{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T06:41:35Z","timestamp":1730270495883,"version":"3.28.0"},"reference-count":54,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,10,23]],"date-time":"2022-10-23T00:00:00Z","timestamp":1666483200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,23]],"date-time":"2022-10-23T00:00:00Z","timestamp":1666483200000},"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":[[2022,10,23]]},"DOI":"10.1109\/iros47612.2022.9982285","type":"proceedings-article","created":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T19:38:15Z","timestamp":1672083495000},"page":"2009-2016","source":"Crossref","is-referenced-by-count":2,"title":["Instance Segmentation with Cross-Modal Consistency"],"prefix":"10.1109","author":[{"given":"Alex Zihao","family":"Zhu","sequence":"first","affiliation":[{"name":"Waymo LLC"}]},{"given":"Vincent","family":"Casser","sequence":"additional","affiliation":[{"name":"Waymo LLC"}]},{"given":"Reza","family":"Mahjourian","sequence":"additional","affiliation":[{"name":"Waymo LLC"}]},{"given":"Henrik","family":"Kretzschmar","sequence":"additional","affiliation":[{"name":"Waymo LLC"}]},{"given":"S\u00f6ren","family":"Pirk","sequence":"additional","affiliation":[{"name":"Adobe Research (Work done while at Google Research)"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_33"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.100"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.305"},{"key":"ref4","article-title":"Range conditioned dilated convolutions for scale invariant 3D object detection","author":"Bewley","year":"2020","journal-title":"arXiv"},{"key":"ref5","article-title":"Semantic instance segmentation with a discriminative loss function","author":"De Brabandere","year":"2017","journal-title":"arXiv"},{"key":"ref6","article-title":"nuScenes: A multimodal dataset for autonomous driving","author":"Caesar","year":"2019","journal-title":"arXiv"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00860"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_40"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.396"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01518"},{"key":"ref12","article-title":"A simple framework for contrastive learning of visual representations","author":"Chen","year":"2020","journal-title":"arXiv"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00215"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.691"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01249"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_32"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299025"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00905"},{"key":"ref20","article-title":"Semantic instance segmentation via deep metric learning","volume":"abs\/1703. 10277","author":"Fathi","year":"2017","journal-title":"arXiv"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00073"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298642"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref26","article-title":"Learning a spatio-temporal embedding for video instance segmentation","author":"Hu","year":"2019","journal-title":"arXiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_33"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00656"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00940"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00479"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01298"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00278"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3179507"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.162"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341029"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00904"},{"key":"ref39","first-page":"2274","article-title":"Associative embedding: End-to-end learning for joint detection and grouping","author":"Newell","year":"2017","journal-title":"NIPS"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00847"},{"key":"ref41","first-page":"652","article-title":"PointNet: Deep learning on point sets for 3D classification and segmentation","author":"Qi","year":"2017","journal-title":"CVPR"},{"key":"ref42","article-title":"PointNet++: Deep hierarchical feature learning on point sets in a metric space","volume-title":"NeurIPS","volume":"30","author":"Qi","year":"2017"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00542"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00422"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58542-6_2"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00513"},{"key":"ref48","article-title":"Learning RGB-D feature embeddings for unseen object instance segmentation","author":"Xiang","year":"2020","journal-title":"CoRL"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00902"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00798"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00407"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.75"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00472"}],"event":{"name":"2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2022,10,23]]},"location":"Kyoto, Japan","end":{"date-parts":[[2022,10,27]]}},"container-title":["2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9981026\/9981028\/09982285.pdf?arnumber=9982285","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T03:28:49Z","timestamp":1706758129000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9982285\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,23]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/iros47612.2022.9982285","relation":{},"subject":[],"published":{"date-parts":[[2022,10,23]]}}}