{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T04:29:09Z","timestamp":1730348949625,"version":"3.28.0"},"publisher-location":"Cham","reference-count":65,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729065","type":"print"},{"value":"9783031729072","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"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":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-72907-2_4","type":"book-chapter","created":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T15:22:17Z","timestamp":1730301737000},"page":"55-72","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DailyDVS-200: A Comprehensive Benchmark Dataset for\u00a0Event-Based Action Recognition"],"prefix":"10.1007","author":[{"ORCID":"http:\/\/orcid.org\/0009-0004-4576-4458","authenticated-orcid":false,"given":"Qi","family":"Wang","sequence":"first","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0009-0004-5499-0537","authenticated-orcid":false,"given":"Zhou","family":"Xu","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0009-0009-7439-7462","authenticated-orcid":false,"given":"Yuming","family":"Lin","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0009-0002-6636-5072","authenticated-orcid":false,"given":"Jingtao","family":"Ye","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0002-9929-4023","authenticated-orcid":false,"given":"Hongsheng","family":"Li","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0003-3214-4095","authenticated-orcid":false,"given":"Guangming","family":"Zhu","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0003-2181-8445","authenticated-orcid":false,"given":"Syed Afaq","family":"Ali Shah","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0002-6603-3257","authenticated-orcid":false,"given":"Mohammed","family":"Bennamoun","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0003-4331-5830","authenticated-orcid":false,"given":"Liang","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,10,31]]},"reference":[{"key":"4_CR1","doi-asserted-by":"crossref","unstructured":"Amir, A., et\u00a0al.: A low power, fully event-based gesture recognition system. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7243\u20137252 (2017)","DOI":"10.1109\/CVPR.2017.781"},{"issue":"2","key":"4_CR2","doi-asserted-by":"publisher","first-page":"2519","DOI":"10.1109\/TPAMI.2022.3172212","volume":"45","author":"RW Baldwin","year":"2022","unstructured":"Baldwin, R.W., Liu, R., Almatrafi, M., Asari, V., Hirakawa, K.: Time-ordered recent event (TORE) volumes for event cameras. IEEE Trans. Pattern Anal. Mach. Intell. 45(2), 2519\u20132532 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"4_CR3","unstructured":"Bertasius, G., Wang, H., Torresani, L.: Is space-time attention all you need for video understanding? In: ICML, vol.\u00a02, p.\u00a04 (2021)"},{"key":"4_CR4","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.: Graph-based spatio-temporal feature learning for neuromorphic vision sensing. IEEE Trans. Image Process. 29, 9084\u20139098 (2020)","journal-title":"IEEE Trans. Image Process."},{"key":"4_CR5","doi-asserted-by":"crossref","unstructured":"de\u00a0Blegiers, T., Dave, I.R., Yousaf, A., Shah, M.: EventTransAct: a video transformer-based framework for event-camera based action recognition. In: 2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp.\u00a01\u20137. IEEE (2023)","DOI":"10.1109\/IROS55552.2023.10341740"},{"issue":"10","key":"4_CR6","doi-asserted-by":"publisher","first-page":"2333","DOI":"10.1109\/JSSC.2014.2342715","volume":"49","author":"C Brandli","year":"2014","unstructured":"Brandli, C., Berner, R., Yang, M., Liu, S.C., Delbruck, T.: A $$240 \\times 180$$ 130 db 3 $$\\upmu $$s latency global shutter spatiotemporal vision sensor. IEEE J. Solid-State Circuits 49(10), 2333\u20132341 (2014). https:\/\/doi.org\/10.1109\/JSSC.2014.2342715","journal-title":"IEEE J. Solid-State Circuits"},{"key":"4_CR7","doi-asserted-by":"crossref","unstructured":"Caba\u00a0Heilbron, F., Escorcia, V., Ghanem, B., Carlos\u00a0Niebles, J.: ActivityNet: a large-scale video benchmark for human activity understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 961\u2013970 (2015)","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"4_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"136","DOI":"10.1007\/978-3-030-58565-5_9","volume-title":"Computer Vision \u2013 ECCV 2020","author":"M Cannici","year":"2020","unstructured":"Cannici, M., Ciccone, M., Romanoni, A., Matteucci, M.: A differentiable recurrent surface for asynchronous event-based data. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020, Part XX. LNCS, vol. 12365, pp. 136\u2013152. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58565-5_9"},{"key":"4_CR9","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? A new model and the kinetics dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6299\u20136308 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"4_CR10","first-page":"24975","volume":"35","author":"K Che","year":"2022","unstructured":"Che, K., et al.: Differentiable hierarchical and surrogate gradient search for spiking neural networks. Adv. Neural. Inf. Process. Syst. 35, 24975\u201324990 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"4_CR11","doi-asserted-by":"crossref","unstructured":"Chen, S., Guo, M.: 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 (2019)","DOI":"10.1109\/CVPRW.2019.00214"},{"key":"4_CR12","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"4_CR13","unstructured":"Dong, Y., Li, Y., Zhao, D., Shen, G., Zeng, Y.: Bullying10k: a large-scale neuromorphic dataset towards privacy-preserving bullying recognition. Adv. Neural Inf. Process. Syst. 36 (2024)"},{"key":"4_CR14","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"4_CR15","doi-asserted-by":"publisher","first-page":"110340","DOI":"10.1016\/j.dib.2024.110340","volume":"54","author":"L Duarte","year":"2024","unstructured":"Duarte, L., Neto, P.: Event-based dataset for the detection and classification of manufacturing assembly tasks. Data Brief 54, 110340 (2024)","journal-title":"Data Brief"},{"key":"4_CR16","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C.: X3D: expanding architectures for efficient video recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 203\u2013213 (2020)","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"4_CR17","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., He, K.: Slowfast networks for video recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6202\u20136211 (2019)","DOI":"10.1109\/ICCV.2019.00630"},{"key":"4_CR18","doi-asserted-by":"crossref","unstructured":"Gao, Y., et al.: Action recognition and benchmark using event cameras. IEEE Trans. Pattern Anal. Mach. Intell. (2023)","DOI":"10.1109\/TPAMI.2023.3300741"},{"key":"4_CR19","doi-asserted-by":"crossref","unstructured":"Gehrig, D., Loquercio, A., Derpanis, K.G., Scaramuzza, D.: 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 (2019)","DOI":"10.1109\/ICCV.2019.00573"},{"key":"4_CR20","unstructured":"Kay, W., et\u00a0al.: The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)"},{"key":"4_CR21","doi-asserted-by":"crossref","unstructured":"Kim, J., Bae, J., Park, G., Zhang, D., Kim, Y.M.: N-ImageNet: towards robust, fine-grained object recognition with event cameras. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2146\u20132156 (2021)","DOI":"10.1109\/ICCV48922.2021.00215"},{"issue":"3","key":"4_CR22","doi-asserted-by":"publisher","first-page":"615","DOI":"10.1109\/TPAMI.2011.209","volume":"34","author":"O Kliper-Gross","year":"2011","unstructured":"Kliper-Gross, O., Hassner, T., Wolf, L.: The action similarity labeling challenge. IEEE Trans. Pattern Anal. Mach. Intell. 34(3), 615\u2013621 (2011)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"5","key":"4_CR23","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.: Human action recognition and prediction: a survey. Int. J. Comput. Vision 130(5), 1366\u20131401 (2022)","journal-title":"Int. J. Comput. Vision"},{"key":"4_CR24","doi-asserted-by":"crossref","unstructured":"Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., Serre, T.: HMDB: a large video database for human motion recognition. In: 2011 International Conference on Computer Vision, pp. 2556\u20132563. IEEE (2011)","DOI":"10.1109\/ICCV.2011.6126543"},{"issue":"7","key":"4_CR25","doi-asserted-by":"publisher","first-page":"1346","DOI":"10.1109\/TPAMI.2016.2574707","volume":"39","author":"X Lagorce","year":"2016","unstructured":"Lagorce, X., Orchard, G., Galluppi, F., Shi, B.E., Benosman, R.B.: HOTS: a hierarchy of event-based time-surfaces for pattern recognition. IEEE Trans. Pattern Anal. Mach. Intell. 39(7), 1346\u20131359 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"4_CR26","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1007\/s11263-005-1838-7","volume":"64","author":"I Laptev","year":"2005","unstructured":"Laptev, I.: On space-time interest points. Int. J. Comput. Vision 64, 107\u2013123 (2005)","journal-title":"Int. J. Comput. Vision"},{"key":"4_CR27","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.: CIFAR10-DVS: an event-stream dataset for object classification. Front. Neurosci. 11, 309 (2017)","journal-title":"Front. Neurosci."},{"key":"4_CR28","doi-asserted-by":"crossref","unstructured":"Li, J., Wang, X., Zhu, L., Li, J., Huang, T., Tian, Y.: Retinomorphic object detection in asynchronous visual streams. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a036, pp. 1332\u20131340 (2022)","DOI":"10.1609\/aaai.v36i2.20021"},{"issue":"1","key":"4_CR29","doi-asserted-by":"publisher","first-page":"746","DOI":"10.1038\/s41597-022-01851-z","volume":"9","author":"Y Li","year":"2022","unstructured":"Li, Y., Dong, Y., Zhao, D., Zeng, Y.: N-Omniglot, a large-scale neuromorphic dataset for spatio-temporal sparse few-shot learning. Sci. Data 9(1), 746 (2022)","journal-title":"Sci. Data"},{"key":"4_CR30","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Graph-based asynchronous event processing for rapid object recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 934\u2013943 (2021)","DOI":"10.1109\/ICCV48922.2021.00097"},{"key":"4_CR31","doi-asserted-by":"crossref","unstructured":"Lin, J., Gan, C., Han, S.: TSM: temporal shift module for efficient video understanding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7083\u20137093 (2019)","DOI":"10.1109\/ICCV.2019.00718"},{"key":"4_CR32","doi-asserted-by":"publisher","first-page":"1546","DOI":"10.3389\/fnins.2021.726582","volume":"15","author":"Y Lin","year":"2021","unstructured":"Lin, Y., Ding, W., Qiang, S., Deng, L., Li, G.: ES-ImageNet: a million event-stream classification dataset for spiking neural networks. Front. Neurosci. 15, 1546 (2021)","journal-title":"Front. Neurosci."},{"key":"4_CR33","doi-asserted-by":"crossref","unstructured":"Liu, J., Kuipers, B., Savarese, S.: Recognizing human actions by attributes. In: CVPR 2011, pp. 3337\u20133344. IEEE (2011)","DOI":"10.1109\/CVPR.2011.5995353"},{"issue":"10","key":"4_CR34","doi-asserted-by":"publisher","first-page":"2684","DOI":"10.1109\/TPAMI.2019.2916873","volume":"42","author":"J Liu","year":"2019","unstructured":"Liu, J., Shahroudy, A., Perez, M., Wang, G., Duan, L.Y., Kot, A.C.: NTU RGB+ D 120: a large-scale benchmark for 3D human activity understanding. IEEE Trans. Pattern Anal. Mach. Intell. 42(10), 2684\u20132701 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"4_CR35","doi-asserted-by":"crossref","unstructured":"Liu, Q., Xing, D., Tang, H., Ma, D., Pan, G.: Event-based action recognition using motion information and spiking neural networks. In: IJCAI, pp. 1743\u20131749 (2021)","DOI":"10.24963\/ijcai.2021\/240"},{"key":"4_CR36","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Video swin transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3202\u20133211 (2022)","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"4_CR37","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1007\/978-3-030-58598-3_25","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Messikommer","year":"2020","unstructured":"Messikommer, N., Gehrig, D., Loquercio, A., Scaramuzza, D.: Event-based asynchronous sparse convolutional networks. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020, Part VIII. LNCS, vol. 12353, pp. 415\u2013431. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58598-3_25"},{"key":"4_CR38","doi-asserted-by":"publisher","first-page":"38","DOI":"10.3389\/fnbot.2019.00038","volume":"13","author":"S Miao","year":"2019","unstructured":"Miao, S., et al.: Neuromorphic vision datasets for pedestrian detection, action recognition, and fall detection. Front. Neurorobot. 13, 38 (2019)","journal-title":"Front. Neurorobot."},{"key":"4_CR39","doi-asserted-by":"crossref","unstructured":"Moeys, D.P., et al.: Steering a predator robot using a mixed frame\/event-driven convolutional neural network. In: 2016 Second International Conference on Event-Based Control, Communication, and Signal Processing (EBCCSP), pp.\u00a01\u20138. IEEE (2016)","DOI":"10.1109\/EBCCSP.2016.7605233"},{"key":"4_CR40","doi-asserted-by":"crossref","unstructured":"Morency, L.P., Quattoni, A., Darrell, T.: Latent-dynamic discriminative models for continuous gesture recognition. In: 2007 IEEE Conference on Computer Vision and Pattern Recognition, pp.\u00a01\u20138. IEEE (2007)","DOI":"10.1109\/CVPR.2007.383299"},{"issue":"6","key":"4_CR41","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1109\/MSP.2019.2931595","volume":"36","author":"EO Neftci","year":"2019","unstructured":"Neftci, E.O., Mostafa, H., Zenke, F.: Surrogate gradient learning in spiking neural networks: bringing the power of gradient-based optimization to spiking neural networks. IEEE Signal Process. Mag. 36(6), 51\u201363 (2019)","journal-title":"IEEE Signal Process. Mag."},{"key":"4_CR42","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.: Converting static image datasets to spiking neuromorphic datasets using saccades. Front. Neurosci. 9, 437 (2015)","journal-title":"Front. Neurosci."},{"key":"4_CR43","doi-asserted-by":"crossref","unstructured":"Peng, Y., Zhang, Y., Xiong, Z., Sun, X., Wu, F.: GET: group event transformer for event-based vision. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6038\u20136048 (2023)","DOI":"10.1109\/ICCV51070.2023.00555"},{"issue":"1","key":"4_CR44","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1109\/JSSC.2010.2085952","volume":"46","author":"C Posch","year":"2010","unstructured":"Posch, C., Matolin, D., Wohlgenannt, R.: A QVGA 143 dB dynamic range frame-free PWM image sensor with lossless pixel-level video compression and time-domain CDS. IEEE J. Solid-State Circuits 46(1), 259\u2013275 (2010)","journal-title":"IEEE J. Solid-State Circuits"},{"key":"4_CR45","doi-asserted-by":"crossref","unstructured":"Rebecq, H., Horstschaefer, T., Scaramuzza, D.: Real-time visual-inertial odometry for event cameras using keyframe-based nonlinear optimization (2017)","DOI":"10.5244\/C.31.16"},{"key":"4_CR46","doi-asserted-by":"crossref","unstructured":"Sabater, A., Montesano, L., Murillo, A.C.: Event transformer. A sparse-aware solution for efficient event data processing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2677\u20132686 (2022)","DOI":"10.1109\/CVPRW56347.2022.00301"},{"key":"4_CR47","doi-asserted-by":"crossref","unstructured":"Schaefer, S., Gehrig, D., Scaramuzza, D.: AEGNN: asynchronous event-based graph neural networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12371\u201312381 (2022)","DOI":"10.1109\/CVPR52688.2022.01205"},{"key":"4_CR48","doi-asserted-by":"crossref","unstructured":"Scovanner, P., Ali, S., Shah, M.: A 3-dimensional sift descriptor and its application to action recognition. In: Proceedings of the 15th ACM International Conference on Multimedia, pp. 357\u2013360 (2007)","DOI":"10.1145\/1291233.1291311"},{"key":"4_CR49","doi-asserted-by":"publisher","first-page":"481","DOI":"10.3389\/fnins.2015.00481","volume":"9","author":"T Serrano-Gotarredona","year":"2015","unstructured":"Serrano-Gotarredona, T., Linares-Barranco, B.: Poker-DVS and MNIST-DVS. Their history, how they were made, and other details. Front. Neurosci. 9, 481 (2015)","journal-title":"Front. Neurosci."},{"key":"4_CR50","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1007\/s11263-010-0384-0","volume":"93","author":"Q Shi","year":"2011","unstructured":"Shi, Q., Cheng, L., Wang, L., Smola, A.: Human action segmentation and recognition using discriminative semi-Markov models. Int. J. Comput. Vision 93, 22\u201332 (2011)","journal-title":"Int. J. Comput. Vision"},{"key":"4_CR51","doi-asserted-by":"crossref","unstructured":"Sironi, A., Brambilla, M., Bourdis, N., Lagorce, X., Benosman, R.: 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 (2018)","DOI":"10.1109\/CVPR.2018.00186"},{"key":"4_CR52","unstructured":"Soomro, K., Zamir, A.R., Shah, M.: UCF101: a dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402 (2012)"},{"key":"4_CR53","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4489\u20134497 (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"4_CR54","doi-asserted-by":"crossref","unstructured":"Tran, D., Wang, H., Torresani, L., Ray, J., LeCun, Y., Paluri, M.: A closer look at spatiotemporal convolutions for action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6450\u20136459 (2018)","DOI":"10.1109\/CVPR.2018.00675"},{"key":"4_CR55","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"4_CR56","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1007\/s11263-015-0846-5","volume":"119","author":"H Wang","year":"2016","unstructured":"Wang, H., Oneata, D., Verbeek, J., Schmid, C.: A robust and efficient video representation for action recognition. Int. J. Comput. Vision 119, 219\u2013238 (2016)","journal-title":"Int. J. Comput. Vision"},{"key":"4_CR57","unstructured":"Wang, X., et al.: Reliable object tracking via collaboration of frame and event flows. arXiv preprint arXiv:2108.05015 (2021)"},{"key":"4_CR58","unstructured":"Wang, X., et al.: HARDVS: revisiting human activity recognition with dynamic vision sensors. arXiv preprint arXiv:2211.09648 (2022)"},{"key":"4_CR59","unstructured":"Yao, M., et al.: Spike-driven transformer. Adv. Neural Inf. Process. Syst. 36 (2024)"},{"key":"4_CR60","doi-asserted-by":"crossref","unstructured":"Zeng, Y., et\u00a0al.: BrainCog: a spiking neural network based, brain-inspired cognitive intelligence engine for brain-inspired AI and brain simulation. Patterns 4(8) (2023)","DOI":"10.1016\/j.patter.2023.100789"},{"key":"4_CR61","unstructured":"Zhou, Z., et al.: SpikFormer: when spiking neural network meets transformer. arXiv preprint arXiv:2209.15425 (2022)"},{"key":"4_CR62","doi-asserted-by":"crossref","unstructured":"Zhu, A.Z., Yuan, L., Chaney, K., Daniilidis, K.: Unsupervised event-based learning of optical flow, depth, and egomotion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 989\u2013997 (2019)","DOI":"10.1109\/CVPR.2019.00108"},{"key":"4_CR63","doi-asserted-by":"crossref","unstructured":"Zhu, L., Li, J., Wang, X., Huang, T., Tian, Y.: NeuSpike-net: high speed video reconstruction via bio-inspired neuromorphic cameras. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2400\u20132409 (2021)","DOI":"10.1109\/ICCV48922.2021.00240"},{"key":"4_CR64","doi-asserted-by":"crossref","unstructured":"Zhu, L., Wang, X., Chang, Y., Li, J., Huang, T., Tian, Y.: Event-based video reconstruction via potential-assisted spiking neural network. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3594\u20133604 (2022)","DOI":"10.1109\/CVPR52688.2022.00358"},{"key":"4_CR65","unstructured":"Zhu, S., Yang, T., Mendieta, M., Chen, C.: A3D: adaptive 3D networks for video action recognition. arXiv preprint arXiv:2011.12384 (2020)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72907-2_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T15:24:35Z","timestamp":1730301875000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72907-2_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,31]]},"ISBN":["9783031729065","9783031729072"],"references-count":65,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72907-2_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,31]]},"assertion":[{"value":"31 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}