{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,28]],"date-time":"2025-06-28T05:42:23Z","timestamp":1751089343639,"version":"3.28.0"},"reference-count":48,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icra40945.2020.9196567","type":"proceedings-article","created":{"date-parts":[[2020,9,15]],"date-time":"2020-09-15T17:25:46Z","timestamp":1600190746000},"page":"10473-10479","source":"Crossref","is-referenced-by-count":8,"title":["Online Learning of Object Representations by Appearance Space Feature Alignment"],"prefix":"10.1109","author":[{"given":"Soren","family":"Pirk","sequence":"first","affiliation":[]},{"given":"Mohi","family":"Khansari","sequence":"additional","affiliation":[]},{"given":"Yunfei","family":"Bai","sequence":"additional","affiliation":[]},{"given":"Corey","family":"Lynch","sequence":"additional","affiliation":[]},{"given":"Pierre","family":"Sermanet","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","article-title":"Unsupervised object discovery: A comparison","author":"tuytelaars","year":"2009","journal-title":"IJCV"},{"key":"ref38","first-page":"1","article-title":"Unsupervised learning of object frames by dense equivariant image labelling","author":"thewlis","year":"2017","journal-title":"NIPS"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2016.2634089"},{"key":"ref32","first-page":"1284","article-title":"The moped framework: Object recognition and pose estimation for manipulation","volume":"30","author":"romea","year":"2011","journal-title":"IJRR"},{"key":"ref31","first-page":"91","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"NIPS"},{"key":"ref30","article-title":"Unsupervised representation learning with deep convolutional generative adversarial networks","author":"radford","year":"2015","journal-title":"CoRR"},{"key":"ref37","first-page":"1857","article-title":"Improved deep metric learning with multi-class n-pair loss objective","author":"sohn","year":"2016","journal-title":"NIPS"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2005.77"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8462891"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.5244\/C.27.53"},{"key":"ref10","article-title":"Object-centric representation learning from unlabeled videos","author":"gao","year":"2016","journal-title":"CoRR"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0620-5"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.544"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref14","article-title":"Deep learning for single-view instance recognition","author":"held","year":"2015","journal-title":"CoRR"},{"key":"ref15","article-title":"Object category learning and retrieval with weak supervision","author":"hickson","year":"2018","journal-title":"CoRR"},{"key":"ref16","first-page":"2117","article-title":"Fusionseg: Learning to combine motion and appearance for fully automatic segmentation of generic objects in videos","author":"jain","year":"2017","journal-title":"CVPR"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6630857"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.363"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299135"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487517"},{"key":"ref4","article-title":"Scaling egocentric vision: The epic-kitchens dataset","author":"damen","year":"2018","journal-title":"ECCV"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.19"},{"key":"ref3","article-title":"Soundnet: Learning sound representations from unlabeled video","author":"aytar","year":"2016","journal-title":"NIPS"},{"key":"ref6","article-title":"Superpoint: Self-supervised interest point detection and description","author":"detone","year":"2017","journal-title":"CoRR"},{"key":"ref29","article-title":"Self-supervisory signals for object discovery and detection","author":"pot","year":"2018","journal-title":"CoRR"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3390\/s17122735"},{"key":"ref8","article-title":"Adversarially learned inference","author":"dumoulin","year":"2016","journal-title":"CoRR"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.167"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383011"},{"key":"ref9","article-title":"Dense object nets: Learning dense visual object descriptors by and for robotic manipulation","author":"florence","year":"2018","journal-title":"CoRL"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.13"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299064"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref45","first-page":"1912","article-title":"3d shapenets: A deep representation for volumetric shapes","author":"wu","year":"2015","journal-title":"CVPR"},{"key":"ref48","article-title":"Tracking persons-of-interest via unsupervised representation adaptation","author":"zhang","year":"2017","journal-title":"CoRR"},{"key":"ref22","first-page":"4406","article-title":"Segmenting “simple” objects using rgb-d","author":"mishra","year":"2012","journal-title":"ICRA"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.76"},{"key":"ref21","first-page":"740","article-title":"Microsoft coco: Common objects in context. In D. Fleet, T. Pajdla, B. Schiele, and T. Tuytelaars, editors","author":"lin","year":"2014","journal-title":"ECCV"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10593-2_42"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.264"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390294"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202206"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.320"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.638"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.320"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"}],"event":{"name":"2020 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2020,5,31]]},"location":"Paris, France","end":{"date-parts":[[2020,8,31]]}},"container-title":["2020 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9187508\/9196508\/09196567.pdf?arnumber=9196567","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T20:22:19Z","timestamp":1656361339000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9196567\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/icra40945.2020.9196567","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}