{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:46:15Z","timestamp":1777657575792,"version":"3.51.4"},"reference-count":46,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T00:00:00Z","timestamp":1685318400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T00:00:00Z","timestamp":1685318400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["62206288"],"award-info":[{"award-number":["62206288"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,5,29]]},"DOI":"10.1109\/icra48891.2023.10160742","type":"proceedings-article","created":{"date-parts":[[2023,7,4]],"date-time":"2023-07-04T17:20:56Z","timestamp":1688491256000},"page":"4945-4952","source":"Crossref","is-referenced-by-count":9,"title":["Unseen Object Instance Segmentation with Fully Test-time RGB-D Embeddings Adaptation"],"prefix":"10.1109","author":[{"given":"Lu","family":"Zhang","sequence":"first","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siqi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xu","family":"Yang","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hong","family":"Qiao","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiyong","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793917"},{"key":"ref35","first-page":"818","article-title":"Visualizing and understanding convo-lutional networks","author":"zeiler","year":"2014","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6385661"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71246-8_49"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.155"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811646"},{"key":"ref36","first-page":"3","article-title":"Cbam: Convolutional block attention module","author":"woo","year":"2018","journal-title":"European Conference on Computer Vision (ECCV)"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00398"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref11","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2019.2952939"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"ref32","article-title":"What makes multi-modal learning better than single (provably)","volume":"34","author":"huang","year":"2021","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref2","article-title":"Learning rgb-d feature embeddings for unseen object instance segmentation","author":"xiang","year":"2020","journal-title":"Conference on Robot Learning (CoRL)"},{"key":"ref1","article-title":"The best of both modes: Separately leveraging rgb and depth for unseen object instance segmentation","author":"xie","year":"2019","journal-title":"Conference on Robot Learning (CoRL)"},{"key":"ref17","article-title":"Neural network-based clustering using pair-wise constraints","author":"hsu","year":"2015","journal-title":"Workshop at International Conference on Learning Representations (ICLR)"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2018.09.015"},{"key":"ref16","first-page":"132","article-title":"Deep clustering for unsupervised learning of visual features","author":"caron","year":"2018","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref38","first-page":"4835","article-title":"Deep multimodal fusion by channel exchanging","volume":"33","author":"wang","year":"2020","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref19","article-title":"Multi-class classification without multi-class labels","author":"hsu","year":"2019","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref18","article-title":"Learning to cluster in order to transfer across domains and tasks","author":"hsu","year":"2018","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00990"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_9"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW54805.2022.00027"},{"key":"ref26","article-title":"Ttt++: When does self-supervised test-time training fail or thrive?","volume":"34","author":"liu","year":"2021","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref25","first-page":"9229","article-title":"Test-time training with self-supervision for generalization under distribution shifts","author":"sun","year":"2020","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00849"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.03.005"},{"key":"ref41","first-page":"8645","article-title":"Channel equilibrium networks for learning deep representation","author":"shao","year":"2020","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref22","first-page":"9865","article-title":"Invariant information clus-tering for unsupervised image classification and segmentation","author":"ji","year":"2019","journal-title":"Proceedings of the IEEE International Conference on Computer Vision (ICCV)"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_9"},{"key":"ref21","article-title":"Autonovel: Automatically discovering and learning novel visual categories","author":"han","year":"2021","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00753"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/34.1000236"},{"key":"ref27","article-title":"Test-time adaptation to distribution shift by confidence maximization and input transformation","author":"mummadi","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2010.522"},{"key":"ref8","article-title":"Tent: Fully test-time adaptation by entropy minimization","author":"wang","year":"2020","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1948.tb01338.x"},{"key":"ref9","author":"hinton","year":"0","journal-title":"Distilling the knowledge in a neural network"},{"key":"ref4","article-title":"Unseen object in-stance segmentation for robotic environments","author":"xie","year":"2021","journal-title":"IEEE Transactions on Robotics"},{"key":"ref3","article-title":"Rice: Refining instance masks in cluttered environments with graph neural networks","author":"xie","year":"2021","journal-title":"Conference on Robot Learning (CoRL)"},{"key":"ref6","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"}],"event":{"name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","location":"London, United Kingdom","start":{"date-parts":[[2023,5,29]]},"end":{"date-parts":[[2023,6,2]]}},"container-title":["2023 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10160211\/10160212\/10160742.pdf?arnumber=10160742","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,24]],"date-time":"2023-07-24T17:32:40Z","timestamp":1690219960000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10160742\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,29]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/icra48891.2023.10160742","relation":{},"subject":[],"published":{"date-parts":[[2023,5,29]]}}}