{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:25:16Z","timestamp":1765308316708,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":64,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62221002, 62425305, U22B205"],"award-info":[{"award-number":["62221002, 62425305, U22B205"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science and Technology Innovation Program of Hunan Province","award":["2023RC1048"],"award-info":[{"award-number":["2023RC1048"]}]},{"name":"Hunan Provincial Natural Science Foundation of China","award":["2024JJ3013"],"award-info":[{"award-number":["2024JJ3013"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755497","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T05:47:42Z","timestamp":1761371262000},"page":"4552-4561","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Dual Enhancement on 3D Vision-Language Perception for Monocular 3D Visual Grounding"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-3540-0627","authenticated-orcid":false,"given":"Yuzhen","family":"Li","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence and Robotics, Hunan University, Changsha, Hunan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6406-4896","authenticated-orcid":false,"given":"Min","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Robotics, Hunan University, Changsha, Hunan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3995-4402","authenticated-orcid":false,"given":"Yuan","family":"Bian","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Robotics, Hunan University, Changsha, Hunan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4862-8975","authenticated-orcid":false,"given":"Xueping","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Information Science and Engineering, Hunan Normal University, Changsha, Hunan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4762-2993","authenticated-orcid":false,"given":"Zhaoyang","family":"Li","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Robotics, Hunan University, Changsha, HuNan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6636-1106","authenticated-orcid":false,"given":"Gen","family":"Li","sequence":"additional","affiliation":[{"name":"School of Informatics, University of Edinburgh, Edinburgh, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5365-6254","authenticated-orcid":false,"given":"Yaonan","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Robotics, Hunan University, Changsha, Hunan, 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":"10.1007\/978-3-030-58452-8_25"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01264"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00938"},{"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\/978-3-030-58565-5_13"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_29"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681058"},{"key":"e_1_3_2_1_8_1","volume-title":"Real-time referring expression comprehension by single-stage grounding network. arXiv preprint arXiv:1812.03426","author":"Chen Xinpeng","year":"2018","unstructured":"Xinpeng Chen, Lin Ma, Jingyuan Chen, Zequn Jie, Wei Liu, and Jiebo Luo. 2018. Real-time referring expression comprehension by single-stage grounding network. arXiv preprint arXiv:1812.03426 (2018)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01211"},{"key":"e_1_3_2_1_10_1","volume-title":"TransVG: End-to-End Visual Grounding with Transformers. In 2021 IEEE\/CVF International Conference on Computer Vision (ICCV). 1749-1759","author":"Deng Jiajun","year":"2021","unstructured":"Jiajun Deng, Zhengyuan Yang, Tianlang Chen, Wengang Zhou, and Houqiang Li. 2021. TransVG: End-to-End Visual Grounding with Transformers. In 2021 IEEE\/CVF International Conference on Computer Vision (ICCV). 1749-1759."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01169"},{"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":"10.1109\/CVPR.2012.6248074"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475397"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680998"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_6"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00398"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01508"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413902"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3711129.3711337"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00088"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00281"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01089"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"e_1_3_2_1_27_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_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00477"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00597"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20074"},{"key":"e_1_3_2_1_31_1","volume-title":"Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019a. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00506"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01535"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00469"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00217"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19769-7_5"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_16"},{"key":"e_1_3_2_1_38_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_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00845"},{"key":"e_1_3_2_1_40_1","volume-title":"Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767","author":"Redmon Joseph","year":"2018","unstructured":"Joseph Redmon and Ali Farhadi. 2018. Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767 (2018)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"e_1_3_2_1_42_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_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00479"},{"key":"e_1_3_2_1_44_1","volume-title":"Proceedings of the 5th ACM International Conference on Multimedia in Asia","author":"Tan Zehan","year":"2024","unstructured":"Zehan Tan, Weidong Yang, and Zhiwei Wang. 2024. Reimagining 3D Visual Grounding: Instance Segmentation and Transformers for Fragmented Point Cloud Scenarios. In Proceedings of the 5th ACM International Conference on Multimedia in Asia (Tainan, Taiwan) (MMAsia '23). Association for Computing Machinery, New York, NY, USA, Article 33, 7 pages."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00107"},{"key":"e_1_3_2_1_46_1","volume-title":"Eda: Easy data augmentation techniques for boosting performance on text classification tasks. arXiv preprint arXiv:1901.11196","author":"Wei Jason","year":"2019","unstructured":"Jason Wei and Kai Zou. 2019. Eda: Easy data augmentation techniques for boosting performance on text classification tasks. arXiv preprint arXiv:1901.11196 (2019)."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681071"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00928"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00474"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2973983"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_23"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00478"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00187"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681256"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3250471"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28525"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00437"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00840"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00330"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00292"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681660"},{"key":"e_1_3_2_1_63_1","volume-title":"Objects as points. arXiv preprint arXiv:1904.07850","author":"Zhou Xingyi","year":"2019","unstructured":"Xingyi Zhou, Dequan Wang, and Philipp Kr\u00e4henb\u00fchl. 2019. Objects as points. arXiv preprint arXiv:1904.07850 (2019)."},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00747"}],"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\/3746027.3755497","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:20:17Z","timestamp":1765308017000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755497"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":64,"alternative-id":["10.1145\/3746027.3755497","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755497","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"}}]}}