{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T19:54:25Z","timestamp":1778270065782,"version":"3.51.4"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,9,27]],"date-time":"2021-09-27T00:00:00Z","timestamp":1632700800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,9,27]],"date-time":"2021-09-27T00:00:00Z","timestamp":1632700800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,9,27]],"date-time":"2021-09-27T00:00:00Z","timestamp":1632700800000},"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":[[2021,9,27]]},"DOI":"10.1109\/iros51168.2021.9636711","type":"proceedings-article","created":{"date-parts":[[2021,12,16]],"date-time":"2021-12-16T20:45:38Z","timestamp":1639687538000},"page":"3375-3382","source":"Crossref","is-referenced-by-count":7,"title":["APEX: Unsupervised, Object-Centric Scene Segmentation and Tracking for Robot Manipulation"],"prefix":"10.1109","author":[{"given":"Yizhe","family":"Wu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Oiwi Parker","family":"Jones","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Martin","family":"Engelcke","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ingmar","family":"Posner","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.2307\/2284239"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917700714"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00255"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007665907178"},{"key":"ref31","article-title":"Tracking Objects as Points","author":"zhou","year":"2020","journal-title":"European Conference on Computer Vision (ECCV)"},{"key":"ref30","article-title":"GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields","author":"niemeyer","year":"2020"},{"key":"ref37","article-title":"GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinement","author":"engelcke","year":"2021"},{"key":"ref36","first-page":"2052","article-title":"Dropout inference in bayesian neural networks with alpha-divergences","author":"li","year":"2017","journal-title":"Int Conference on Machine Learning"},{"key":"ref35","article-title":"Categorical Reparameterization with Gumbel-Softmax","author":"jang","year":"2017","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref34","first-page":"802","article-title":"Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting","author":"xingjian","year":"2015","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref10","article-title":"Sequential Attend, Infer, Repeat: Generative Modelling of Moving Objects","author":"kosiorek","year":"2018","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref11","article-title":"Entity Abstraction in Visual Model-Based Reinforcement Learning","author":"veerapaneni","year":"2020","journal-title":"Conference on Robot Learning (CoRL)"},{"key":"ref40","article-title":"Unmasking the Inductive Biases of Unsupervised Object Representations for Video Sequences","author":"weis","year":"2020"},{"key":"ref12","article-title":"Representation Matters: Improving Perception and Exploration for Robotics","author":"wulfmeier","year":"2020"},{"key":"ref13","article-title":"COBRA: Data-Efficient Model-Based RL through Unsupervised Object Discovery and Curiosity-Driven Exploration","author":"watters","year":"2019"},{"key":"ref14","article-title":"Auto-Encoding Variational Bayes","author":"kingma","year":"2014","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref15","article-title":"Stochastic Backpropagation and Approximate Inference in Deep Generative Models","author":"rezende","year":"2014","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref16","article-title":"Spatial Transformer Networks","author":"jaderberg","year":"2015","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref17","article-title":"Tagger: Deep Unsupervised Perceptual Grouping","author":"greff","year":"2016","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref18","article-title":"Neural Expectation Maximization","author":"greff","year":"2017","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref19","article-title":"Relational Neural Expectation Maximization: Unsupervised Discovery of Objects and their Interactions","author":"van steenkiste","year":"2018"},{"key":"ref28","article-title":"RELATE: Physically Plausible Multi-Object Scene Synthesis Using Structured Latent Spaces","author":"ehrhardt","year":"2020","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref27","article-title":"IROS 2020: Open Cloud Robot Table Organization Challenge (OCRTOC)","year":"2020"},{"key":"ref3","article-title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","author":"ren","year":"2015"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013412"},{"key":"ref29","article-title":"BlockGAN: Learning 3D Object-aware Scene Representations from Unlabelled Images","author":"nguyen-phuoc","year":"2020"},{"key":"ref5","article-title":"MONet: Unsupervised Scene Decomposition and Representation","author":"burgess","year":"2019"},{"key":"ref8","article-title":"Multi-Object Representation Learning with Iterative Variational Inference","author":"greff","year":"2019","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref7","article-title":"GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations","author":"engelcke","year":"2020","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref9","article-title":"SCALOR: Generative World Models with Scalable Object Representations","author":"jiang","year":"2020","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref20","article-title":"Object-Centric Learning with Slot Attention","author":"locatello","year":"2020","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref22","article-title":"Efficient Inference in Occlusion-Aware Generative Models of Images","author":"huang","year":"2015"},{"key":"ref21","article-title":"Attend, Infer, Repeat: Fast Scene Understanding with Generative Models","author":"eslami","year":"2016","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref24","article-title":"Objects as Points","author":"zhou","year":"2019"},{"key":"ref42","article-title":"Adam: A Method for Stochastic Optimization","author":"kingma","year":"2015","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref23","article-title":"Scaling Data-Driven Robotics with Reward Sketching and Batch Reinforcement Learning","author":"cabi","year":"2019"},{"key":"ref41","article-title":"MOT16: A Benchmark for Multi-Object Tracking","author":"milan","year":"2016"},{"key":"ref26","first-page":"6140","article-title":"Improving generative imagination in object-centric world models","author":"lin","year":"2020","journal-title":"Int Conference on Machine Learning"},{"key":"ref25","article-title":"SPACE: Unsupervised Object-Oriented Scene Representation via Spatial Attention and Decomposition","author":"lin","year":"2020","journal-title":"International Conference on Learning Representations (ICLR)"}],"event":{"name":"2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Prague, Czech Republic","start":{"date-parts":[[2021,9,27]]},"end":{"date-parts":[[2021,10,1]]}},"container-title":["2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9635848\/9635849\/09636711.pdf?arnumber=9636711","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T16:54:43Z","timestamp":1652201683000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9636711\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,27]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/iros51168.2021.9636711","relation":{},"subject":[],"published":{"date-parts":[[2021,9,27]]}}}