{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:07:03Z","timestamp":1765339623035,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":47,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755836","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T05:56:43Z","timestamp":1761371803000},"page":"5257-5266","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["TriCLIP-3D: A Unified Parameter-Efficient Framework for Tri-Modal 3D Visual Grounding based on CLIP"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-9658-2378","authenticated-orcid":false,"given":"Fan","family":"Li","sequence":"first","affiliation":[{"name":"SGIT AI Lab, State Grid Corporation of China, Xi'an, China and Xi'an Jiaotong University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3726-6029","authenticated-orcid":false,"given":"Zanyi","family":"Wang","sequence":"additional","affiliation":[{"name":"SGIT AI Lab, State Grid Corporation of China, Xi'an, China and Xi'an Jiaotong University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5897-2172","authenticated-orcid":false,"given":"Zeyi","family":"Huang","sequence":"additional","affiliation":[{"name":"Huawei, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3529-9087","authenticated-orcid":false,"given":"Guang","family":"Dai","sequence":"additional","affiliation":[{"name":"SGIT AI Lab, State Grid Corporation of China, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4888-4445","authenticated-orcid":false,"given":"Jingdong","family":"Wang","sequence":"additional","affiliation":[{"name":"Hefei University of Technology, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4035-0630","authenticated-orcid":false,"given":"Mengmeng","family":"Wang","sequence":"additional","affiliation":[{"name":"Zhejiang University of Technology, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00068"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_25"},{"key":"e_1_3_2_1_3_1","volume-title":"Look around and refer: 2d synthetic semantics knowledge distillation for 3d visual grounding. Advances in neural information processing systems","author":"Bakr Eslam","year":"2022","unstructured":"Eslam Bakr, Yasmeen Alsaedy, and Mohamed Elhoseiny. 2022. Look around and refer: 2d synthetic semantics knowledge distillation for 3d visual grounding. Advances in neural information processing systems, Vol. 35 (2022), 37146-37158."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01597"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01340"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_13"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01660"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00319"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00370"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-78447-7_12"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00217"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01508"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02025"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611902"},{"key":"e_1_3_2_1_19_1","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence.","author":"Huang Xiaoshui","year":"2024","unstructured":"Xiaoshui Huang, Zhou Huang, Sheng Li, Wentao Qu, Tong He, Yuenan Hou, Yifan Zuo, and Wanli Ouyang. 2024. EPCL: Frozen CLIP Transformer is An Efficient Point Cloud Encoder. In Proceedings of the AAAI Conference on Artificial Intelligence."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_24"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00492"},{"key":"e_1_3_2_1_22_1","volume-title":"European Conference on Computer Vision. Springer, 456-473","author":"Lin Zhenxiang","year":"2024","unstructured":"Zhenxiang Lin, Xidong Peng, Peishan Cong, Ge Zheng, Yujin Sun, Yuenan Hou, Xinge Zhu, Sibei Yang, and Yuexin Ma. 2024. Wildrefer: 3d object localization in large-scale dynamic scenes with multi-modal visual data and natural language. In European Conference on Computer Vision. Springer, 456-473."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-78113-1_17"},{"key":"e_1_3_2_1_24_1","volume-title":"Fixing Weight Decay Regularization in Adam. ArXiv","author":"Loshchilov Ilya","year":"2017","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Fixing Weight Decay Regularization in Adam. ArXiv, Vol. abs\/1711.05101 (2017). https:\/\/api.semanticscholar.org\/CorpusID:3312944"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00033"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_30"},{"key":"e_1_3_2_1_27_1","volume-title":"Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al., 2019. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00937"},{"key":"e_1_3_2_1_29_1","volume-title":"Pointnet: Deep hierarchical feature learning on point sets in a metric space. Advances in neural information processing systems","author":"Qi Charles Ruizhongtai","year":"2017","unstructured":"Charles Ruizhongtai Qi, Li Yi, Hao Su, and Leonidas J Guibas. 2017. Pointnet: Deep hierarchical feature learning on point sets in a metric space. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_30_1","volume-title":"International conference on machine learning. PmLR, 8748-8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al., 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PmLR, 8748-8763."},{"key":"e_1_3_2_1_31_1","volume-title":"Conference on Robot Learning. PMLR, 1046-1056","author":"Roh Junha","year":"2022","unstructured":"Junha Roh, Karthik Desingh, Ali Farhadi, and Dieter Fox. 2022. Languagerefer: Spatial-language model for 3d visual grounding. In Conference on Robot Learning. PMLR, 1046-1056."},{"key":"e_1_3_2_1_32_1","volume-title":"proceedings of the IEEE conference on computer vision and pattern recognition. 2980-2988","author":"Ross T-YLPG","year":"2017","unstructured":"T-YLPG Ross and GKHP Doll\u00e1r. 2017. Focal loss for dense object detection. In proceedings of the IEEE conference on computer vision and pattern recognition. 2980-2988."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_28"},{"key":"e_1_3_2_1_34_1","first-page":"1265","volume-title":"2022 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","author":"Rukhovich Danila D.","year":"2021","unstructured":"Danila D. Rukhovich, Anna Vorontsova, and Anton Konushin. 2021. ImVoxelNet: Image to Voxels Projection for Monocular and Multi-View General-Purpose 3D Object Detection. 2022 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV) (2021), 1265-1274. https:\/\/api.semanticscholar.org\/CorpusID:235293744"},{"key":"e_1_3_2_1_35_1","first-page":"4603","volume-title":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019","author":"Vora Sourabh","year":"2019","unstructured":"Sourabh Vora, Alex H. Lang, Bassam Helou, and Oscar Beijbom. 2019. PointPainting: Sequential Fusion for 3D Object Detection. 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019), 4603-4611. https:\/\/api.semanticscholar.org\/CorpusID:208248084"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00775"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01868"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28408"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01843"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00120"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02558"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00187"},{"key":"e_1_3_2_1_43_1","first-page":"26650","article-title":"Lamm: Language-assisted multi-modal instruction-tuning dataset, framework, and benchmark","volume":"36","author":"Yin Zhenfei","year":"2023","unstructured":"Zhenfei Yin, Jiong Wang, Jianjian Cao, Zhelun Shi, Dingning Liu, Mukai Li, Xiaoshui Huang, Zhiyong Wang, Lu Sheng, Lei Bai, et al., 2023. Lamm: Language-assisted multi-modal instruction-tuning dataset, framework, and benchmark. Advances in Neural Information Processing Systems, Vol. 36 (2023), 26650-26685.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01949"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00836"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00292"},{"key":"e_1_3_2_1_47_1","volume-title":"Object2scene: Putting objects in context for open-vocabulary 3d detection. arXiv preprint arXiv:2309.09456","author":"Zhu Chenming","year":"2023","unstructured":"Chenming Zhu, Wenwei Zhang, Tai Wang, Xihui Liu, and Kai Chen. 2023. Object2scene: Putting objects in context for open-vocabulary 3d detection. arXiv preprint arXiv:2309.09456 (2023)."}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755836","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:03:37Z","timestamp":1765339417000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755836"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":47,"alternative-id":["10.1145\/3746027.3755836","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755836","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}