{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:47:29Z","timestamp":1778082449163,"version":"3.51.4"},"reference-count":76,"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\/icra57147.2024.10610695","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"15424-15432","source":"Crossref","is-referenced-by-count":4,"title":["Composing Pre-Trained Object-Centric Representations for Robotics From \"What\" and \"Where\" Foundation Models"],"prefix":"10.1109","author":[{"given":"Junyao","family":"Shi","sequence":"first","affiliation":[{"name":"University of Pennsylvania,Computer and Information Science"}]},{"given":"Jianing","family":"Qian","sequence":"additional","affiliation":[{"name":"University of Pennsylvania,Computer and Information Science"}]},{"given":"Yecheng Jason","family":"Ma","sequence":"additional","affiliation":[{"name":"University of Pennsylvania,Computer and Information Science"}]},{"given":"Dinesh","family":"Jayaraman","sequence":"additional","affiliation":[{"name":"University of Pennsylvania,Computer and Information Science"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref2","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref3","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref6","article-title":"Masked visual pre-training for motor control","author":"Xiao","year":"2022"},{"key":"ref7","first-page":"1303","article-title":"Learning language-conditioned robot behavior from offline data and crowd-sourced annotation","volume-title":"Conference on Robot Learning","author":"Nair"},{"key":"ref8","article-title":"Vip: Towards universal visual reward and representation via value-implicit pre-training","author":"Ma","year":"2022"},{"key":"ref9","article-title":"Liv: Language-image representations and rewards for robotic control","author":"Ma","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/0166-2236(92)90344-8"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/0959-4388(94)90066-3"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2011.08.005"},{"key":"ref15","article-title":"Object-centric learning with slot attention","author":"Locatello","year":"2020"},{"key":"ref16","article-title":"Monet: Unsupervised scene decomposition and representation","author":"Burgess","year":"2019"},{"key":"ref17","article-title":"Genesis-v2: Inferring unordered object representations without iterative refinement","author":"Engelcke","year":"2021","journal-title":"Neural Information Processing Systems"},{"key":"ref18","article-title":"Space: Unsupervised object-oriented scene representation via spatial attention and decomposition","author":"Lin","year":"2020"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00328"},{"key":"ref20","article-title":"Contrastive learning of structured world models","author":"Kipf","year":"2019"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461196"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794224"},{"key":"ref23","article-title":"Graph inverse reinforcement learning from diverse videos","volume-title":"Conference on Robot Learning","author":"Kumar"},{"key":"ref24","article-title":"Viola: Imitation learning for vision-based manipulation with object proposal priors","author":"Zhu","year":"2022"},{"key":"ref25","article-title":"Graph-structured visual imitation","volume-title":"Conference on Robot Learning","author":"Sieb"},{"key":"ref26","article-title":"Unsupervised learning of object keypoints for perception and control","author":"Kulkarni","year":"2019"},{"key":"ref27","article-title":"Unsupervised learning of object structure and dynamics from videos","author":"Minderer","year":"2019"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref29","article-title":"Segment everything everywhere all at once","author":"Zou","year":"2023"},{"key":"ref30","article-title":"R3m: A universal visual representation for robot manipulation","author":"Nair","year":"2022"},{"key":"ref31","first-page":"416","article-title":"Real-world robot learning with masked visual pre-training","volume-title":"Conference on Robot Learning","author":"Radosavovic"},{"key":"ref32","article-title":"Where are we in the search for an artificial visual cortex for embodied intelligence?","volume-title":"Workshop on Reincarnating Reinforcement Learning at ICLR 2023","author":"Majumdar"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/icra48891.2023.10160888"},{"key":"ref34","article-title":"A perspective on objects and systematic generalization in model-based rl","author":"van Steenkiste","year":"2019"},{"key":"ref35","article-title":"On the binding problem in artificial neural networks","author":"Greff","year":"2020"},{"key":"ref36","first-page":"1","article-title":"Building machines that learn and think like people","author":"Lake","year":"2016","journal-title":"en, Behav. Brain Sci"},{"key":"ref37","first-page":"5221","article-title":"Generalization and robustness implications in object-centric learning","volume-title":"Proceedings of the 39th International Conference on Machine Learning","volume":"162","author":"Dittadi"},{"key":"ref38","article-title":"An investigation into pre-training object-centric represen-tations for reinforcement learning","author":"Yoon","year":"2023"},{"key":"ref39","article-title":"Con-ditional object-centric learning from video","author":"Kipf","year":"2021"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.009"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981307"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.029"},{"key":"ref43","article-title":"Reconstruction bottlenecks in Object-Centric generative models","author":"Engelcke"},{"key":"ref44","article-title":"Inductive biases for object-centric representations in the presence of complex textures","volume-title":"UAI 2022 Workshop on Causal Representation Learning","author":"Papa"},{"key":"ref45","article-title":"Promising or elusive? unsupervised object segmentation from real-world single images","author":"Yang","year":"2022","journal-title":"NeurIPS"},{"key":"ref46","article-title":"Deep vit features as dense visual descriptors","author":"Amir","year":"2021"},{"key":"ref47","article-title":"The hungarian method for the assignment problem","volume":"52","author":"Kuhn","year":"1955","journal-title":"Naval Research Logistics (NRL)"},{"key":"ref48","article-title":"Deep sets","volume":"30","author":"Zaheer","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref50","article-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf","year":"2016"},{"key":"ref51","article-title":"Graph attention networks","author":"Veli\u010dkovi\u0107","year":"2017"},{"key":"ref52","article-title":"Policy architectures for compositional generalization in control","author":"Zhou","year":"2022"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1023\/b:visi.0000029664.99615.94"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref55","article-title":"Deep object pose estimation for semantic robotic grasping of household objects","volume-title":"Conference on Robot Learning","author":"Tremblay"},{"key":"ref56","article-title":"Object-centric forward modeling for model predictive control","author":"Ye","year":"2019"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2965875"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561548"},{"key":"ref59","article-title":"Pdsketch: Integrated planning domain programming and learning","author":"Mao","year":"2023"},{"key":"ref60","article-title":"Vima: General robot manipulation with multimodal prompts","author":"Jiang","year":"2022"},{"key":"ref61","article-title":"Learning neuro-symbolic skills for bilevel planning","author":"Silver","year":"2022"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2844175"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref64","article-title":"Focus: Object-centric world models for robotics manipulation","author":"Ferraro","year":"2023"},{"key":"ref65","article-title":"Pave the way to grasp anything: Transferring foundation models for universal pick-place robots","author":"Yang","year":"2023"},{"key":"ref66","article-title":"Learning generalizable manipulation policies with object-centric 3d representations","volume-title":"7th Annual Conference on Robot Learning","author":"Zhu"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/icra57147.2024.10610234"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610131"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2974707"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3140817"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.2307\/2284239"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/BF01908075"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.324"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref76","article-title":"What matters in learning from offline human demonstrations for robot manipulation","author":"Mandlekar","year":"2021"}],"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\/10610695.pdf?arnumber=10610695","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,10]],"date-time":"2024-08-10T05:21:25Z","timestamp":1723267285000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10610695\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":76,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10610695","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}