{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:14:55Z","timestamp":1777889695072,"version":"3.51.4"},"reference-count":59,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00172","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"1762-1772","source":"Crossref","is-referenced-by-count":0,"title":["LIRA: Reasoning Reconstruction via Multimodal Large Language Models"],"prefix":"10.1109","author":[{"given":"Zhen","family":"Zhou","sequence":"first","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tong","family":"Wang","sequence":"additional","affiliation":[{"name":"Baidu Inc.,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunkai","family":"Ma","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiao","family":"Tan","sequence":"additional","affiliation":[{"name":"Baidu Inc.,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fengshui","family":"Jing","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_25"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_13"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3393141"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/237170.237269"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.5555\/3001460.3001507"},{"key":"ref7","article-title":"The llama 3 herd of models","author":"Grattafiori","year":"2024","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610243"},{"key":"ref9","article-title":"Semantic abstraction: Openworld 3D scene understanding from 2D vision-language models","volume-title":"Proceedings of the 2022 Conference on Robot Learning","author":"Ha","year":"2022"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_20"},{"key":"ref11","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72698-9_6"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160969"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_10"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.066"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197519"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02018"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01807"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"ref21","article-title":"Language-driven semantic segmentation","volume-title":"International Conference on Learning Representations","author":"Li","year":"2022"},{"key":"ref22","article-title":"Beyond bare queries: Open-vocabulary object grounding with 3d scene graph","author":"Linok","year":"2024","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01840"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/37402.37422"},{"key":"ref27","first-page":"1610","article-title":"Ovir-3d: Open-vocabulary 3d instance retrieval without training on 3d data","volume-title":"Proceedings of The 7th Conference on Robot Learning","author":"Lu","year":"2023"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3451395"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.074"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967890"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ISMAR.2011.6092378"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00385"},{"key":"ref33","article-title":"Gpt-4 technical report","author":"Achiam","year":"2024","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00085"},{"key":"ref35","article-title":"Qwen2.5 technical report","author":"Qwen","year":"2025","journal-title":"arXiv preprint"},{"key":"ref36","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of the 38th International Conference on Machine Learning","author":"Radford","year":"2021"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160590"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2989"},{"key":"ref39","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28408"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02032"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00370"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02041"},{"key":"ref45","article-title":"EmbodiedSAM: Online segment any 3d thing in real time","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Xu","year":"2025"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610193"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02671"},{"key":"ref48","article-title":"Lisa++: An improved baseline for reasoning segmentation with large language model","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00008"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00317"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802196"},{"key":"ref52","article-title":"Sam3d: Segment anything in 3d scenes","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops","author":"He","year":"2023"},{"key":"ref53","article-title":"Faster segment anything: Towards lightweight sam for mobile applications","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72775-7_2"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3053188"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01397"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_21"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11128258"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0868"}],"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\/11443314.pdf?arnumber=11443314","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:15:21Z","timestamp":1777612521000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443314\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00172","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}