{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T16:38:01Z","timestamp":1757608681020,"version":"3.44.0"},"reference-count":46,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001659","name":"German Research Foundation","doi-asserted-by":"publisher","award":["169"],"award-info":[{"award-number":["169"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"publisher","award":["62106026,62272170,42130112"],"award-info":[{"award-number":["62106026,62272170,42130112"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11128104","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"1444-1450","source":"Crossref","is-referenced-by-count":0,"title":["3D Dense Captioning via Prototypical Momentum Distillation"],"prefix":"10.1109","author":[{"given":"Jinpeng","family":"Mi","sequence":"first","affiliation":[{"name":"Institute of Machine Intelligence, University of Shanghai for Science and Technology,China"}]},{"given":"Ying","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Machine Intelligence, University of Shanghai for Science and Technology,China"}]},{"given":"Shaofei","family":"Jin","sequence":"additional","affiliation":[{"name":"Institute of Machine Intelligence, University of Shanghai for Science and Technology,China"}]},{"given":"Shiming","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Machine Intelligence, University of Shanghai for Science and Technology,China"}]},{"given":"Xian","family":"Wei","sequence":"additional","affiliation":[{"name":"Software Engineering Institute, East China Normal University,China"}]},{"given":"Jianwei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Universit&#x00E4;t Hamburg,Technical Aspects of Multimodal Systems,Department of Informatics,Germany"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.494"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00321"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00235"},{"issue":"4","key":"ref6","first-page":"516","article-title":"Information processing model of machine maps","volume":"49","author":"You","year":"2024","journal-title":"Geomatics and Information Science of Wuhan University"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00110"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560895"},{"journal-title":"Contextual modeling for 3d dense captioning on point clouds","year":"2022","author":"Zhong","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00837"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01057"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01597"},{"key":"ref13","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01660"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01070"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3387838"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_13"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_25"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/1150402.1150464"},{"journal-title":"Distilling the knowledge in a neural network","year":"2015","author":"Hinton","key":"ref20"},{"key":"ref21","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","volume":"30","author":"Tarvainen","year":"2017","journal-title":"NeurIPS"},{"key":"ref22","article-title":"Active learning literature survey","volume-title":"Computer Sciences Technical Report 1648, University of Wisconsin-Madison Department of Computer Sciences","author":"Settles","year":"2009"},{"key":"ref23","article-title":"Prototypical networks for few-shot learning","volume":"30","author":"Snell","year":"2017","journal-title":"NeurIPS"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_31"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/194"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00290"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25359"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681161"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161294"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341909"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00251"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27831"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.111437"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02675"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3387349"},{"key":"ref36","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume":"34","author":"Li","year":"2021","journal-title":"NeurIPS"},{"key":"ref37","article-title":"Pointnet++: Deep hierarchical feature learning on point sets in a metric space","volume":"30","author":"Qi","year":"2017","journal-title":"NeurIPS"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00937"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref43","first-page":"65","article-title":"METEOR: An automatic metric for mt evaluation with improved correlation with human judgments","volume-title":"ACL Workshop","author":"Banerjee","year":"2005"},{"key":"ref44","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of sum-maries","volume-title":"Proceedings of the Workshop on Text Summarization Branches Out","author":"Lin","year":"2004"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2023.3279204"},{"key":"ref46","first-page":"487","article-title":"D3Net: A unified speaker-listener architecture for 3d dense captioning and visual grounding","author":"Chen","year":"2022","journal-title":"ECCV"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2025,5,19]]},"location":"Atlanta, GA, USA","end":{"date-parts":[[2025,5,23]]}},"container-title":["2025 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11127273\/11127223\/11128104.pdf?arnumber=11128104","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:16:09Z","timestamp":1756880169000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11128104\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11128104","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}