{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:25:33Z","timestamp":1740101133847,"version":"3.37.3"},"reference-count":48,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,7,9]],"date-time":"2022-07-09T00:00:00Z","timestamp":1657324800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,9]],"date-time":"2022-07-09T00:00:00Z","timestamp":1657324800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001942","name":"CHIST-ERA","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001942","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,7,9]]},"DOI":"10.1109\/icarm54641.2022.9959321","type":"proceedings-article","created":{"date-parts":[[2022,11,29]],"date-time":"2022-11-29T19:31:50Z","timestamp":1669750310000},"page":"37-44","source":"Crossref","is-referenced-by-count":1,"title":["VP-GO: A \u2018Light\u2019 Action-Conditioned Visual Prediction Model for Grasping Objects"],"prefix":"10.1109","author":[{"given":"Anji","family":"Ma","sequence":"first","affiliation":[{"name":"Beijing Institute of Technology,School of Mechatronical Engineering,Beijing,China,100081"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yoann","family":"Fleytoux","sequence":"additional","affiliation":[{"name":"Inria, University of Lorraine, CNRS,Loria,France,F-54000"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jean-Baptiste","family":"Mouret","sequence":"additional","affiliation":[{"name":"Inria, University of Lorraine, CNRS,Loria,France,F-54000"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Serena","family":"Ivaldi","sequence":"additional","affiliation":[{"name":"Inria, University of Lorraine, CNRS,Loria,France,F-54000"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/BF02532251"},{"key":"ref38","first-page":"1747","article-title":"Pixel recurrent neural networks","author":"van den oord","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.230"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3126686.3126737"},{"key":"ref31","article-title":"Transformation-based models of video sequences","author":"van amersfoort","year":"2017","journal-title":"arXiv preprint arXiv 1701 08241"},{"key":"ref30","article-title":"Visual dynamics: Probabilistic future frame synthesis via cross convolutional networks","volume":"29","author":"xue","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref37","article-title":"Pixelcnn ++: A pixelcnn implementation with discretized logistic mixture likelihood and other modifications","author":"salimans","year":"2017","journal-title":"ICLRE"},{"key":"ref36","article-title":"Stochastic variational video prediction","author":"babaeizadeh","year":"2017","journal-title":"arXiv preprint arXiv 1710 11252"},{"key":"ref35","article-title":"Auto-encoding variational bayes","author":"kingma","year":"2013","journal-title":"arXiv preprint arXiv 1312 6114"},{"journal-title":"Probabilistic models for some intelligence and attainment tests","year":"1993","author":"rasch","key":"ref34"},{"key":"ref10","article-title":"High fidelity video prediction with large stochastic recurrent neural networks","volume":"abs 1911 1655","author":"villegas","year":"2019","journal-title":"CoRR"},{"key":"ref40","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"arXiv preprint arXiv 1706 03762"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00235"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2012.6651528"},{"key":"ref13","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-32552-1","author":"siciliano","year":"2016","journal-title":"Springer Handbook of Robotics"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2009.5152709"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989165"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICHR.2009.5379566"},{"key":"ref17","article-title":"Driving policy transfer via modularity and abstraction","volume":"abs 1804 9364","author":"muller","year":"2018","journal-title":"CoRR"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-012-9306-z"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9378"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1016\/B978-0-444-53859-8.00003-5","article-title":"The cross-entropy method for optimization","volume":"31","author":"botev","year":"2013","journal-title":"Handbook of Statistics"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref27","volume":"1","author":"goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref3","article-title":"Visual foresight: Model-based deep reinforcement learning for vision-based robotic control","author":"ebert","year":"2018","journal-title":"arXiv preprint arXiv 1812 08942"},{"key":"ref6","article-title":"Unsupervised learning for physical interaction through video prediction","volume":"29","author":"finn","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.281"},{"key":"ref5","first-page":"885","article-title":"Robonet: Large-scale multi-robot learning","volume":"abs 1910 11215","author":"dasari","year":"2019","journal-title":"CoRR"},{"key":"ref8","first-page":"2786","article-title":"Deep visual foresight for planning robot motion","volume":"abs 1610 696","author":"finn","year":"2016","journal-title":"CoRR"},{"key":"ref7","first-page":"1174","article-title":"Stochastic video generation with a learned prior","author":"denton","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2021.3066040"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2010.5509544"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2011.2162271"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref20","first-page":"4238","article-title":"Learning synergies between pushing and grasping with selfsupervised deep reinforcement learning","author":"zeng","year":"2018"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1049\/el:20080522"},{"key":"ref48","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv preprint arXiv 1409 1556"},{"key":"ref22","first-page":"3406","article-title":"Supersizing self-supervision: Learning to grasp from 50k tries and 700 robot hours","author":"pinto","year":"2015"},{"article-title":"Fvd: A new metric for video generation","year":"2019","author":"unterthiner","key":"ref47"},{"key":"ref21","first-page":"1316","article-title":"Real-time grasp detection using convolutional neural networks","volume":"abs 1412 3128","author":"redmon","year":"2014","journal-title":"CoRR"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989324"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-017-0468-y"},{"key":"ref41","article-title":"Scaling autoregressive video models","author":"weissenborn","year":"2019","journal-title":"arXiv preprint arXiv 1906 02916"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.058"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref26","first-page":"7444","article-title":"Solar: Deep structured representations for model-based reinforcement learning","author":"zhang","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00770"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2009.5152834"}],"event":{"name":"2022 International Conference on Advanced Robotics and Mechatronics (ICARM)","start":{"date-parts":[[2022,7,9]]},"location":"Guilin, China","end":{"date-parts":[[2022,7,11]]}},"container-title":["2022 International Conference on Advanced Robotics and Mechatronics (ICARM)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9959088\/9959097\/09959321.pdf?arnumber=9959321","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,19]],"date-time":"2022-12-19T20:02:09Z","timestamp":1671480129000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9959321\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,9]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/icarm54641.2022.9959321","relation":{},"subject":[],"published":{"date-parts":[[2022,7,9]]}}}