{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:28:25Z","timestamp":1777865305340,"version":"3.51.4"},"reference-count":57,"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\/100007219","name":"Natural Science Foundation of Shanghai","doi-asserted-by":"publisher","award":["25ZR1402138"],"award-info":[{"award-number":["25ZR1402138"]}],"id":[{"id":"10.13039\/100007219","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001475","name":"Nanyang Technological University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001475","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\/iccv51701.2025.02672","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"28774-28784","source":"Crossref","is-referenced-by-count":0,"title":["GroundFlow: A Plug-in Module for Temporal Reasoning on 3D Point Cloud Sequential Grounding"],"prefix":"10.1109","author":[{"given":"Zijun","family":"Lin","sequence":"first","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuting","family":"He","sequence":"additional","affiliation":[{"name":"Shanghai University of Finance and Economics,MoE Key Laboratory of Interdisciplinary Research of Computation and Economics"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cheston","family":"Tan","sequence":"additional","affiliation":[{"name":"Centre for Frontier AI Research, A*STAR"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bihan","family":"Wen","sequence":"additional","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00068"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_25"},{"key":"ref3","article-title":"Arkitscenes: A diverse real-world dataset for 3d indoor scene understanding using mobile rgb-d data","author":"Baruch","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01597"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01340"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_13"},{"key":"ref7","first-page":"5834","article-title":"History aware multimodal transformer for vision-and-language navigation","volume":"34","author":"Chen","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1492"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01660"},{"key":"ref10","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"Chung","year":"2014","journal-title":"arXiv preprint arXiv"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00008"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01260"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1201\/b17103-3"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00430"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01735"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01410"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475397"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680998"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0900"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00257"},{"key":"ref24","article-title":"An embodied generalist agent in 3d world","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Huang","year":"2024"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_24"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72673-6_16"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01057"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_7"},{"key":"ref29","article-title":"Neural-symbolic videoqa: Learning compositional spatiotemporal reasoning for real-world video question answering","author":"Liang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref30","article-title":"Scalable 3d captioning with pretrained models","author":"Luo","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0658"},{"key":"ref32","article-title":"Adafuse: Adaptive temporal fusion network for efficient action recognition","author":"Meng","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3048662"},{"key":"ref34","article-title":"Pointnet++: Deep hierarchical feature learning on point sets in a metric space","author":"Qi","year":"2017","journal-title":"Advances in neural information processing systems, 30"},{"key":"ref35","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref36","article-title":"Habitat-matterport 3D dataset (HM3d): 1000 largescale 3D environments for embodied AI","volume-title":"Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track","author":"Ramakrishnan","year":"2021"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00331"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01333"},{"key":"ref39","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in neural information processing systems, 30"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00775"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00051"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01320"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00251"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.2324-16.2017"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01633"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2156"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00647"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00181"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01949"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01397"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01329"},{"key":"ref52","volume-title":"Task-oriented sequential grounding and navigation in 3d scenes","author":"Zhang","year":"2025"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00292"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01293"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_49"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00272"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72784-9_11"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444671.pdf?arnumber=11444671","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:11:59Z","timestamp":1777529519000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444671\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02672","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}