{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:18:28Z","timestamp":1777655908298,"version":"3.51.4"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,5,13]]},"DOI":"10.1109\/icra57147.2024.10611196","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"4812-4818","source":"Crossref","is-referenced-by-count":4,"title":["Scaling Motion Forecasting Models with Ensemble Distillation"],"prefix":"10.1109","author":[{"given":"Scott","family":"Ettinger","sequence":"first","affiliation":[{"name":"Research Scientist at Waymo"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kratarth","family":"Goel","sequence":"additional","affiliation":[{"name":"Research Scientist at Waymo"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Avikalp","family":"Srivastava","sequence":"additional","affiliation":[{"name":"Research Scientist at Waymo"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rami","family":"Al-Rfou","sequence":"additional","affiliation":[{"name":"Research Scientist at Waymo"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.110"},{"key":"ref2","author":"Allen-Zhu","year":"2020","journal-title":"Towards understanding ensemble, knowledge distillation and self-distillation in deep learning"},{"key":"ref3","article-title":"Towards understanding ensemble, knowledge distillation and self-distillation in deep learning","author":"Allen-Zhu","year":"2020"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/BF00117832"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196697"},{"key":"ref6","article-title":"Intentnet: Learning to predict intention from raw sensor data","author":"Casas","year":"2021","journal-title":"CoRR"},{"key":"ref7","article-title":"Multipath: Multiple probabilistic anchor trajectory hypotheses for behavior prediction","author":"Chai","year":"2019","journal-title":"CoRL"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00895"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793868"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45014-9_1"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00957"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00957"},{"key":"ref13","article-title":"Deep ensembles: A loss landscape perspective","author":"Fort","year":"2019"},{"key":"ref14","article-title":"Born again neural networks","author":"Furlanello","year":"2018","journal-title":"ICML"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01154"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01502"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00240"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/34.58871"},{"key":"ref19","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00865"},{"key":"ref21","article-title":"One thousand and one hours: Self-driving motion prediction dataset","author":"Houston","year":"2020","journal-title":"CoRR"},{"key":"ref22","article-title":"Scaling laws for neural language models","author":"Kaplan","year":"2020"},{"key":"ref23","article-title":"What-if motion prediction for autonomous driving","author":"Khandelwal","year":"2020"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1139"},{"key":"ref25","article-title":"Neural network ensembles, cross validation, and active learning","author":"Krogh","year":"1994","journal-title":"NIPS"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.233"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2014-432"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_32"},{"key":"ref29","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2019","journal-title":"ICLR"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1613\/jair.614","article-title":"Popular ensemble methods: An empirical study","volume":"11","author":"Maclin","year":"1999","journal-title":"J. Artif. Intell. Res."},{"key":"ref31","author":"Malinin","year":"2019","journal-title":"Ensemble distribution distillation"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197340"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/icra48891.2023.10160609"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00291"},{"key":"ref35","article-title":"Trajectron++: Multi-agent generative trajectory forecasting with heterogeneous data for control","author":"Salzmann","year":"2020","journal-title":"CoRR"},{"key":"ref36","article-title":"MultiPATH: Multiple probabilistic anchor trajectory hypotheses for behavior prediction","volume-title":"Conf. on Robot Learning","author":"Sapp"},{"key":"ref37","article-title":"Boosting the margin: A new explanation for the effectiveness of voting methods","author":"Schapire","year":"1997","journal-title":"ICML"},{"key":"ref38","article-title":"Motion transformer with global intention localization and local movement refinement","author":"Shi","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812368"},{"key":"ref40","article-title":"Multipath++: Efficient information fusion and trajectory aggregation for behavior prediction","author":"Varadarajan","year":"2021","journal-title":"ICRA"},{"key":"ref41","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref42","article-title":"Argoverse 2: Next generation datasets for self-driving perception and forecasting","author":"Wilson","year":"2023"},{"key":"ref43","article-title":"Tnt: Target-driven trajectory prediction","author":"Zhao","year":"2020"},{"key":"ref44","article-title":"Understanding knowledge distillation in non-autoregressive machine translation","author":"Zhou","year":"2020"}],"event":{"name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","location":"Yokohama, Japan","start":{"date-parts":[[2024,5,13]]},"end":{"date-parts":[[2024,5,17]]}},"container-title":["2024 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10609961\/10609862\/10611196.pdf?arnumber=10611196","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,11]],"date-time":"2024-08-11T04:06:46Z","timestamp":1723349206000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10611196\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10611196","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}