{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T13:48:18Z","timestamp":1765547298875,"version":"3.28.0"},"reference-count":52,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"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":[[2024,5,13]]},"DOI":"10.1109\/icra57147.2024.10611181","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"1913-1920","source":"Crossref","is-referenced-by-count":1,"title":["Scaling Object-centric Robotic Manipulation with Multimodal Object Identification"],"prefix":"10.1109","author":[{"given":"Chaitanya","family":"Mitash","sequence":"first","affiliation":[{"name":"Amazon Robotics,MA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mostafa","family":"Hussein","sequence":"additional","affiliation":[{"name":"Amazon Robotics,MA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jeroen","family":"Vanbaar","sequence":"additional","affiliation":[{"name":"Amazon Robotics,MA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vikedo","family":"Terhuja","sequence":"additional","affiliation":[{"name":"Amazon Robotics,MA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kapil","family":"Katyal","sequence":"additional","affiliation":[{"name":"Amazon Robotics,MA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Deep vit features as dense visual descriptors","author":"Amir","year":"2022","journal-title":"ECCVW What is Motion For?"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_38"},{"journal-title":"Unsupervised learning of visual features by contrasting cluster assignments","year":"2020","author":"Caron","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"article-title":"A simple framework for contrastive learning of visual representations","year":"2020","author":"Chen","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_19"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.202"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2016.2600527"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref12","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume-title":"NAACL-HLT (1)","author":"Devlin","year":"2019"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02057"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","year":"2020","author":"Dosovitskiy","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2019.01.001"},{"journal-title":"Bootstrap your own latent: A new approach to self-supervised learning","year":"2020","author":"Grill","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-68792-6_51"},{"key":"ref19","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-24261-3_7","article-title":"Deep metric learning using triplet network","volume-title":"International Workshop on Similarity-Based Pattern Recognition","author":"Hoffer"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.242"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540039"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01064"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7758087"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1177\/0278364914549607"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.124"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01752"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aau4984"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-95459-8_9"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160846"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463191"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383172"},{"journal-title":"Learning transferable visual models from natural language supervision","year":"2021","author":"Radford","key":"ref32"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917713117"},{"journal-title":"Distilled feature fields enable few-shot language-guided manipulation","year":"2023","author":"(William)Shen","key":"ref35"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.22"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2003.1238663"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917735594"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917735594"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_27"},{"journal-title":"Particular object retrieval with integral max-pooling of cnn activations","year":"2015","author":"Tolias","key":"ref41"},{"journal-title":"Representation learning with contrastive predictive coding","year":"2018","author":"van den Oord","key":"ref42"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.180"},{"journal-title":"Learning super-features for image retrieval","year":"2022","author":"Weinzaepfel","key":"ref44"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00265"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01846"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2021.3054775"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919868017"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989165"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01157"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3369699"},{"key":"ref52","first-page":"13328","article-title":"Curriculum learning for vision-and-language navigation","volume":"34","author":"Zhang","year":"2021","journal-title":"Advances in Neural Information Processing Systems"}],"event":{"name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2024,5,13]]},"location":"Yokohama, Japan","end":{"date-parts":[[2024,5,17]]}},"container-title":["2024 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10609961\/10609862\/10611181.pdf?arnumber=10611181","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,11]],"date-time":"2024-08-11T04:11:48Z","timestamp":1723349508000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10611181\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10611181","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}