{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T20:38:23Z","timestamp":1776976703574,"version":"3.51.4"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007219","name":"Natural Science Foundation of Shanghai","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007219","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012492","name":"Youth Innovation Promotion Association","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012492","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002367","name":"Chinese Academy of Sciences","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iros60139.2025.11246315","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"11773-11780","source":"Crossref","is-referenced-by-count":0,"title":["PCGE: Boosting 3D Visual Grounding via Progressive Comprehension and Geometric-topology Perception Enhancement"],"prefix":"10.1109","author":[{"given":"Zeyue","family":"Wang","sequence":"first","affiliation":[{"name":"Chinese Academy of Sciences,Bio-Vision System Laboratory, Science and Technology on Micro-System Laboratory, Shanghai Institute of Microsystem and Information Technology,Shanghai,China,200050"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xixia","family":"Xu","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Bio-Vision System Laboratory, Science and Technology on Micro-System Laboratory, Shanghai Institute of Microsystem and Information Technology,Shanghai,China,200050"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Runze","family":"Liu","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,Harbin,China,150006"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongchen","family":"Zhu","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Bio-Vision System Laboratory, Science and Technology on Micro-System Laboratory, Shanghai Institute of Microsystem and Information Technology,Shanghai,China,200050"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiamao","family":"Li","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Bio-Vision System Laboratory, Science and Technology on Micro-System Laboratory, Shanghai Institute of Microsystem and Information Technology,Shanghai,China,200050"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2022.3141105"},{"key":"ref2","article-title":"Language models as zero-shot planners: Extracting actionable knowledge for embodied agents","volume-title":"International conference on machine learning","author":"Huang"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20097"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01441"},{"key":"ref5","first-page":"6236","article-title":"Avlen: Audio-visual-language embodied navigation in 3d environments","volume":"35","author":"Paul","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00229"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00181"},{"key":"ref8","article-title":"Languagerefer: Spatial-language model for 3d visual grounding","volume-title":"Conference on Robot Learning","author":"Roh"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00456"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_13"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00187"},{"key":"ref12","first-page":"37146","article-title":"Look around and refer: 2d synthetic semantics knowledge distillation for 3d visual grounding","volume":"35","author":"Bakr","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_24"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01843"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00292"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00370"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01596"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01320"},{"key":"ref19","article-title":"Pointnet++: Deep hierarchical feature learning on point sets in a metric space","volume":"30","author":"Qi","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref20","article-title":"Roberta: A robustly optimized bert pretraining approach","author":"Liu","year":"2019"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00937"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01333"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16253"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01597"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01508"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01057"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01660"},{"key":"ref28","first-page":"49542","article-title":"Exploiting contextual objects and relations for 3d visual grounding","volume":"36","author":"Yang","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802292"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01410"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28559"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_22"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_25"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Hangzhou, China","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11246315.pdf?arnumber=11246315","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T19:54:50Z","timestamp":1776974090000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11246315\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11246315","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}