{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T22:35:37Z","timestamp":1761172537372,"version":"build-2065373602"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T00:00:00Z","timestamp":1757980800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T00:00:00Z","timestamp":1757980800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100018693","name":"Horizon Europe","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100018693","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,9,16]]},"DOI":"10.1109\/icdl63968.2025.11204356","type":"proceedings-article","created":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T17:07:41Z","timestamp":1761066461000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["Push, See, Predict: Emergent Perception Through Intrinsically Motivated Play"],"prefix":"10.1109","author":[{"given":"Orestis","family":"Konstantaropoulos","sequence":"first","affiliation":[{"name":"Robotics Institute, Athena Research Center,Maroussi,Greece,15125"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mehdi","family":"Khamassi","sequence":"additional","affiliation":[{"name":"Sorbonne University,Institute of Intelligent Systems and Robotics, CNRS,Paris,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Petros","family":"Maragos","sequence":"additional","affiliation":[{"name":"RI\/Athena RC,Maroussi,Greece,15125"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"George","family":"Retsinas","sequence":"additional","affiliation":[{"name":"RI\/AthenaRC,Maroussi,Greece,15125"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.5555\/2999134.2999257"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1126\/science.1223416"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2015.09.010"},{"volume-title":"A path towards autonomous machine intelligence","year":"2022","author":"LeCun","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2012.05.008"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2016.2538961"},{"key":"ref8","article-title":"Monet: Unsupervised scene decomposition and representation","volume":"abs\/1901.11390","author":"Burgess","year":"2019","journal-title":"CoRR"},{"article-title":"Multi-object representation learning with iterative variational inference","volume-title":"Proceedings of the 36th International Conference on Machine Learning, ICML","author":"Greff","key":"ref9"},{"article-title":"GENESIS: generative scene inference and sampling with object-centric latent representations","volume-title":"8th International Conference on Learning Representations, ICLR","author":"Engelcke","key":"ref10"},{"article-title":"Sequential attend, infer, repeat: Generative modelling of moving objects","volume-title":"Advances in Neural Information Processing Systems, NeurIPS","author":"Kosiorek","key":"ref11"},{"article-title":"SCALOR: generative world models with scalable object representations","volume-title":"8th International Conference on Learning Representations, ICLR","author":"Jiang","key":"ref12"},{"article-title":"SPACE: unsupervised object-oriented scene representation via spatial attention and decomposition","volume-title":"8th International Conference on Learning Representations, ICLR","author":"Lin","key":"ref13"},{"article-title":"Self-supervised visual reinforcement learning with object-centric representations","volume-title":"International Conference on Learning Representations","author":"Zadaianchuk","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2021.3058954"},{"article-title":"Learning handeye coordination for robotic grasping with large-scale data collection","volume-title":"International Symposium on Experimental Robotics","author":"Levine","key":"ref16"},{"key":"ref17","article-title":"Qt-opt: Scalable deep reinforcement learning for vision-based robotic manipulation","volume":"abs\/1806.10293","author":"Kalashnikov","year":"2018","journal-title":"CoRR"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"article-title":"Self-supervised exploration via disagreement","volume-title":"Proceedings of the 36th International Conference on Machine Learning","author":"Pathak","key":"ref19"},{"key":"ref20","article-title":"Behavior from the void: Unsupervised active pre-training","author":"Liu","year":"2021","journal-title":"Neural Information Processing Systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2009.5152393"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2003.1249191"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2014.2334912"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_1"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00276"},{"key":"ref26","article-title":"Curious exploration via structured world models yields zero-shot object manipulation","author":"Sancaktar","year":"2022","journal-title":"Neural Information Processing Systems"},{"key":"ref27","article-title":"COBRA: data-efficient model-based RL through unsupervised object discovery and curiosity-driven exploration","volume":"abs\/1905.09275","author":"Watters","year":"2019","journal-title":"CoRR"},{"article-title":"Object-centric learning with slot attention","volume-title":"NeuIPS","author":"Locatello","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/d14-1179"},{"key":"ref30","article-title":"Spatial broadcast decoder: A simple architecture for learning disentangled representations in vaes","volume":"abs\/1901.07017","author":"Watters","year":"2019","journal-title":"CoRR"},{"article-title":"Conditional object-centric learning from video","volume-title":"The Tenth International Conference on Learning Representations, ICLR 2022","author":"Kipf","key":"ref31"},{"article-title":"Contrastive learning of structured world models","volume-title":"International Conference on Learning Representations","author":"Kipf","key":"ref32"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.5555\/3016100.3016191"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/iros.2013.6696520"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1093\/cercor\/bht318"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1162\/1064546053278973"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1207\/s15516709cog1401_3"}],"event":{"name":"2025 IEEE International Conference on Development and Learning (ICDL)","start":{"date-parts":[[2025,9,16]]},"location":"Prague, Czech Republic","end":{"date-parts":[[2025,9,19]]}},"container-title":["2025 IEEE International Conference on Development and Learning (ICDL)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11204361\/11204347\/11204356.pdf?arnumber=11204356","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T05:16:25Z","timestamp":1761110185000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11204356\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,16]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icdl63968.2025.11204356","relation":{},"subject":[],"published":{"date-parts":[[2025,9,16]]}}}