{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T07:25:48Z","timestamp":1767079548139,"version":"3.48.0"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T00:00:00Z","timestamp":1764720000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T00:00:00Z","timestamp":1764720000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,3]]},"DOI":"10.1109\/dicta68720.2025.11302488","type":"proceedings-article","created":{"date-parts":[[2025,12,29]],"date-time":"2025-12-29T18:36:22Z","timestamp":1767033382000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["IntentFuse: Language-Guided 3D Scene Understanding via Prompt Filtering and Fusion"],"prefix":"10.1109","author":[{"given":"Ahalya","family":"Ravendran","sequence":"first","affiliation":[{"name":"CSIRO Data61,Australia"}]},{"given":"Madhawa","family":"Perera","sequence":"additional","affiliation":[{"name":"CSIRO Data61,Australia"}]},{"given":"Feng","family":"Xu","sequence":"additional","affiliation":[{"name":"CSIRO Data61,Australia"}]},{"given":"Lars","family":"Petersson","sequence":"additional","affiliation":[{"name":"CSIRO Data61,Australia"}]},{"given":"Dadong","family":"Wang","sequence":"additional","affiliation":[{"name":"CSIRO Data61,Australia"}]},{"given":"Xun","family":"Li","sequence":"additional","affiliation":[{"name":"CSIRO Data61,Australia"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01807"},{"key":"ref2","article-title":"Diffusion-based attention warping for consistent 3d scene editing","author":"Gomel","year":"2024","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01895"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02049"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530127"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00580"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref9","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning. PmLR","author":"Radford"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3026892"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610243"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2931042"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460902"},{"key":"ref14","article-title":"Do as i can, not as i say: Grounding language in robotic affordances","author":"Ahn","year":"2022","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1177\/1059712317726357"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298990"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00611"},{"key":"ref18","article-title":"Ai2-thor: An interactive 3d environment for visual ai","author":"Kolve","year":"2017","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00943"},{"key":"ref20","article-title":"The replica dataset: A digital replica of indoor spaces","author":"Straub","year":"2019","journal-title":"arXiv preprint"},{"key":"ref21","article-title":"Gemma: Open models based on gemini research and technology","author":"Team","year":"2024","journal-title":"arXiv preprint"},{"key":"ref22","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3758177"}],"event":{"name":"2025 International Conference on Digital Image Computing: Techniques and Applications (DICTA)","start":{"date-parts":[[2025,12,3]]},"location":"Adelaide, Australia","end":{"date-parts":[[2025,12,5]]}},"container-title":["2025 International Conference on Digital Image Computing: Techniques and Applications (DICTA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11302408\/11302416\/11302488.pdf?arnumber=11302488","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T07:22:01Z","timestamp":1767079321000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11302488\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,3]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/dicta68720.2025.11302488","relation":{},"subject":[],"published":{"date-parts":[[2025,12,3]]}}}