{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,25]],"date-time":"2026-07-25T00:45:00Z","timestamp":1784940300347,"version":"3.55.0"},"reference-count":86,"publisher":"IOP Publishing","issue":"1","license":[{"start":{"date-parts":[[2025,2,12]],"date-time":"2025-02-12T00:00:00Z","timestamp":1739318400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,2,12]],"date-time":"2025-02-12T00:00:00Z","timestamp":1739318400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"name":"DoE MMICC center SEA-CROGS","award":["Award #DE-SC0023198"],"award-info":[{"award-number":["Award #DE-SC0023198"]}]},{"name":"National Science Foundation","award":["CAREER Award"],"award-info":[{"award-number":["CAREER Award"]}]},{"name":"CoCoSys"},{"DOI":"10.13039\/100000185","name":"DARPA","doi-asserted-by":"crossref","award":["Young Faculty Award"],"award-info":[{"award-number":["Young Faculty Award"]}],"id":[{"id":"10.13039\/100000185","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Neuromorph. Comput. Eng."],"published-print":{"date-parts":[[2025,3,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Spiking Neural Networks (SNNs) have emerged as a compelling, energy-efficient alternative to traditional Artificial Neural Networks (ANNs) for static image tasks such as image classification and segmentation. However, in the more complex video classification domain, SNN-based methods fall considerably short of ANN-based benchmarks due to the challenges in processing dense frame sequences. To bridge this gap, we propose\n                    <jats:bold>ReSpike<\/jats:bold>\n                    , a hybrid framework that synergizes the strengths of ANNs and SNNs to tackle action recognition tasks with high accuracy and low energy cost. By partitioning film clips into RGB image\n                    <jats:bold>Key Frames<\/jats:bold>\n                    , which primarily capture spatial information, and event-like\n                    <jats:bold>Residual Frames<\/jats:bold>\n                    , which emphasize temporal dynamics cues, ReSpike leverages ANN for processing spatial features and SNN for modeling temporal features. In addition, we propose a multi-scale cross-attention mechanism for effective feature fusion. Compared to state-of-the-art SNN baselines, our ReSpike hybrid architecture demonstrates significant performance improvements (e.g.\n                    <jats:inline-formula>\n                      <jats:tex-math>\n                        \n                      <\/jats:tex-math>\n                      <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\" overflow=\"scroll\">\n                        <mml:mrow>\n                          <mml:mo>&gt;<\/mml:mo>\n                        <\/mml:mrow>\n                      <\/mml:math>\n                    <\/jats:inline-formula>\n                    <jats:bold>30<\/jats:bold>\n                    % absolute accuracy improvement on HMDB-51, UCF-101, and Kinetics-400). Furthermore, ReSpike achieves comparable performance with prior ANN approaches while bringing better accuracy-energy tradeoff. Code is shared at\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/Intelligent-Computing-Lab-Yale\/ReSpike\">https:\/\/github.com\/Intelligent-Computing-Lab-Yale\/ReSpike<\/jats:ext-link>\n                    .\n                  <\/jats:p>","DOI":"10.1088\/2634-4386\/adb070","type":"journal-article","created":{"date-parts":[[2025,1,30]],"date-time":"2025-01-30T17:54:51Z","timestamp":1738259691000},"page":"014009","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["ReSpike: residual frames-based hybrid spiking neural networks for efficient action recognition"],"prefix":"10.1088","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-7592-9466","authenticated-orcid":true,"given":"Shiting","family":"Xiao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6444-7253","authenticated-orcid":true,"given":"Yuhang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3542-7720","authenticated-orcid":true,"given":"Youngeun","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2927-8255","authenticated-orcid":true,"given":"Donghyun","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4167-6782","authenticated-orcid":true,"given":"Priyadarshini","family":"Panda","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2025,2,12]]},"reference":[{"key":"nceadb070bib1","first-page":"pp 770","type":"conference-proceedings","article-title":"Deep residual learning for image recognition","author":"Kaiming","year":"2016"},{"key":"nceadb070bib2","first-page":"p 25","type":"conference-proceedings","article-title":"Imagenet classification with deep convolutional neural networks","author":"Krizhevsky","year":"2012"},{"key":"nceadb070bib3","first-page":"pp 1","type":"conference-proceedings","article-title":"Going deeper with convolutions","author":"Szegedy","year":"2015"},{"key":"nceadb070bib4","first-page":"p 28","type":"conference-proceedings","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","author":"Ren","year":"2015"},{"key":"nceadb070bib5","first-page":"pp 2961","type":"conference-proceedings","article-title":"Mask r-cnn","author":"Kaiming","year":"2017"},{"key":"nceadb070bib6","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","type":"preprint"},{"key":"nceadb070bib7","first-page":"pp 10012","type":"conference-proceedings","article-title":"Swin transformer: Hierarchical vision transformer using shifted windows","author":"Liu","year":"2021"},{"key":"nceadb070bib8","doi-asserted-by":"publisher","first-page":"5917","DOI":"10.1109\/TMC.2023.3315138","type":"journal-article","article-title":"Devit: decomposing vision transformers for collaborative inference in edge devices","volume":"23","author":"Guanyu","year":"2023","journal-title":"IEEE Trans. Mobile Comput."},{"key":"nceadb070bib9","doi-asserted-by":"publisher","first-page":"35","DOI":"10.3389\/fnbot.2018.00035","type":"journal-article","article-title":"A survey of robotics control based on learning-inspired spiking neural networks","volume":"12","author":"Bing","year":"2018","journal-title":"Front. Neurorobot."},{"key":"nceadb070bib10","doi-asserted-by":"publisher","first-page":"76903","DOI":"10.1109\/ACCESS.2020.2990416","type":"journal-article","article-title":"Deep scnn-based real-time object detection for self-driving vehicles using lidar temporal data","volume":"8","author":"Zhou","year":"2020","journal-title":"IEEE Access"},{"key":"nceadb070bib11","author":"Stagsted","year":"2020","type":"book"},{"key":"nceadb070bib12","doi-asserted-by":"publisher","first-page":"607","DOI":"10.1038\/s41586-019-1677-2","type":"journal-article","article-title":"Towards spike-based machine intelligence with neuromorphic computing","volume":"575","author":"Roy","year":"2019","journal-title":"Nature"},{"key":"nceadb070bib13","doi-asserted-by":"crossref","DOI":"10.1088\/2634-4386\/ac4a83","type":"journal-article","article-title":"2022 roadmap on neuromorphic computing and engineering","volume":"2","author":"Christensen","year":"2022","journal-title":"Neuromorph. Comput. Eng."},{"key":"nceadb070bib14","doi-asserted-by":"publisher","first-page":"331","DOI":"10.3389\/fnins.2018.00331","type":"journal-article","article-title":"Spatio-temporal backpropagation for training high-performance spiking neural networks","volume":"12","author":"Yujie","year":"2018","journal-title":"Front. Neurosci."},{"key":"nceadb070bib15","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1038\/s41467-021-27653-2","type":"journal-article","article-title":"Brain-inspired global-local learning incorporated with neuromorphic computing","volume":"13","author":"Yujie","year":"2022","journal-title":"Nat. Commun."},{"key":"nceadb070bib16","first-page":"pp 21056","type":"journal-article","article-title":"Timoth\u00e9e Masquelier and Yonghong Tian. Deep residual learning in spiking neural networks","volume":"vol 34","author":"Fang","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"nceadb070bib17","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-98448-0","type":"journal-article","article-title":"Visual explanations from spiking neural networks using inter-spike intervals","volume":"11","author":"Kim","year":"2021","journal-title":"Sci. Rep."},{"key":"nceadb070bib18","first-page":"pp 8308","type":"conference-proceedings","article-title":"Exploring temporal information dynamics in spiking neural networks","volume":"vol 37","author":"Kim","year":"2023"},{"key":"nceadb070bib19","doi-asserted-by":"publisher","first-page":"1537","DOI":"10.1109\/TCAD.2015.2474396","type":"journal-article","article-title":"Truenorth: Design and tool flow of a 65 mw 1 million neuron programmable neurosynaptic chip","volume":"34","author":"Akopyan","year":"2015","journal-title":"IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst."},{"key":"nceadb070bib20","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1109\/MM.2018.112130359","type":"journal-article","article-title":"Loihi: A neuromorphic manycore processor with on-chip learning","volume":"38","author":"Davies","year":"2018","journal-title":"IEEE Micro"},{"key":"nceadb070bib21","doi-asserted-by":"crossref","first-page":"652","DOI":"10.1109\/JPROC.2014.2304638","type":"journal-article","article-title":"The spinnaker project","volume":"102","author":"Furber","year":"2014","journal-title":"Proc. IEEE"},{"key":"nceadb070bib22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TNNLS.2024.3355393","type":"journal-article","article-title":"Advancing spiking neural networks toward deep residual learning","author":"Yifan","year":"2024","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"nceadb070bib23","article-title":"Temporal efficient training of spiking neural network via gradient re-weighting","author":"Deng","year":"2022","type":"preprint"},{"key":"nceadb070bib24","first-page":"pp 248","type":"conference-proceedings","article-title":"Imagenet: a large-scale hierarchical image database","author":"Deng","year":"2009"},{"key":"nceadb070bib25","first-page":"pp 4489","type":"conference-proceedings","article-title":"Learning spatiotemporal features with 3d convolutional networks","author":"Tran","year":"2015"},{"key":"nceadb070bib26","article-title":"Convnet architecture search for spatiotemporal feature learning","author":"Tran","year":"2017","type":"preprint"},{"key":"nceadb070bib27","first-page":"pp 2556","type":"conference-proceedings","article-title":"Hmdb: a large video database for human motion recognition","author":"Kuehne","year":"2011"},{"key":"nceadb070bib28","article-title":"Ucf101: A dataset of 101 human actions classes from videos in the wild","author":"Soomro","year":"2012","type":"preprint"},{"key":"nceadb070bib29","doi-asserted-by":"crossref","first-page":"6979","DOI":"10.1007\/s11063-023-11247-8","type":"journal-article","article-title":"Convolutional spiking neural networks for spatio-temporal feature extraction","volume":"55","author":"Samadzadeh","year":"2023","journal-title":"Neural Process. Lett."},{"key":"nceadb070bib30","doi-asserted-by":"publisher","first-page":"4532","DOI":"10.3390\/s23094532","type":"journal-article","article-title":"Integrating spatial and temporal information for violent activity detection from video using deep spiking neural networks","volume":"23","author":"Wang","year":"2023","journal-title":"Sensors"},{"key":"nceadb070bib31","first-page":"pp 8801","type":"conference-proceedings","article-title":"Spiking transformers for event-based single object tracking","author":"Zhang","year":"2022"},{"key":"nceadb070bib32","first-page":"pp 366","type":"conference-proceedings","article-title":"Spike-flownet: event-based optical flow estimation with energy-efficient hybrid neural networks","author":"Lee","year":"2020"},{"key":"nceadb070bib33","first-page":"pp 3594","type":"conference-proceedings","article-title":"Event-based video reconstruction via potential-assisted spiking neural network","author":"Zhu","year":"2022"},{"key":"nceadb070bib34","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017","type":"preprint"},{"key":"nceadb070bib35","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1007\/s11263-014-0788-3","type":"journal-article","article-title":"Spiking deep convolutional neural networks for energy-efficient object recognition","volume":"113","author":"Cao","year":"2015","journal-title":"Int. J. Comput. Vis."},{"key":"nceadb070bib36","first-page":"pp 1311","type":"conference-proceedings","article-title":"Direct training for spiking neural networks: Faster, larger, better","volume":"vol 33","author":"Yujie","year":"2019"},{"key":"nceadb070bib37","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1109\/MSP.2019.2931595","type":"journal-article","article-title":"Surrogate gradient learning in spiking neural networks: Bringing the power of gradient-based optimization to spiking neural networks","volume":"36","author":"Neftci","year":"2019","journal-title":"IEEE Signal Process. Mag."},{"key":"nceadb070bib38","doi-asserted-by":"publisher","first-page":"508","DOI":"10.3389\/fnins.2016.00508","type":"journal-article","article-title":"Training deep spiking neural networks using backpropagation","volume":"10","author":"Haeng Lee","year":"2016","journal-title":"Front. Neurosci."},{"key":"nceadb070bib39","doi-asserted-by":"publisher","first-page":"7852","DOI":"10.1109\/TSMC.2023.3300318","type":"journal-article","article-title":"Snib: improving spike-based machine learning using nonlinear information bottleneck","volume":"53","author":"Yang","year":"2023","journal-title":"IEEE Trans. Syst. Man Cybern. Syst."},{"key":"nceadb070bib40","article-title":"Enabling deep spiking neural networks with hybrid conversion and spike timing dependent backpropagation","author":"Rathi","year":"2020","type":"preprint"},{"key":"nceadb070bib41","first-page":"pp 11062","type":"conference-proceedings","article-title":"Going deeper with directly-trained larger spiking neural networks","volume":"vol 35","author":"Zheng","year":"2021"},{"key":"nceadb070bib42","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2021.773954","type":"journal-article","article-title":"Revisiting batch normalization for training low-latency deep spiking neural networks from scratch","volume":"15","author":"Kim","year":"2021","journal-title":"Front. Neurosci."},{"key":"nceadb070bib43","article-title":"Diet-snn: Direct input encoding with leakage and threshold optimization in deep spiking neural networks","author":"Rathi","year":"2020","type":"preprint"},{"key":"nceadb070bib44","first-page":"pp 2661","type":"conference-proceedings","article-title":"Incorporating learnable membrane time constant to enhance learning of spiking neural networks","author":"Fang","year":"2021"},{"key":"nceadb070bib45","doi-asserted-by":"publisher","first-page":"1947","DOI":"10.1109\/TNNLS.2021.3110991","type":"journal-article","article-title":"Rectified linear postsynaptic potential function for backpropagation in deep spiking neural networks","volume":"33","author":"Zhang","year":"2021","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"nceadb070bib46","first-page":"pp 19420","type":"conference-proceedings","article-title":"Membrane potential batch normalization for spiking neural networks","author":"Guo","year":"2023"},{"key":"nceadb070bib47","doi-asserted-by":"publisher","first-page":"5200","DOI":"10.1109\/TNNLS.2021.3119238","type":"journal-article","article-title":"Spiking deep residual networks","volume":"34","author":"Yangfan","year":"2021","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"nceadb070bib48","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2024.1346805","type":"journal-article","article-title":"Rethinking skip connections in spiking neural networks with time-to-first-spike coding","volume":"18","author":"Kim","year":"2024","journal-title":"Front. Neurosci."},{"key":"nceadb070bib49","article-title":"Spikformer: When spiking neural network meets transformer","author":"Zhou","year":"2022","type":"preprint"},{"key":"nceadb070bib50","type":"conference-proceedings","article-title":"Spike-driven transformer","volume":"vol 36","author":"Yao","year":"2024"},{"key":"nceadb070bib51","article-title":"Spikingformer: Spike-driven residual learning for transformer-based spiking neural network","author":"Zhou","year":"2023","type":"preprint"},{"key":"nceadb070bib52","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1016\/j.neunet.2018.12.002","type":"journal-article","article-title":"Deep learning in spiking neural networks","volume":"111","author":"Tavanaei","year":"2019","journal-title":"Neural Netw."},{"key":"nceadb070bib53","doi-asserted-by":"publisher","DOI":"10.1088\/2634-4386\/ac9b86","type":"journal-article","article-title":"Beyond classification: Directly training spiking neural networks for semantic segmentation","volume":"2","author":"Kim","year":"2022","journal-title":"Neuromorph. Comput. Eng."},{"key":"nceadb070bib54","first-page":"pp 6555","type":"conference-proceedings","article-title":"Deep directly-trained spiking neural networks for object detection","author":"Qiaoyi","year":"2023"},{"key":"nceadb070bib55","first-page":"pp 10221","type":"conference-proceedings","article-title":"Temporal-wise attention spiking neural networks for event streams classification","author":"Yao","year":"2021"},{"key":"nceadb070bib56","article-title":"Eas-snn: End-to-end adaptive sampling and representation for event-based detection with recurrent spiking neural networks","author":"Wang","year":"2024","type":"preprint"},{"key":"nceadb070bib57","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TNNLS.2024.3377717","type":"journal-article","article-title":"Tcja-snn: Temporal-channel joint attention for spiking neural networks","author":"Zhu","year":"2024","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"nceadb070bib58","article-title":"Event-based human pose tracking by spiking spatiotemporal transformer","author":"Zou","year":"2023","type":"preprint"},{"key":"nceadb070bib59","doi-asserted-by":"publisher","first-page":"126","DOI":"10.3389\/fnins.2018.00126","type":"journal-article","article-title":"Learning to recognize actions from limited training examples using a recurrent spiking neural model","volume":"12","author":"Panda","year":"2018","journal-title":"Front. Neurosci."},{"key":"nceadb070bib60","article-title":"Spiking two-stream methods with unsupervised stdp-based learning for action recognition","author":"El-Assal","year":"2023","type":"preprint"},{"key":"nceadb070bib61","article-title":"S3tc: Spiking separated spatial and temporal convolutions with unsupervised stdp-based learning for action recognition","author":"El-Assal","year":"2023","type":"preprint"},{"key":"nceadb070bib62","first-page":"pp 1395","type":"conference-proceedings","article-title":"Actions as space-time shapes","volume":"vol 1","author":"Blank","year":"2005"},{"key":"nceadb070bib63","first-page":"pp 1","type":"conference-proceedings","article-title":"Action mach a spatio-temporal maximum average correlation height filter for action recognition","author":"Rodriguez","year":"2008"},{"key":"nceadb070bib64","first-page":"pp 32","type":"conference-proceedings","article-title":"Recognizing human actions: a local svm approach","volume":"vol 3","author":"Schuldt","year":"2004"},{"key":"nceadb070bib65","first-page":"pp 6504","type":"conference-proceedings","article-title":"Fusion-flownet: Energy-efficient optical flow estimation using sensor fusion and deep fused spiking-analog network architectures","author":"Lee","year":"2022"},{"key":"nceadb070bib66","doi-asserted-by":"publisher","first-page":"3427","DOI":"10.1038\/s41467-022-30964-7","type":"journal-article","article-title":"A framework for the general design and computation of hybrid neural networks","volume":"13","author":"Zhao","year":"2022","journal-title":"Nat. Commun."},{"key":"nceadb070bib67","article-title":"A hybrid ann-snn architecture for low-power and low-latency visual perception","author":"Aydin","year":"2023","type":"preprint"},{"key":"nceadb070bib68","first-page":"p 30","type":"conference-proceedings","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"nceadb070bib69","first-page":"pp 4651","type":"conference-proceedings","article-title":"Perceiver: General perception with iterative attention","author":"Jaegle","year":"2021"},{"key":"nceadb070bib70","article-title":"Perceiver io: A general architecture for structured inputs & outputs","author":"Jaegle","year":"2021","type":"preprint"},{"key":"nceadb070bib71","first-page":"pp 10684","type":"conference-proceedings","article-title":"High-resolution image synthesis with latent diffusion models","author":"Rombach","year":"2022"},{"key":"nceadb070bib72","type":"journal-article","article-title":"Efficient human activity recognition with spatio-temporal spiking neural networks","volume":"17","author":"Yuhang","year":"2023","journal-title":"Front. Neurosci."},{"key":"nceadb070bib73","first-page":"pp 630","type":"conference-proceedings","article-title":"Identity mappings in deep residual networks","volume":"vol 14","author":"Kaiming","year":"2016"},{"key":"nceadb070bib74","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","type":"preprint"},{"key":"nceadb070bib75","article-title":"Neural machine translation by jointly learning to align and translate","author":"Bahdanau","year":"2014","type":"preprint"},{"key":"nceadb070bib76","first-page":"pp 71","type":"conference-proceedings","article-title":"Rate coding or direct coding: Which one is better for accurate, robust and energy-efficient spiking neural networks?","author":"Kim","year":"2022"},{"key":"nceadb070bib77","first-page":"pp 6299","type":"conference-proceedings","article-title":"Quo vadis, action recognition? a new model and the kinetics dataset","author":"Carreira","year":"2017"},{"key":"nceadb070bib78","first-page":"pp 6824","type":"conference-proceedings","article-title":"Multiscale vision transformers","author":"Fan","year":"2021"},{"key":"nceadb070bib79","article-title":"Uncovering the representation of spiking neural networks trained with surrogate gradient","author":"Yuhang","year":"2023","type":"preprint"},{"key":"nceadb070bib80","first-page":"pp 3376","type":"conference-proceedings","article-title":"Adascan: Adaptive scan pooling in deep convolutional neural networks for human action recognition in videos","author":"Kar","year":"2017"},{"key":"nceadb070bib81","type":"conference-proceedings","article-title":"Spatiotemporal residual networks for video action recognition","volume":"vol 2","author":"Christoph","year":"2016"},{"key":"nceadb070bib82","first-page":"pp 402","type":"conference-proceedings","article-title":"Raft: Recurrent all-pairs field transforms for optical flow","volume":"vol 16","author":"Teed","year":"2020"},{"key":"nceadb070bib83","first-page":"pp 1725","type":"conference-proceedings","article-title":"Large-scale video classification with convolutional neural networks","author":"Karpathy","year":"2014"},{"key":"nceadb070bib84","first-page":"pp 10","type":"conference-proceedings","article-title":"1.1 computing\u2019s energy problem (and what we can do about it)","author":"Horowitz","year":"2014"},{"key":"nceadb070bib85","doi-asserted-by":"publisher","first-page":"3174","DOI":"10.1109\/TNNLS.2021.3111897","type":"journal-article","article-title":"Diet-snn: A low-latency spiking neural network with direct input encoding and leakage and threshold optimization","volume":"34","author":"Rathi","year":"2021","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"nceadb070bib86","first-page":"pp 442","type":"conference-proceedings","article-title":"Heatvit: Hardware-efficient adaptive token pruning for vision transformers","author":"Dong","year":"2023"}],"container-title":["Neuromorphic Computing and Engineering"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/adb070","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/adb070\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/adb070","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/adb070\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/adb070\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/adb070\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/adb070\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/adb070\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T10:36:49Z","timestamp":1765535809000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/adb070"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,12]]},"references-count":86,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,2,12]]},"published-print":{"date-parts":[[2025,3,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2634-4386\/adb070","relation":{},"ISSN":["2634-4386"],"issn-type":[{"value":"2634-4386","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,12]]},"assertion":[{"value":"ReSpike: residual frames-based hybrid spiking neural networks for efficient action recognition","name":"article_title","label":"Article Title"},{"value":"Neuromorphic Computing and Engineering","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2025 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2024-10-28","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-01-30","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-02-12","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}