{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T17:42:55Z","timestamp":1772905375718,"version":"3.50.1"},"reference-count":33,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T00:00:00Z","timestamp":1648771200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T00:00:00Z","timestamp":1648771200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T00:00:00Z","timestamp":1648771200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"CIFAR AI Chair at the Vector Institute for AI"},{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2022,4]]},"DOI":"10.1109\/lra.2022.3150855","type":"journal-article","created":{"date-parts":[[2022,2,14]],"date-time":"2022-02-14T23:03:13Z","timestamp":1644879793000},"page":"4924-4930","source":"Crossref","is-referenced-by-count":32,"title":["PlaTe: Visually-Grounded Planning With Transformers in Procedural Tasks"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5633-1739","authenticated-orcid":false,"given":"Jiankai","family":"Sun","sequence":"first","affiliation":[{"name":"School of Engineering, Stanford University, Stanford, CA, USA"}]},{"given":"De-An","family":"Huang","sequence":"additional","affiliation":[{"name":"Nvidia, Cupertino, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2858-1121","authenticated-orcid":false,"given":"Bo","family":"Lu","sequence":"additional","affiliation":[{"name":"Robotics and Microsystems Center, School of Mechanical and Electric Engineering, Soochow University, Suzhou, Jiangsu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3625-6679","authenticated-orcid":false,"given":"Yun-Hui","family":"Liu","sequence":"additional","affiliation":[{"name":"Chinese University of Hong Kong, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4030-0684","authenticated-orcid":false,"given":"Bolei","family":"Zhou","sequence":"additional","affiliation":[{"name":"University of California, Los Angeles, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0482-4296","authenticated-orcid":false,"given":"Animesh","family":"Garg","sequence":"additional","affiliation":[{"name":"Nvidia, Cupertino, CA, USA"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref10","first-page":"4732","article-title":"Universal planning networks: Learning generalizable representations for visuomotor control","author":"srinivas","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref12","article-title":"Egocentric human trajectory forecasting with a wearable camera and multi-modal fusion","author":"qiu","year":"2021"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00426"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01532"},{"key":"ref15","article-title":"Towards automatic learning of procedures from web instructional videos","author":"zhou","year":"0","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00365"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_9"},{"key":"ref18","first-page":"706","article-title":"A persistent spatial semantic representation for high-level natural language instruction execution","author":"blukis","year":"0","journal-title":"Proc Conf Robot Learn"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460689"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00346"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref27","first-page":"1290","article-title":"Empirical analysis of beam search performance degradation in neural sequence models","author":"cohen","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref3","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref6","first-page":"2555","article-title":"Learning latent dynamics for planning from pixels","author":"hafner","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref29","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref5","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"chung","year":"2014","journal-title":"NIPS *2010 Workshop on Deep Learning"},{"key":"ref8","first-page":"6","article-title":"On the model-based stochastic value gradient for continuous reinforcement learning learning","author":"amos","year":"0","journal-title":"Proc 3rd Conf Learn Dyn Control"},{"key":"ref7","first-page":"42","article-title":"Dynamics learning with cascaded variational inference for multi-step manipulation","volume":"100","author":"fang","year":"2020","journal-title":"CoRL"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_20"},{"key":"ref9","first-page":"8733","article-title":"Learning plannable representations with causal infogan","volume":"31","author":"kurutach","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-32552-1_14"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00876"},{"key":"ref22","article-title":"Modular action concept grounding in semantic video prediction","author":"yu","year":"2020"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.234"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00367"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"ref26","first-page":"1197","article-title":"Uncertainty-aware anticipation of activities","author":"y","year":"0","journal-title":"Proc IEEE\/CVF Int Conf Comput Vis Workshops"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00095"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/9647862\/09712373.pdf?arnumber=9712373","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T20:52:47Z","timestamp":1653339167000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9712373\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4]]},"references-count":33,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/lra.2022.3150855","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,4]]}}}