{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:19:00Z","timestamp":1778048340860,"version":"3.51.4"},"reference-count":54,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100016311","name":"Arm","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100016311","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00175","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"1746-1756","source":"Crossref","is-referenced-by-count":0,"title":["Descrip3D: Enhancing Large Language Model-based 3D Scene Understanding with Object-Level Text Descriptions"],"prefix":"10.1109","author":[{"given":"Jintang","family":"Xue","sequence":"first","affiliation":[{"name":"University of Southern California,Los Angeles,California,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ganning","family":"Zhao","sequence":"additional","affiliation":[{"name":"University of Southern California,Los Angeles,California,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie-En","family":"Yao","sequence":"additional","affiliation":[{"name":"University of Southern California,Los Angeles,California,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hong-En","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Southern California,Los Angeles,California,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yue","family":"Hu","sequence":"additional","affiliation":[{"name":"University of Southern California,Los Angeles,California,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meida","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Southern California,Los Angeles,California,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Suya","family":"You","sequence":"additional","affiliation":[{"name":"DEVCOM Army Research Laboratory,Los Angeles,California,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"C.-C. Jay","family":"Kuo","sequence":"additional","affiliation":[{"name":"University of Southern California,Los Angeles,California,USA"}],"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":"10.1109\/CVPR52688.2022.01854"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01597"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_13"},{"key":"ref5","article-title":"D3net: A speaker-listener architecture for semi-supervised dense captioning and visual grounding in rgb-d scans","author":"Chen","year":"2021"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02496"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3387838"},{"key":"ref8","article-title":"Grounded 3d-llm with referent tokens","author":"Chen","year":"2024"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00321"},{"issue":"3","key":"ref10","first-page":"6","article-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality","volume":"2","author":"Chiang","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref12","article-title":"Scene-llm: Extending language model for 3d visual understanding and reasoning","author":"Fu","year":"2024"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610243"},{"key":"ref14","article-title":"Point-bind & point-llm: Aligning point cloud with multi-modality for 3d understanding, generation, and instruction following","author":"Guo","year":"2023"},{"key":"ref15","article-title":"A survey on large language models: Applications, challenges, limitations, and practical usage","author":"Hadi","year":"2023","journal-title":"Authorea Preprints"},{"key":"ref16","article-title":"Imagebind-llm: Multi-modality instruction tuning","author":"Han","year":"2023"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00217"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0900"},{"issue":"2","key":"ref19","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume-title":"ICLR","volume":"1","author":"Hu"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3620"},{"key":"ref21","article-title":"An embodied generalist agent in 3d world","author":"Huang","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01057"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s44336-024-00009-2"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2025.103624"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2025.3584895"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3291"},{"key":"ref28","article-title":"Sqa3d: Situated question answering in 3d scenes","author":"Ma","year":"2022"},{"key":"ref29","article-title":"When llms step into the 3d world: A survey and meta-analysis of 3d tasks via multi-modal large language models","author":"Ma","year":"2024"},{"key":"ref30","article-title":"Large language models: A survey","author":"Minaee","year":"2024"},{"key":"ref31","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023"},{"key":"ref32","article-title":"Gpt4scene: Understand 3d scenes from videos with vision-language models","author":"Qi","year":"2025"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/icra48891.2023.10160590"},{"key":"ref35","first-page":"16857","article-title":"Mpnet: Masked and permuted pre-training for language understanding","volume":"33","author":"Song","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref36","first-page":"15","article-title":"Three ways to improve verbo-visual fusion for dense 3d visual grounding","volume":"2","author":"Unal","year":"2023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/OJCOMS.2023.3320646"},{"key":"ref38","article-title":"Chat-3d: Data-efficiently tuning large language model for universal dialogue of 3d scenes","author":"Wang","year":"2023"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.077"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72698-9_8"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1561\/116.00000064"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00120"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i9.33001"},{"key":"ref44","first-page":"26650","article-title":"Lamm: Language-assisted multi-modal instruction-tuning dataset, framework, and benchmark","volume":"36","author":"Yin","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3296889"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01949"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51701.2025.00831"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2025\/1200"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01397"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00292"},{"issue":"2","key":"ref51","article-title":"A survey of large language models","volume":"1","author":"Zhao","year":"2023"},{"key":"ref52","article-title":"Uni3d: Exploring unified 3d representation at scale","author":"Zhou","year":"2023"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00272"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72784-9_11"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492252.pdf?arnumber=11492252","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T05:55:37Z","timestamp":1778046937000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492252\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00175","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}