{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T14:36:46Z","timestamp":1769006206826,"version":"3.49.0"},"reference-count":33,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"project \u201cRadarSkin\u201d"},{"name":"German Federal Ministry of Education and Research (BMBF) the call \u201cElectronic Systems for Edge Computing\u201d","award":["16ME0543"],"award-info":[{"award-number":["16ME0543"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3497158","type":"journal-article","created":{"date-parts":[[2024,11,13]],"date-time":"2024-11-13T18:57:40Z","timestamp":1731524260000},"page":"169787-169804","source":"Crossref","is-referenced-by-count":1,"title":["Leveraging Temporal Patterns: Automated Augmentation to Create Temporal Early Exit Networks for Efficient Edge AI"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4830-9440","authenticated-orcid":false,"given":"Max","family":"Sponner","sequence":"first","affiliation":[{"name":"Infineon Technologies Dresden GmbH & Co. KG, Dresden, Germany"}]},{"given":"Lorenzo","family":"Servadei","sequence":"additional","affiliation":[{"name":"Chair for Design Automation, Technical University of Munich, Munich, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0294-8594","authenticated-orcid":false,"given":"Bernd","family":"Waschneck","sequence":"additional","affiliation":[{"name":"Infineon Technologies AG, Neubiberg, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4993-7860","authenticated-orcid":false,"given":"Robert","family":"Wille","sequence":"additional","affiliation":[{"name":"Chair for Design Automation, Technical University of Munich, Munich, Germany"}]},{"given":"Akash","family":"Kumar","sequence":"additional","affiliation":[{"name":"Chair of Embedded Systems, Ruhr University Bochum, Bochum, Germany"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2016.7900006"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3534580"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CODESISSS.2015.7331375"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013812"},{"key":"ref5","first-page":"1","article-title":"Efficient post-training augmentation for adaptive inference in heterogeneous and distributed iot environments","volume-title":"Proc. 2024 Int. Conf. Embedded Comput. Syst., Archit., Model., Simul. (SAMOS)","author":"Sponner"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/FMEC62297.2024.10710223"},{"key":"ref7","article-title":"Temporal patience: Efficient adaptive deep learning for embedded radar data processing","author":"Sponner","year":"2023","journal-title":"arXiv:2309.05686"},{"key":"ref8","article-title":"Temporal decisions: Leveraging temporal correlation for efficient decisions in early exit neural networks","author":"Sponner","year":"2024","journal-title":"arXiv:2403.07958"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3657283"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.116"},{"key":"ref11","first-page":"475","article-title":"Conditional deep learning for energy-efficient and enhanced pattern recognition","volume-title":"Proc. Design, Autom. Test Eur. Conf. Exhibit. (DATE)","author":"Panda"},{"key":"ref12","first-page":"3","article-title":"A panda? No, it\u2019s a sloth: Slowdown attacks on adaptive multi-exit neural network inference","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Hong"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01427"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298640"},{"key":"ref15","first-page":"6","article-title":"BERT loses patience: Fast and robust inference with early exit","volume-title":"Proc. 33rd Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Zhou"},{"key":"ref16","first-page":"527","article-title":"Adaptive neural networks for efficient inference","volume-title":"Proc. 34th Int. Conf. Mach. Learn., (ICML)","author":"Bolukbasi"},{"key":"ref17","first-page":"1","article-title":"Changing model behavior at test-time using reinforcement learning","volume-title":"Proc. 5th Int. Conf. Learn. Represent., (ICLR)","author":"Odena"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3517207.3526982"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/dac56929.2023.10247722"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.23919\/DATE56975.2023.10137095"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN54540.2023.10191876"},{"key":"ref22","article-title":"Speech commands: A dataset for limited-vocabulary speech recognition","author":"Warden","year":"2018","journal-title":"arXiv:1804.03209"},{"key":"ref23","first-page":"1","article-title":"Mlperf tiny benchmark","volume-title":"Proc. Neural Inf. Process. Syst. Track Datasets Benchmarks 1","author":"Banbury"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.hrtlng.2011.05.001"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-020-0495-6"},{"key":"ref26","first-page":"1","article-title":"Tensorflow lite micro: Embedded machine learning for TinyML systems","volume-title":"Proc. 3rd Mach. Learn. Syst. (MLSys)","author":"David"},{"key":"ref27","article-title":"Hello edge: Keyword spotting on microcontrollers","author":"Zhang","year":"2017","journal-title":"arXiv:1711.07128"},{"key":"ref28","article-title":"Visual wake words dataset","author":"Chowdhery","year":"2019","journal-title":"arXiv:1906.05721"},{"key":"ref29","volume-title":"Las Vegas Wedding Cam","year":"2024"},{"key":"ref30","volume-title":"Ultralytics YOLOv8","author":"Jocher","year":"2023"},{"key":"ref31","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017","journal-title":"arXiv:1704.04861"},{"key":"ref32","volume-title":"TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems","author":"Abadi","year":"2015"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.25080\/tcwv9851"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10380310\/10752535.pdf?arnumber=10752535","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T23:21:47Z","timestamp":1732663307000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10752535\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3497158","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}