{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T15:00:16Z","timestamp":1784041216646,"version":"3.55.0"},"reference-count":81,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T00:00:00Z","timestamp":1732579200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Comput. Neurosci."],"abstract":"<jats:p>Event-based cameras are suitable for human action recognition (HAR) by providing movement perception with highly dynamic range, high temporal resolution, high power efficiency and low latency. Spike Neural Networks (SNNs) are naturally suited to deal with the asynchronous and sparse data from the event cameras due to their spike-based event-driven paradigm, with less power consumption compared to artificial neural networks. In this paper, we propose two end-to-end SNNs, namely Spike-HAR and Spike-HAR++, to introduce spiking transformer into event-based HAR. Spike-HAR includes two novel blocks: a spike attention branch, which enables model to focus on regions with high spike rates, reducing the impact of noise to improve the accuracy, and a parallel spike transformer block with simplified spiking self-attention mechanism, increasing computational efficiency. To better extract crucial information from high-level features, we modify the architecture of the spike attention branch and extend it in Spike-HAR to a higher dimension, proposing Spike-HAR++ to further enhance classification performance. Comprehensive experiments were conducted on four HAR datasets: SL-Animals-DVS, N-LSA64, DVS128 Gesture and DailyAction-DVS, to demonstrate the superior performance of our proposed model. Additionally, the proposed Spike-HAR and Spike-HAR++ require only 0.03 and 0.06 mJ, respectively, to process a sequence of event frames, with model sizes of only 0.7 and 1.8 M. This efficiency positions it as a promising new SNN baseline for the HAR community. Code is available at <jats:ext-link>Spike-HAR++<\/jats:ext-link>.<\/jats:p>","DOI":"10.3389\/fncom.2024.1508297","type":"journal-article","created":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T04:25:17Z","timestamp":1732595117000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["Spike-HAR++: an energy-efficient and lightweight parallel spiking transformer for event-based human action recognition"],"prefix":"10.3389","volume":"18","author":[{"given":"Xinxu","family":"Lin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingxuan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2024,11,26]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2303.08774","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv"},{"key":"B2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/IPTA59101.2023.10320049","article-title":"\u201cVK-sits: a robust time-surface for fast event-based recognition,\u201d","volume-title":"2023 Twelfth International Conference on Image Processing Theory, Tools and Applications (IPTA)","author":"Acin","year":"2023"},{"key":"B3","first-page":"7243","article-title":"\u201cA low power, fully event-based gesture recognition system,\u201d","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"Amir","year":"2017"},{"key":"B4","doi-asserted-by":"publisher","first-page":"2519","DOI":"10.1109\/TPAMI.2022.3172212","article-title":"Time-ordered recent event (TORE) volumes for event cameras","volume":"45","author":"Baldwin","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2401.02274","article-title":"Shapeaug: occlusion augmentation for event camera data","author":"Bendig","year":"2024","journal-title":"arXiv"},{"key":"B6","doi-asserted-by":"publisher","first-page":"14315","DOI":"10.1109\/TNNLS.2023.3278265","article-title":"A spatial-channel-temporal-fused attention for spiking neural networks","volume":"35","author":"Cai","year":"2024","journal-title":"IEEE Trans. Neural Netw. Learn. Syst"},{"key":"B7","doi-asserted-by":"publisher","first-page":"136","DOI":"10.1007\/978-3-030-58565-5_9","article-title":"\u201cA differentiable recurrent surface for asynchronous event-based data,\u201d","author":"Cannici","year":"2020","journal-title":"Computer Vision"},{"key":"B8","unstructured":"CorporationI.\n          Intel stratix 10 tx device overview2023"},{"key":"B9","first-page":"1","article-title":"\u201cA time-surface enhancement model for event-based spatiotemporal feature extraction,\u201d","volume-title":"2024 International Joint Conference on Neural Networks (IJCNN)","author":"Ding","year":"2024"},{"key":"B10","doi-asserted-by":"publisher","first-page":"1084","DOI":"10.1109\/TSMC.2022.3192017","article-title":"Individual surveillance around parked aircraft at nighttime: thermal infrared vision-based human action recognition","volume":"53","author":"Ding","year":"2022","journal-title":"IEEE Trans. Syst. Man Cybern. Syst"},{"key":"B11","doi-asserted-by":"publisher","first-page":"eadi1480","DOI":"10.1126\/sciadv.adi1480","article-title":"Spikingjelly: an open-source machine learning infrastructure platform for spike-based intelligence","volume":"9","author":"Fang","year":"2023","journal-title":"Sci. Adv"},{"key":"B12","doi-asserted-by":"publisher","first-page":"21056","DOI":"10.48550\/arXiv.2102.04159","article-title":"Deep residual learning in spiking neural networks","volume":"34","author":"Fang","year":"","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"B13","first-page":"2661","article-title":"\u201cIncorporating learnable membrane time constant to enhance learning of spiking neural networks,\u201d","volume-title":"Proceedings of the IEEE\/CVF international conference on computer vision","author":"Fang","year":""},{"key":"B14","doi-asserted-by":"publisher","first-page":"14081","DOI":"10.1109\/TPAMI.2023.3300741","article-title":"Action recognition and benchmark using event cameras","volume":"45","author":"Gao","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1903.07067","article-title":"Spatiotemporal filtering for event-based action recognition","author":"Ghosh","year":"2019","journal-title":"arXiv"},{"key":"B16","doi-asserted-by":"publisher","first-page":"1521","DOI":"10.1109\/TCDS.2024.3380907","article-title":"Eventaugment: learning augmentation policies from asynchronous event-based data","volume":"16","author":"Gu","year":"2024","journal-title":"IEEE Trans. Cogn. Dev. Syst"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2106.05836","article-title":"Eventdrop: data augmentation for event-based learning","author":"Gu","year":"2021","journal-title":"arXiv"},{"key":"B18","doi-asserted-by":"publisher","first-page":"1077","DOI":"10.1109\/TCDS.2023.3327081","article-title":"Transformer-based spiking neural networks for multimodal audio-visual classification","volume":"16","author":"Guo","year":"2023","journal-title":"IEEE Trans. Cogn. Dev. Syst"},{"key":"B19","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1109\/TPAMI.2022.3152247","article-title":"A survey on vision transformer","volume":"45","author":"Han","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"B20","first-page":"770","article-title":"\u201cDeep residual learning for image recognition,\u201d","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"He","year":"2016"},{"key":"B21","first-page":"2529","article-title":"\u201cContinuous sign language recognition with correlation network,\u201d","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Hu","year":"2023"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3355393","article-title":"Advancing spiking neural networks toward deep residual learning","author":"Hu","year":"2024","journal-title":"IEEE Trans. Neural Netw. Learn. Syst"},{"key":"B23","doi-asserted-by":"crossref","first-page":"1312","DOI":"10.1109\/CVPRW53098.2021.00144","article-title":"\u201cv2e: From video frames to realistic dvs events,\u201d","volume-title":"2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","author":"Hu","year":"2021"},{"key":"B24","doi-asserted-by":"publisher","first-page":"5200","DOI":"10.1109\/TNNLS.2021.3119238","article-title":"Spiking deep residual networks","volume":"34","author":"Hu","year":"2023","journal-title":"IEEE Trans. Neural Netw. Learn. Syst"},{"key":"B25","doi-asserted-by":"crossref","first-page":"10426","DOI":"10.1109\/ICPR48806.2021.9412991","article-title":"\u201cTemporal binary representation for event-based action recognition,\u201d","volume-title":"2020 25th International Conference on Pattern Recognition (ICPR)","author":"Innocenti","year":"2021"},{"key":"B26","doi-asserted-by":"publisher","first-page":"515306","DOI":"10.3389\/fnins.2020.00424","article-title":"Synaptic plasticity dynamics for deep continuous local learning (decolle)","volume":"14","author":"Kaiser","year":"2020","journal-title":"Front. Neurosci"},{"key":"B27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s00138-022-01367-x","article-title":"Aligning accumulative representations for sign language recognition","volume":"34","author":"K\u0131nd\u0131roglu","year":"2022","journal-title":"Mach. Vis. Appl"},{"key":"B28","first-page":"631","article-title":"\u201cNeuromorphic data augmentation for training spiking neural networks,\u201d","volume-title":"European Conference on Computer Vision","author":"Li","year":"2022"},{"key":"B29","doi-asserted-by":"crossref","first-page":"2737","DOI":"10.1109\/ISCAS.2008.4542023","article-title":"\u201cHuman activity recognition for video surveillance,\u201d","volume-title":"2008 IEEE international symposium on circuits and systems (ISCAS)","author":"Lin","year":"2008"},{"key":"B30","article-title":"\u201cSpike-slr: an energy-efficient parallel spiking transformer for event-based sign language recognition,\u201d","author":"Lin","year":"2024","journal-title":"BMVC 2024"},{"key":"B31","doi-asserted-by":"publisher","first-page":"04798","DOI":"10.48550\/arXiv.2402:04798","article-title":"Spiking-physformer: camera-based remote photoplethysmography with parallel spike-driven transformer","volume":"2402","author":"Liu","year":"2024","journal-title":"arXiv"},{"key":"B32","doi-asserted-by":"publisher","first-page":"1308","DOI":"10.1609\/aaai.v34i02.5486","article-title":"Effective aer object classification using segmented probability-maximization learning in spiking neural networks","volume":"34","author":"Liu","year":"2020","journal-title":"Proc. AAAI Conf. Artif. Intell"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/240","article-title":"\u201cEvent-based action recognition using motion information and spiking neural networks,\u201d","author":"Liu","year":"2021","journal-title":"International Joint Conferences on Artificial Intelligence Organization, Virtual conference (IJCAI)"},{"key":"B34","first-page":"19400","article-title":"\u201cMulti-task temporal shift attention networks for on-device contactless vitals measurement,\u201d","author":"Liu","year":"2020","journal-title":"Advances in Neural Information Processing Systems, Vol. 33"},{"key":"B35","article-title":"\u201cDecoupled weight decay regularization,\u201d","volume-title":"International Conference on Learning Representations","author":"Loshchilov","year":"2017"},{"key":"B36","doi-asserted-by":"publisher","first-page":"1659","DOI":"10.1016\/S0893-6080(97)00011-7","article-title":"Networks of spiking neurons: the third generation of neural network models","volume":"10","author":"Maass","year":"1997","journal-title":"Neural Netw"},{"key":"B37","first-page":"10245","article-title":"\u201cSpeed invariant time surface for learning to detect corner points with event-based cameras,\u201d","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Manderscheid","year":"2019"},{"key":"B38","doi-asserted-by":"publisher","first-page":"18608","DOI":"10.1109\/ACCESS.2022.3151362","article-title":"Using motion history images with 3D convolutional networks in isolated sign language recognition","volume":"10","author":"Mercanoglu Sincan","year":"2022","journal-title":"IEEE Access"},{"key":"B39","unstructured":"MurrayJ.\n          World federation of the deaf2018"},{"key":"B40","doi-asserted-by":"publisher","first-page":"107805","DOI":"10.1016\/j.compeleceng.2022.107805","article-title":"Harednet: a deep learning based architecture for autonomous video surveillance by recognizing human actions","volume":"99","author":"Nasir","year":"2022","journal-title":"Comput. Electr. Eng"},{"key":"B41","doi-asserted-by":"publisher","first-page":"5","DOI":"10.3233\/AIS-180510","article-title":"Sensors, vision and networks: from video surveillance to activity recognition and health monitoring","volume":"11","author":"Prati","year":"2019","journal-title":"J. Ambient Intell. Smart Environ"},{"key":"B42","doi-asserted-by":"publisher","first-page":"123487","DOI":"10.3389\/fnins.2015.00141","article-title":"A reconfigurable on-line learning spiking neuromorphic processor comprising 256 neurons and 128k synapses","volume":"9","author":"Qiao","year":"2015","journal-title":"Front. Neurosci"},{"key":"B43","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2310.17429","article-title":"Lsa64: an argentinian sign language dataset","author":"Ronchetti","year":"2023","journal-title":"arXiv"},{"key":"B44","doi-asserted-by":"crossref","first-page":"2676","DOI":"10.1109\/CVPRW56347.2022.00301","article-title":"\u201cEvent transformer. a sparse-aware solution for efficient event data processing,\u201d","volume-title":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","author":"Sabater","year":"2022"},{"key":"B45","doi-asserted-by":"publisher","first-page":"16013","DOI":"10.1109\/TPAMI.2023.3311336","article-title":"Event transformer+. a multi-purpose solution for efficient event data processing","volume":"45","author":"Sabater","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"B46","doi-asserted-by":"publisher","first-page":"813","DOI":"10.1109\/TETCI.2020.3014367","article-title":"Har-depth: a novel framework for human action recognition using sequential learning and depth estimated history images","volume":"5","author":"Sahoo","year":"2020","journal-title":"IEEE Trans. Emerg. Top. Comput. Intell"},{"key":"B47","doi-asserted-by":"publisher","first-page":"119170","DOI":"10.1016\/j.ins.2023.119170","article-title":"Eventmix: an efficient data augmentation strategy for event-based learning","volume":"644","author":"Shen","year":"2023","journal-title":"Inf. Sci"},{"key":"B48","doi-asserted-by":"publisher","first-page":"226","DOI":"10.1145\/3656046","article-title":"Stepnet: apatial-temporal part-aware network for isolated sign language recognition","volume":"20","author":"Shen","year":"2024","journal-title":"ACM Trans. Multimedia Comput. Commun. Appl"},{"key":"B49","doi-asserted-by":"publisher","first-page":"768","DOI":"10.1109\/LSP.2023.3289111","article-title":"Qisampling: an effective sampling strategy for event-based sign language recognition","volume":"30","author":"Shi","year":"2023","journal-title":"IEEE Signal Process. Lett"},{"key":"B50","first-page":"1412","article-title":"Slayer: spike layer error reassignment in time","volume":"31","author":"Shrestha","year":"2018","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"B51","doi-asserted-by":"publisher","DOI":"10.1117\/12.2520589","article-title":"\u201cSuper-convergence: very fast training of neural networks using large learning rates,\u201d","author":"Smith","year":"2018","journal-title":"Defense"},{"key":"B52","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1098\/rspb.1967.0013","article-title":"The frequency of nerve action potentials generated by applied currents","volume":"167","author":"Stein","year":"1967","journal-title":"Proc. R. Soc. Lond. B. Biol. Sci"},{"key":"B53","first-page":"1869","article-title":"A survey of robot perception and control based on event camera","volume":"48","author":"Su","year":"2022","journal-title":"Acta Autom. Sin"},{"key":"B54","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2403.09274","article-title":"Eventrpg: event data augmentation with relevance propagation guidance","author":"Sun","year":"2024","journal-title":"arXiv"},{"key":"B55","doi-asserted-by":"publisher","first-page":"3200","DOI":"10.1109\/TPAMI.2022.3183112","article-title":"Human action recognition from various data modalities: a review","volume":"45","author":"Sun","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"B56","doi-asserted-by":"publisher","first-page":"505","DOI":"10.1007\/s10044-021-01011-w","article-title":"Sl-animals-dvs: event-driven sign language animals dataset","volume":"25","author":"Vasudevan","year":"2022","journal-title":"Pattern Anal. Applic"},{"key":"B57","article-title":"\u201cAttention is all you need,\u201d","volume-title":"Neural Information Processing Systems","author":"Vaswani","year":"2017"},{"key":"B58","doi-asserted-by":"crossref","first-page":"3457","DOI":"10.1109\/CVPRW53098.2021.00385","article-title":"\u201cIsolated sign language recognition with multi-scale spatial-temporal graph convolutional networks,\u201d","volume-title":"2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","author":"V\u00e1zquez-Enr\u00edquez","year":"2021"},{"key":"B59","doi-asserted-by":"publisher","first-page":"53880","DOI":"10.1109\/ACCESS.2023.3282311","article-title":"A comprehensive survey of RGB-based and skeleton-based human action recognition","volume":"11","author":"Wang","year":"2023","journal-title":"IEEE Access"},{"key":"B60","doi-asserted-by":"publisher","first-page":"22265","DOI":"10.1007\/s00521-023-08873-7","article-title":"TIM-SLR: a lightweight network for video isolated sign language recognition","volume":"35","author":"Wang","year":"2023","journal-title":"Neural Comput. Appl"},{"key":"B61","doi-asserted-by":"crossref","first-page":"416","DOI":"10.1109\/CVPR.2017.52","article-title":"\u201cScene flow to action map: a new representation for rgb-d based action recognition with convolutional neural networks,\u201d","volume-title":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Wang","year":"2017"},{"key":"B62","doi-asserted-by":"publisher","first-page":"7499","DOI":"10.1109\/JSEN.2022.3153610","article-title":"Recent advances in pedestrian navigation activity recognition: a review","volume":"22","author":"Wang","year":"2022","journal-title":"IEEE Sens. J"},{"key":"B63","doi-asserted-by":"crossref","first-page":"1826","DOI":"10.1109\/WACV.2019.00199","article-title":"\u201cSpace-time event clouds for gesture recognition: from RGB cameras to event cameras,\u201d","volume-title":"2019 IEEE Winter Conference on Applications of Computer Vision (WACV)","author":"Wang","year":"2019"},{"key":"B64","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2408.09764","article-title":"Event stream based human action recognition: a high-definition benchmark dataset and algorithms","author":"Wang","year":"2024","journal-title":"arXiv"},{"key":"B65","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2308.04369","article-title":"Sstformer: bridging spiking neural network and memory support transformer for frame-event based recognition","author":"Wang","year":"2023","journal-title":"arXiv"},{"key":"B66","doi-asserted-by":"publisher","first-page":"3436","DOI":"10.1109\/TPAMI.2021.3054886","article-title":"Event-stream representation for human gaits identification using deep neural networks","volume":"44","author":"Wang","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"B67","first-page":"1761","article-title":"\u201cMasked spiking transformer,\u201d","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Wang","year":"2023"},{"key":"B68","doi-asserted-by":"publisher","first-page":"323875","DOI":"10.3389\/fnins.2018.00331","article-title":"Spatio-temporal backpropagation for training high-performance spiking neural networks","volume":"12","author":"Wu","year":"2018","journal-title":"Front. Neurosci"},{"key":"B69","doi-asserted-by":"publisher","first-page":"3649","DOI":"10.1109\/TNNLS.2019.2945630","article-title":"An event-driven categorization model for aer image sensors using multispike encoding and learning","volume":"31","author":"Xiao","year":"2019","journal-title":"IEEE Trans. Neural Netw. Learn. Syst"},{"key":"B70","doi-asserted-by":"crossref","DOI":"10.24963\/ijcai.2018\/228","article-title":"\u201cCSNN: an augmented spiking based framework with perceptron-inception,\u201d","volume-title":"IJCAI, Vol. 1646","author":"Xu","year":"2018"},{"key":"B71","first-page":"10221","article-title":"\u201cTemporal-wise attention spiking neural networks for event streams classification,\u201d","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Yao","year":"2021"},{"key":"B72","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2404.03663","article-title":"Spike-driven transformer v2: Meta spiking neural network architecture inspiring the design of next-generation neuromorphic chips","author":"Yao","year":"","journal-title":"arXiv"},{"key":"B73","first-page":"16924","article-title":"\u201cInherent redundancy in spiking neural networks,\u201d","volume-title":"Proceedings of the IEEE\/CVF international conference on computer vision","author":"Yao","year":"2023"},{"key":"B74","first-page":"64043","article-title":"Spike-driven transformer","volume":"36","author":"Yao","year":"","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"B75","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2406.15034","article-title":"Svformer: a direct training spiking transformer for efficient video action recognition","author":"Yu","year":"2024","journal-title":"arXiv"},{"key":"B76","doi-asserted-by":"publisher","first-page":"18218","DOI":"10.1109\/JSEN.2022.3198395","article-title":"A radar-based human activity recognition using a novel 3-d point cloud classifier","volume":"22","author":"Yu","year":"2022","journal-title":"IEEE Sens. J"},{"key":"B77","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1109\/ISSCC42615.2023.10067650","author":"Zhang","year":"2023"},{"key":"B78","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1109\/ASYNC48570.2021.00013","article-title":"\u201cA 28nm configurable asynchronous snn accelerator with energy-efficient learning,\u201d","volume-title":"2021 27th IEEE International Symposium on Asynchronous Circuits and Systems (ASYNC)","author":"Zhang","year":"2021"},{"key":"B79","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2209.15425","article-title":"Spikformer: when spiking neural network meets transformer","author":"Zhou","year":"2022","journal-title":"arXiv"},{"key":"B80","first-page":"989","article-title":"\u201cUnsupervised event-based learning of optical flow, depth, and egomotion,\u201d","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Zhu","year":"2019"},{"key":"B81","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2303.09681","article-title":"Event-based human pose tracking by spiking spatiotemporal transformer","author":"Zou","year":"2023","journal-title":"arXiv"}],"container-title":["Frontiers in Computational Neuroscience"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fncom.2024.1508297\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T04:25:37Z","timestamp":1732595137000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fncom.2024.1508297\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,26]]},"references-count":81,"alternative-id":["10.3389\/fncom.2024.1508297"],"URL":"https:\/\/doi.org\/10.3389\/fncom.2024.1508297","relation":{},"ISSN":["1662-5188"],"issn-type":[{"value":"1662-5188","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,26]]},"article-number":"1508297"}}