{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,24]],"date-time":"2025-08-24T01:44:33Z","timestamp":1755999873664,"version":"3.28.0"},"reference-count":52,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"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":[[2021,5,30]]},"DOI":"10.1109\/icra48506.2021.9560806","type":"proceedings-article","created":{"date-parts":[[2021,10,20]],"date-time":"2021-10-20T00:28:35Z","timestamp":1634689715000},"page":"10160-10167","source":"Crossref","is-referenced-by-count":4,"title":["\u201cWhat\u2019s This?\u201d - Learning to Segment Unknown Objects from Manipulation Sequences"],"prefix":"10.1109","author":[{"given":"Wout","family":"Boerdijk","sequence":"first","affiliation":[]},{"given":"Martin","family":"Sundermeyer","sequence":"additional","affiliation":[]},{"given":"Maximilian","family":"Durner","sequence":"additional","affiliation":[]},{"given":"Rudolph","family":"Triebel","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"crossref","first-page":"833","DOI":"10.1007\/978-3-030-01234-2_49","article-title":"Encoder-decoder with atrous separable convolution for semantic image segmentation","author":"chen","year":"2018","journal-title":"Computer Vision – ECCV 2018"},{"year":"0","key":"ref38","article-title":"The KITTI Vision Benchmark Suite"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00060"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_10"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.422"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9190838"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.228"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1122-2"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.81"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46604-0_12"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00374"},{"article-title":"Learning trailer moments in full-length movies","year":"2020","author":"wang","key":"ref27"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907586"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.2003.1251"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1016\/j.neunet.2019.04.024","article-title":"Deep neural network concepts for background subtraction: A systematic review and comparative evaluation","volume":"117","author":"bouwmans","year":"2019","journal-title":"Neural Networks"},{"article-title":"Multi-Temporal Scene Classification and Scene Change Detection with Correlation based Fusion","year":"2020","author":"ru","key":"ref22"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2019.8851762"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00936"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.316"},{"key":"ref26","first-page":"289","author":"lu","year":"2016","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref25","first-page":"6000","article-title":"Attention is all you need","author":"vaswani","year":"0"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.146"},{"article-title":"Decoupled Weight Decay Regularization","year":"2019","author":"loshchilov","key":"ref51"},{"key":"ref52","doi-asserted-by":"crossref","DOI":"10.1109\/IROS51168.2021.9636281","article-title":"Unknown object segmentation from stereo images","author":"durner","year":"2021"},{"article-title":"Self-Supervised Object-in-Gripper Segmentation from Robotic Motions","year":"0","author":"boerdijk","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.156"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.1166"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(81)90024-2"},{"key":"ref14","article-title":"Raft: Recurrent all-pairs field transforms for optical flow","author":"teed","year":"2020","journal-title":"ECCV"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.147"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.12"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00238"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2004.838698"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.2174\/1874479610902030223"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196714"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00276"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2010.5509328"},{"key":"ref5","first-page":"1817","article-title":"Manipulator and Object Tracking for In Hand Model Acquisition","author":"krainin","year":"0","journal-title":"Proc IEEE Int Conf Robots Automation"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794334"},{"key":"ref49","article-title":"Shapenet: An information-rich 3d model repository","author":"chang","year":"2015","journal-title":"Stanford University — Princeton University — Toyota Technological Institute at Chicago Tech Rep"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2012.6225218"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196543"},{"article-title":"Blenderproc","year":"2019","author":"denninger","key":"ref46"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1070-x"},{"key":"ref48","doi-asserted-by":"crossref","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","author":"lin","year":"2014","journal-title":"Computer Vision – ECCV 2014"},{"article-title":"Semantic Scene Completion from a Single Depth Image","year":"2016","author":"song","key":"ref47"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_39"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.316"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2014.126"},{"key":"ref43","first-page":"802","article-title":"Convolutional lstm network: A machine learning approach for precipitation nowcasting","author":"shi","year":"0"}],"event":{"name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2021,5,30]]},"location":"Xi'an, China","end":{"date-parts":[[2021,6,5]]}},"container-title":["2021 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9560720\/9560666\/09560806.pdf?arnumber=9560806","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,12]],"date-time":"2023-01-12T22:54:10Z","timestamp":1673564050000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9560806\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,30]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/icra48506.2021.9560806","relation":{},"subject":[],"published":{"date-parts":[[2021,5,30]]}}}