{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T12:59:30Z","timestamp":1793365170771,"version":"4.5.0"},"reference-count":46,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,1]],"date-time":"2021-06-01T00:00:00Z","timestamp":1622505600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,1]],"date-time":"2021-06-01T00:00:00Z","timestamp":1622505600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001321","name":"National Research Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001321","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001321","name":"National Research Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001321","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,6]]},"DOI":"10.1109\/cvpr46437.2021.00309","type":"proceedings-article","created":{"date-parts":[[2021,11,2]],"date-time":"2021-11-02T21:56:02Z","timestamp":1635890162000},"page":"3073-3082","source":"Crossref","is-referenced-by-count":3,"title":["GATSBI: Generative Agent-centric Spatio-temporal Object Interaction"],"prefix":"10.1109","author":[{"given":"Cheol-Hui","family":"Min","sequence":"first","affiliation":[{"name":"Seoul National University,Dept. of Electrical and Computer Engineering,Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinseok","family":"Bae","sequence":"additional","affiliation":[{"name":"Seoul National University,Dept. of Electrical and Computer Engineering,Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junho","family":"Lee","sequence":"additional","affiliation":[{"name":"Seoul National University,Dept. of Electrical and Computer Engineering,Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Young Min","family":"Kim","sequence":"additional","affiliation":[{"name":"Seoul National University,Dept. of Electrical and Computer Engineering,Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Relational neural expectation maximization: Unsupervised discovery of objects and their interactions","author":"van steenkiste","year":"2018"},{"key":"ref38","author":"unterthiner","year":"2018","journal-title":"Towards accurate generative models of video A new metric and challenges"},{"key":"ref33","author":"redmon","year":"2018","journal-title":"YOLOv3 An Incremental Improvement"},{"key":"ref32","first-page":"92","article-title":"Unsupervised learning of object structure and dynamics from videos","author":"minderer","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref31","article-title":"Space: Unsupervised object-oriented scene representation via spatial attention and decomposition","author":"lin","year":"2020"},{"key":"ref30","article-title":"Improving generative imagination in object-centric world models","author":"lin","year":"2020"},{"key":"ref37","first-page":"5966","article-title":"Faster attend-infer-repeat with tractable probabilistic models","author":"stelzner","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref36","article-title":"R-sqair: relational sequential attend, infer, repeat","author":"stani?","year":"2019"},{"key":"ref35","first-page":"843","article-title":"Unsupervised learning of video representations using lstms","author":"srivastava","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref34","article-title":"Coppeliasim (formerly v-rep): a versatile and scalable robot simulation framework","author":"rohmer","year":"2013","journal-title":"Proc of the International Conference on Intelligent Robots and Systems (IROS)"},{"key":"ref10","article-title":"Self-supervised visual planning with temporal skip connections","author":"ebert","year":"2017"},{"key":"ref40","article-title":"Entity abstraction in visual model-based reinforcement learning","author":"veerapaneni","year":"2019"},{"key":"ref11","article-title":"Genesis: Generative scene inference and sampling with object-centric latent representations","author":"engelcke","year":"2019"},{"key":"ref12","first-page":"3225","article-title":"Attend, infer, repeat: Fast scene understanding with generative models","author":"eslami","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487173"},{"key":"ref14","first-page":"2199","article-title":"Sequential neural models with stochastic layers","author":"fraccaro","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref15","article-title":"Multi-object represen-tation learning with iterative variational inference","author":"greff","year":"2019"},{"key":"ref16","first-page":"6691","article-title":"Neural expectation maximization","author":"greff","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref17","author":"ha","year":"2018","journal-title":"World Models"},{"key":"ref18","article-title":"Dream to control: Learning behaviors by latent imagination","author":"hafner","year":"2019"},{"key":"ref19","author":"hafner","year":"2018","journal-title":"Learning latent dynamics for planning from pixels"},{"key":"ref28","first-page":"10724","article-title":"Unsupervised learning of object keypoints for perception and control","author":"kulkarni","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref4","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"chung","year":"2014"},{"key":"ref27","author":"kossen","year":"2019","journal-title":"Structured object-aware physics prediction for video modeling and planning"},{"key":"ref3","author":"burgess","year":"2019","journal-title":"Monet Unsupervised scene decomposition and representation"},{"key":"ref6","article-title":"Exploiting spatial invariance for scalable unsupervised object tracking","author":"crawford","year":"2019"},{"key":"ref29","article-title":"Stochastic latent actor-critic: Deep reinforcement learning with a latent variable model","author":"lee","year":"2019"},{"key":"ref5","first-page":"2980","article-title":"A recurrent latent variable model for sequential data","author":"chung","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref8","article-title":"Probabilistic recurrent state-space models","author":"doerr","year":"2018"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013412"},{"key":"ref2","article-title":"Learning physical graph representations from visual scenes","author":"bear","year":"2020"},{"key":"ref9","article-title":"Robustness via retrying: Closed-loop robotic manipulation with self-supervised learning","author":"ebert","year":"2018"},{"key":"ref1","article-title":"and Sergey Levine. Stochastic variational video prediction","author":"babaeizadeh","year":"2017"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref45","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":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2974707"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref42","article-title":"Cobra: Data-efficient model-based rl through unsupervised object discovery and curiosity-driven exploration","author":"watters","year":"2019"},{"key":"ref24","article-title":"Deep variational bayes filters: Unsupervised learning of state space models from raw data","author":"karl","year":"2016"},{"key":"ref41","first-page":"2746","article-title":"Embed to control: A locally linear latent dynamics model for control from raw images","author":"watter","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref23","article-title":"Scalor: Generative world models with scalable object representations","author":"jiang","year":"2020","journal-title":"ICLRE"},{"key":"ref44","article-title":"Unsupervised video decomposition using spatio-temporal iterative inference","author":"zablotskaia","year":"2020"},{"key":"ref26","first-page":"8606","article-title":"Sequential attend, infer, repeat: Generative modelling of moving objects","author":"kosiorek","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref43","article-title":"Unmasking the inductive biases of unsupervised object representations for video sequences","author":"weis","year":"2020"},{"key":"ref25","article-title":"Auto-encoding variational bayes","author":"kingma","year":"2013"}],"event":{"name":"2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","location":"Nashville, TN, USA","start":{"date-parts":[[2021,6,20]]},"end":{"date-parts":[[2021,6,25]]}},"container-title":["2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9577055\/9577056\/09578878.pdf?arnumber=9578878","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,2]],"date-time":"2022-08-02T23:18:37Z","timestamp":1659482317000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9578878\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/cvpr46437.2021.00309","relation":{},"subject":[],"published":{"date-parts":[[2021,6]]}}}