"2019","unstructured":"Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., et al. (2019). Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems, 32, 8026\u20138037.","journal-title":"Advances in neural information processing systems"},{"key":"2769_CR65","doi-asserted-by":"crossref","unstructured":"Peng, Y., Zhang, Y., Xiong, Z., Sun, X., & Wu, F. (2023). Get: Group event transformer for event-based vision. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6038\u20136048 .","DOI":"10.1109\/ICCV51070.2023.00555"},{"key":"2769_CR66","first-page":"11795","volume":"34","author":"N Perez-Nieves","year":"2021","unstructured":"Perez-Nieves, N., & Goodman, D. (2021). Sparse spiking gradient descent. Advances in Neural Information Processing Systems, 34, 11795\u201311808.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2769_CR67","first-page":"16639","volume":"33","author":"E Perot","year":"2020","unstructured":"Perot, E., De Tournemire, P., Nitti, D., Masci, J., & Sironi, A. (2020). Learning to detect objects with a 1 megapixel event camera. Advances in Neural Information Processing Systems, 33, 16639\u201316652.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2769_CR68","doi-asserted-by":"crossref","unstructured":"Plizzari, C., Planamente, M., Goletto, G., Cannici, M., Gusso, E., Matteucci, M., & Caputo, B. (2022). E2 (go) motion: Motion augmented event stream for egocentric action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19935\u201319947 .","DOI":"10.1109\/CVPR52688.2022.01931"},{"key":"2769_CR69","unstructured":"Qi, C.R., Su, H., Mo, K., & Guibas, L.J. (2017). Pointnet: Deep learning on point sets for 3d classification and segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 652\u2013660 ."},{"key":"2769_CR70","doi-asserted-by":"crossref","unstructured":"Ruan, C., Guo, R., Gong, Z., Xu, J., Yang, W., & Chen, X. (2025). Pre-mamba: A 4d state space model for ultra-high-frequent event camera deraining. arXiv preprint arXiv:2505.05307 .","DOI":"10.1109\/ICCV51701.2025.00857"},{"key":"2769_CR71","doi-asserted-by":"crossref","unstructured":"Schaefer, S., Gehrig, D., & Scaramuzza, D. (2022). Aegnn: Asynchronous event-based graph neural networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12371\u201312381 .","DOI":"10.1109\/CVPR52688.2022.01205"},{"key":"2769_CR72","doi-asserted-by":"crossref","unstructured":"Serrano-Gotarredona, T., Linares-Barranco, B. (2015). Poker-dvs and mnist-dvs. their history, how they were made, and other details. Frontiers in neuroscience 9, 481","DOI":"10.3389\/fnins.2015.00481"},{"key":"2769_CR73","unstructured":"Shi, X., Chen, Z., Wang, H., Yeung, D.-Y., Wong, W.-K., & Woo, W.-c. (2015). Convolutional lstm network: A machine learning approach for precipitation nowcasting. Advances in neural information processing systems 28 ."},{"key":"2769_CR74","doi-asserted-by":"crossref","unstructured":"Sironi, A., Brambilla, M., Bourdis, N., Lagorce, X., & Benosman, R. (2018). Hats: Histograms of averaged time surfaces for robust event-based object classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1731\u20131740 .","DOI":"10.1109\/CVPR.2018.00186"},{"key":"2769_CR75","doi-asserted-by":"crossref","unstructured":"Soo Kim, T., Reiter, A. (2017). Interpretable 3d human action analysis with temporal convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 20\u201328 .","DOI":"10.1109\/CVPRW.2017.207"},{"issue":"11","key":"2769_CR76","first-page":"1","volume":"2","author":"K Soomro","year":"2012","unstructured":"Soomro, K., Zamir, A. R., & Shah, M. (2012). A dataset of 101 human action classes from videos in the wild. Center for Research in Computer Vision, 2(11), 1\u20137.","journal-title":"Center for Research in Computer Vision"},{"issue":"9","key":"2769_CR77","doi-asserted-by":"publisher","first-page":"10913","DOI":"10.1109\/TPAMI.2023.3268134","volume":"45","author":"S Sudhakaran","year":"2023","unstructured":"Sudhakaran, S., Escalera, S., & Lanz, O. (2023). Gate-shift-fuse for video action recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(9), 10913\u201310928.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2769_CR78","doi-asserted-by":"crossref","unstructured":"Sun, K., Xiao, B., Liu, D., & Wang, J. (2019). Deep high-resolution representation learning for human pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5693\u20135703 .","DOI":"10.1109\/CVPR.2019.00584"},{"issue":"3","key":"2769_CR79","first-page":"3200","volume":"45","author":"Z Sun","year":"2022","unstructured":"Sun, Z., Ke, Q., Rahmani, H., Bennamoun, M., Wang, G., & Liu, J. (2022). Human action recognition from various data modalities: A review. IEEE transactions on pattern analysis and machine intelligence, 45(3), 3200\u20133225.","journal-title":"IEEE transactions on pattern analysis and machine intelligence"},{"key":"2769_CR80","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., & Paluri, M. (2015). Learning spatiotemporal features with 3d convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4489\u20134497 .","DOI":"10.1109\/ICCV.2015.510"},{"key":"2769_CR81","unstructured":"Tran, D., Ray, J., Shou, Z., Chang, S.-F., & Paluri, M. (2017). Convnet architecture search for spatiotemporal feature learning. arXiv preprint arXiv:1708.05038 ."},{"key":"2769_CR82","doi-asserted-by":"crossref","unstructured":"Tran, D., Wang, H., Torresani, L., Ray, J., LeCun, Y., & Paluri, M. (2018). A closer look at spatiotemporal convolutions for action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6450\u20136459 .","DOI":"10.1109\/CVPR.2018.00675"},{"key":"2769_CR83","first-page":"4712","volume":"34","author":"S Vemprala","year":"2021","unstructured":"Vemprala, S., Mian, S., & Kapoor, A. (2021). Representation learning for event-based visuomotor policies. Advances in Neural Information Processing Systems, 34, 4712\u20134724.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2769_CR84","doi-asserted-by":"crossref","unstructured":"Wang, Y., Du, B., Shen, Y., Wu, K., Zhao, G., Sun, J., & Wen, H. (2019). Ev-gait: Event-based robust gait recognition using dynamic vision sensors. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6358\u20136367 .","DOI":"10.1109\/CVPR.2019.00652"},{"key":"2769_CR85","unstructured":"Wang, S., Huang, J., Ma, Q., Gao, J., Xu, C., Wang, X., Chen, L., & Jiang, B. (2025). Mamba-fetrack v2: Revisiting state space model for frame-event based visual object tracking. arXiv preprint arXiv:2506.23783 ."},{"key":"2769_CR86","doi-asserted-by":"crossref","unstructured":"Wang, X., Jin, Y., Wu, W., Zhang, W., Zhu, L., Jiang, B., & Tian, Y. (2025). Object detection using event camera: A moe heat conduction based detector and a new benchmark dataset. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 29321\u201329330 .","DOI":"10.1109\/CVPR52734.2025.02730"},{"key":"2769_CR87","doi-asserted-by":"crossref","unstructured":"Wang, P., Li, Z., Hou, Y., & Li, W. (2016). Action recognition based on joint trajectory maps using convolutional neural networks. In: Proceedings of the 24th ACM International Conference on Multimedia, pp. 102\u2013106 .","DOI":"10.1145\/2964284.2967191"},{"key":"2769_CR88","doi-asserted-by":"crossref","unstructured":"Wang, Z., She, Q., & Smolic, A. (2021). Action-net: Multipath excitation for action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13214\u201313223 .","DOI":"10.1109\/CVPR46437.2021.01301"},{"key":"2769_CR89","doi-asserted-by":"crossref","unstructured":"Wang, X., Wang, S., Tang, C., Zhu, L., Jiang, B., Tian, Y., & Tang, J. (2024). Event stream-based visual object tracking: A high-resolution benchmark dataset and a novel baseline. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19248\u201319257 .","DOI":"10.1109\/CVPR52733.2024.01821"},{"key":"2769_CR90","unstructured":"Wang, X., Wu, Z., Rong, Y., Zhu, L., Jiang, B., Tang, J., & Tian, Y. (2023). Sstformer: bridging spiking neural network and memory support transformer for frame-event based recognition. arXiv preprint arXiv:2308.04369"},{"key":"2769_CR91","doi-asserted-by":"crossref","unstructured":"Wang, Q., Xu, Z., Lin, Y., Ye, J., Li, H., Zhu, G., Shah, S.A.A., Bennamoun, M., & Zhang, L. (2024). Dailydvs-200: A comprehensive benchmark dataset for event-based action recognition. arXiv preprint arXiv:2407.05106 .","DOI":"10.1007\/978-3-031-72907-2_4"},{"key":"2769_CR92","doi-asserted-by":"crossref","unstructured":"Wang, Y., Zhang, X., Shen, Y., Du, B., Zhao, G., Lizhen, L.C.C., & Wen, H. (2021). Event-stream representation for human gaits identification using deep neural networks. IEEE Transactions on Pattern Analysis and Machine Intelligence .","DOI":"10.1109\/TPAMI.2021.3054886"},{"key":"2769_CR93","doi-asserted-by":"crossref","unstructured":"Wang, Q., Zhang, Y., Yuan, J., & Lu, Y. (2019). Space-time event clouds for gesture recognition: From rgb cameras to event cameras. In: 2019 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 1826\u20131835 IEEE.","DOI":"10.1109\/WACV.2019.00199"},{"key":"2769_CR94","doi-asserted-by":"crossref","unstructured":"Wang, G., Zhao, P., Shi, Y., Zhao, C., & Yang, S. (2024). Generative model-based feature knowledge distillation for action recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, pp. 15474\u201315482 .","DOI":"10.1609\/aaai.v38i14.29473"},{"key":"2769_CR95","doi-asserted-by":"publisher","first-page":"5615","DOI":"10.1609\/aaai.v38i6.28372","volume":"38","author":"X Wang","year":"2024","unstructured":"Wang, X., Wu, Z., Jiang, B., Bao, Z., Zhu, L., Li, G., Wang, Y., & Tian, Y. (2024). Hardvs: Revisiting human activity recognition with dynamic vision sensors. Proceedings of the AAAI Conference on Artificial Intelligence, 38, 5615\u20135623.","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"2769_CR96","doi-asserted-by":"crossref","unstructured":"Xiao, Z., Wang, X. (2025). Event-based video super-resolution via state space models. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 12564\u201312574 .","DOI":"10.1109\/CVPR52734.2025.01172"},{"key":"2769_CR97","doi-asserted-by":"crossref","unstructured":"Xiao, B., Wu, H., & Wei, Y. (2018). Simple baselines for human pose estimation and tracking. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 466\u2013481 .","DOI":"10.1007\/978-3-030-01231-1_29"},{"issue":"2","key":"2769_CR98","doi-asserted-by":"publisher","first-page":"1976","DOI":"10.1109\/LRA.2022.3140819","volume":"7","author":"B Xie","year":"2022","unstructured":"Xie, B., Deng, Y., Shao, Z., Liu, H., & Li, Y. (2022). Vmv-gcn: Volumetric multi-view based graph cnn for event stream classification. IEEE Robotics and Automation Letters, 7(2), 1976\u20131983.","journal-title":"IEEE Robotics and Automation Letters"},{"key":"2769_CR99","doi-asserted-by":"crossref","unstructured":"Xing, Z., Dai, Q., Hu, H., Chen, J., Wu, Z., Jiang, & Y.-G. (2023). Svformer: Semi-supervised video transformer for action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18816\u201318826 .","DOI":"10.1109\/CVPR52729.2023.01804"},{"key":"2769_CR100","doi-asserted-by":"publisher","first-page":"9229","DOI":"10.1609\/aaai.v39i9.32999","volume":"39","author":"N Yang","year":"2025","unstructured":"Yang, N., Wang, Y., Liu, Z., Li, M., An, Y., & Zhao, X. (2025). Smamba: Sparse mamba for event-based object detection. Proceedings of the AAAI Conference on Artificial Intelligence, 39, 9229\u20139237.","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"2769_CR101","unstructured":"Yao, M., Hu, J., Zhou, Z., Yuan, L., Tian, Y., Xu, B., & Li, G. (2024). Spike-driven transformer. Advances in neural information processing systems 36 ."},{"key":"2769_CR102","doi-asserted-by":"crossref","unstructured":"Zhang, H.-B., Zhang, Y.-X., Zhong, B., Lei, Q., Yang, L., Du, J.-X., & Chen, D.-S. (2019). A comprehensive survey of vision-based human action recognition methods. Sensors,19(5), 1005.","DOI":"10.3390\/s19051005"},{"key":"2769_CR103","doi-asserted-by":"crossref","unstructured":"Zheng, Y., Huang, H., Wang, X., Yan, X., & Xu, L. (2024). Spatio-temporal fusion for human action recognition via joint trajectory graph. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, pp. 7579\u20137587 .","DOI":"10.1609\/aaai.v38i7.28590"},{"key":"2769_CR104","doi-asserted-by":"crossref","unstructured":"Zhou, J., Zheng, X., Lyu, Y., & Wang, L. (2024). Exact: Language-guided conceptual reasoning and uncertainty estimation for event-based action recognition and more. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18633\u201318643 .","DOI":"10.1109\/CVPR52733.2024.01763"},{"key":"2769_CR105","unstructured":"Zhou, Z., Zhu, Y., He, C., Wang, Y., Yan, S., Tian, Y., & Yuan, L. (2022). Spikformer: When spiking neural network meets transformer. arXiv preprint arXiv:2209.15425 ."},{"key":"2769_CR106","unstructured":"Zhu, L., Liao, B., Zhang, Q., Wang, X., Liu, W., & Wang, X. (2024). Vision mamba: Efficient visual representation learning with bidirectional state space model. arXiv preprint arXiv:2401.09417 ."},{"key":"2769_CR107","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1016\/j.imavis.2016.06.007","volume":"55","author":"F Zhu","year":"2016","unstructured":"Zhu, F., Shao, L., Xie, J., & Fang, Y. (2016). From handcrafted to learned representations for human action recognition: A survey. Image and Vision Computing, 55, 42\u201352.","journal-title":"Image and Vision Computing"},{"key":"2769_CR108","doi-asserted-by":"crossref","unstructured":"Zubic, N., Gehrig, M., & Scaramuzza, D. (2024). State space models for event cameras. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5819\u20135828 .","DOI":"10.1109\/CVPR52733.2024.00556"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-026-02769-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-026-02769-4","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-026-02769-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T07:32:38Z","timestamp":1779348758000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-026-02769-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,9]]},"references-count":108,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,4]]}},"alternative-id":["2769"],"URL":"https:\/\/doi.org\/10.1007\/s11263-026-02769-4","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,9]]},"assertion":[{"value":"23 December 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 January 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 March 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"181"}}