{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T18:10:42Z","timestamp":1771956642182,"version":"3.50.1"},"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62372014"],"award-info":[{"award-number":["62372014"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["4252040"],"award-info":[{"award-number":["4252040"]}],"id":[{"id":"10.13039\/501100004826","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\/icra55743.2025.11127295","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"12766-12773","source":"Crossref","is-referenced-by-count":3,"title":["3DWG: 3D Weakly Supervised Visual Grounding via Category and Instance-Level Alignment"],"prefix":"10.1109","author":[{"given":"Xiaoqi","family":"Li","sequence":"first","affiliation":[{"name":"School of CS, Peking University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaming","family":"Liu","sequence":"additional","affiliation":[{"name":"School of CS, Peking University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nuowei","family":"Han","sequence":"additional","affiliation":[{"name":"School of CS, Peking University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"Heng","sequence":"additional","affiliation":[{"name":"School of CS, Peking University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yandong","family":"Guo","sequence":"additional","affiliation":[{"name":"AI2Robotic"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Dong","sequence":"additional","affiliation":[{"name":"School of CS, Peking University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Liu","sequence":"additional","affiliation":[{"name":"Wangxuan Institute of Computer Technology, Peking University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00187"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00181"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475397"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01508"},{"key":"ref5","first-page":"1046","article-title":"Languagerefer: Spatiallanguage model for 3d visual grounding","volume-title":"Conference on Robot Learning","author":"Roh","year":"2022"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01410"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00292"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610443"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1162\/artl.1993.1.1_2.135"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610096"},{"key":"ref11","article-title":"Vida: Homeostatic visual domain adapter for continual test time adaptation","author":"Liu","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02707"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611565"},{"key":"ref14","first-page":"16353","article-title":"Find what you want: Learning demand-conditioned object attribute space for demanddriven navigation","volume":"36","author":"Wang","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01710"},{"key":"ref16","article-title":"Robomamba: Multimodal state space model for efficient robot reasoning and manipulation","author":"Liu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00251"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_13"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_25"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01387"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00425"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00641"},{"key":"ref24","article-title":"Interpretable and globally optimal prediction for textual grounding using image concepts","volume":"30","author":"Yeh","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00556"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_44"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_38"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.656"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28559"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01949"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01320"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_22"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01241"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01633"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01333"},{"key":"ref36","article-title":"Multi-object 3d grounding with dynamic modules and language-informed spatial attention","author":"Zhang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01596"},{"key":"ref38","first-page":"2","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proceedings of naacL-HLT","volume":"1","author":"Kenton","year":"2019"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00611"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1162"},{"key":"ref41","article-title":"Improved baselines with momentum contrastive learning","author":"Chen","year":"2020","journal-title":"arXiv preprint arXiv"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16253"},{"key":"ref43","article-title":"Looking outside the box to ground language in 3d scenes","author":"Jain","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00269"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00294"},{"key":"ref46","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint arXiv"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","location":"Atlanta, GA, USA","start":{"date-parts":[[2025,5,19]]},"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\/11127295.pdf?arnumber=11127295","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:13:34Z","timestamp":1756880014000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11127295\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11127295","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}