{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T06:01:38Z","timestamp":1779948098836,"version":"3.53.1"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T00:00:00Z","timestamp":1773964800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T00:00:00Z","timestamp":1773964800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007937","name":"Peking University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100007937","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,20]]},"DOI":"10.1109\/3dv69130.2026.00168","type":"proceedings-article","created":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T19:40:49Z","timestamp":1779910849000},"page":"1771-1780","source":"Crossref","is-referenced-by-count":0,"title":["3D CoCa: Contrastive Learners are 3D Captioners"],"prefix":"10.1109","author":[{"given":"Ting","family":"Huang","sequence":"first","affiliation":[{"name":"School of Computer Science, Peking University,State Key Laboratory of Multimedia Information Processing"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zeyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"The Australian National University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yemin","family":"Wang","sequence":"additional","affiliation":[{"name":"Xiamen University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Tang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Peking University,State Key Laboratory of Multimedia Information Processing"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_25"},{"key":"ref2","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization","author":"Banerjee","year":"2005"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01597"},{"key":"ref4","article-title":"Medical ai for early detection of lung cancer: A survey","author":"Cai","year":"2024","journal-title":"arXiv preprint"},{"key":"ref5","article-title":"Msdet: Receptive field enhanced multiscale detection for tiny pulmonary nodule","author":"Cai","year":"2024","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00321"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01660"},{"key":"ref8","article-title":"Scanrefer: 3d object localization in rgb-d scans using natural language","volume-title":"16th European Conference on Computer Vision (ECCV)","author":"Zhenyu Chen","year":"2020"},{"key":"ref9","article-title":"D3net: A speaker-listener architecture for semi-supervised dense captioning and visual grounding in rgb-d scans","author":"Zhenyu Chen","year":"2021","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00047"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01070"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3387838"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3478518"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01486-4"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_31"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72649-1_21"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01057"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.202"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72649-1_22"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2021.3131120"},{"key":"ref22","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Text Summarization Branches Out","author":"Lin","year":"2004"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-short.8"},{"key":"ref24","article-title":"Decoupled weight decay regularization","volume-title":"International Conference on Learning Representations","author":"Loshchilov","year":"2019"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP46576.2022.9897388"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2006.479"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20086-1_35"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref29","article-title":"Pointnet++: Deep hierarchical feature learning on point sets in a metric space","author":"Ruizhongtai Qi","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref30","author":"Radford","year":"2021","journal-title":"Learning transferable visual models from natural language supervision"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00964"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/194"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00519"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_34"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3239541"},{"key":"ref37","author":"Yu","year":"2022","journal-title":"Coca: Contrastive captioners are image-text foundation models"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01871"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00837"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28559"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/BIBM62325.2024.10821943"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.3233\/FAIA250915"}],"event":{"name":"2026 International Conference on 3D Vision (3DV)","location":"Vancouver, BC, Canada","start":{"date-parts":[[2026,3,20]]},"end":{"date-parts":[[2026,3,23]]}},"container-title":["2026 International Conference on 3D Vision (3DV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11533157\/11533158\/11533223.pdf?arnumber=11533223","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T05:01:48Z","timestamp":1779944508000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11533223\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,20]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/3dv69130.2026.00168","relation":{},"subject":[],"published":{"date-parts":[[2026,3,20]]}}}