{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:25:10Z","timestamp":1761895510483,"version":"build-2065373602"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11208909","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Injecting Cross-modal Fine-Grained Perception into LLMs for 3D Object-of-Interest Understanding"],"prefix":"10.1109","author":[{"given":"Qianqian","family":"Sun","sequence":"first","affiliation":[{"name":"Beijing Jiaotong University,School of Computer Science and Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lu","family":"Shi","sequence":"additional","affiliation":[{"name":"Beijing Jiaotong University,School of Computer Science and Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Linna","family":"Zhang","sequence":"additional","affiliation":[{"name":"Guizhou University,School of Mechanical Engineering,Guiyang,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gaoyun","family":"An","sequence":"additional","affiliation":[{"name":"Beijing Jiaotong University,School of Computer Science and Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Jin","sequence":"additional","affiliation":[{"name":"Beijing Jiaotong University,School of Computer Science and Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yidong","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing Jiaotong University,School of Computer Science and Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yigang","family":"Cen","sequence":"additional","affiliation":[{"name":"Beijing Jiaotong University,School of Computer Science and Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Sqa3d: Situated question answering in 3d scenes","year":"2022","author":"Ma","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02496"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-naacl.18"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3557703"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01854"},{"key":"ref6","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01070"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3387838"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/194"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.170"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2024.3405079"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00709"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_13"},{"issue":"3","key":"ref16","first-page":"6","article-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality","volume":"2","author":"Chiang","year":"2023"},{"article-title":"Gpt-4 technical report","year":"2023","author":"Achiam","key":"ref17"},{"article-title":"Llama: Open and efficient foundation language models","year":"2023","author":"Touvron","key":"ref18"},{"article-title":"Point-bind & point-llm: Aligning point cloud with multi-modality for 3d understanding, generation, and instruction following","year":"2023","author":"Guo","key":"ref19"},{"key":"ref20","first-page":"20482","article-title":"3d-llm: Injecting the 3d world into large language models","volume":"36","author":"Hong","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","year":"2023","author":"Li","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.4308687"},{"key":"ref23","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning","author":"Li"},{"article-title":"Lora: Low-rank adaptation of large language models","year":"2021","author":"Hu","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.552"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00290"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2025,6,30]]},"location":"Nantes, France","end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11208909.pdf?arnumber=11208909","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:52:00Z","timestamp":1761889920000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11208909\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11208909","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}