{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T19:58:13Z","timestamp":1774123093106,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":65,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National R&D project of China","award":["2021YFC3340304"],"award-info":[{"award-number":["2021YFC3340304"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3680614","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:27Z","timestamp":1729925967000},"page":"3818-3827","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["Cross-Task Knowledge Transfer for Semi-supervised Joint 3D Grounding and Captioning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-9329-754X","authenticated-orcid":false,"given":"Yang","family":"Liu","sequence":"first","affiliation":[{"name":"Wangxuan Institute of Computer Technology, State Key Laboratory of Multimedia Information Processing, Peking University, Beijing, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8179-4508","authenticated-orcid":false,"given":"Daizong","family":"Liu","sequence":"additional","affiliation":[{"name":"Wangxuan Institute of Computer Technology, State Key Laboratory of Multimedia Information Processing, Peking University, Beijing, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4944-9621","authenticated-orcid":false,"given":"Zongming","family":"Guo","sequence":"additional","affiliation":[{"name":"Wangxuan Institute of Computer Technology, State Key Laboratory of Multimedia Information Processing, Peking University, Beijing, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9860-0922","authenticated-orcid":false,"given":"Wei","family":"Hu","sequence":"additional","affiliation":[{"name":"Wangxuan Institute of Computer Technology, State Key Laboratory of Multimedia Information Processing, Peking University, Beijing, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Proceedings, Part I 16","author":"Achlioptas Panos","year":"2020","unstructured":"Panos Achlioptas, Ahmed Abdelreheem, Fei Xia, Mohamed Elhoseiny, and Leonidas Guibas. 2020. Referit3d: Neural listeners for fine-grained 3d object identification in real-world scenes. In Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part I 16. Springer, 422--440."},{"key":"e_1_3_2_1_2_1","volume-title":"Learning with pseudo-ensembles. Advances in neural information processing systems","author":"Bachman Philip","year":"2014","unstructured":"Philip Bachman, Ouais Alsharif, and Doina Precup. 2014. Learning with pseudo-ensembles. Advances in neural information processing systems, Vol. 27 (2014)."},{"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","volume-title":"Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization. 65--72","author":"Banerjee Satanjeev","year":"2005","unstructured":"Satanjeev Banerjee and Alon Lavie. 2005. METEOR: An automatic metric for MT evaluation with improved correlation with human judgments. In Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization. 65--72."},{"key":"e_1_3_2_1_5_1","volume-title":"Remixmatch: Semi-supervised learning with distribution alignment and augmentation anchoring. arXiv preprint arXiv:1911.09785","author":"Berthelot David","year":"2019","unstructured":"David Berthelot, Nicholas Carlini, Ekin D Cubuk, Alex Kurakin, Kihyuk Sohn, Han Zhang, and Colin Raffel. 2019. Remixmatch: Semi-supervised learning with distribution alignment and augmentation anchoring. arXiv preprint arXiv:1911.09785 (2019)."},{"key":"e_1_3_2_1_6_1","volume-title":"Mixmatch: A holistic approach to semi-supervised learning. Advances in neural information processing systems","author":"Berthelot David","year":"2019","unstructured":"David Berthelot, Nicholas Carlini, Ian Goodfellow, Nicolas Papernot, Avital Oliver, and Colin A Raffel. 2019. Mixmatch: A holistic approach to semi-supervised learning. Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01597"},{"key":"e_1_3_2_1_8_1","volume-title":"Proceedings, Part XX. Springer, 202--221","author":"Chen Dave Zhenyu","year":"2020","unstructured":"Dave Zhenyu Chen, Angel X Chang, and Matthias Nie\u00dfner. 2020. Scanrefer: 3d object localization in rgb-d scans using natural language. In Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part XX. Springer, 202--221."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_29"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01070"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00321"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01660"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00885"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.90"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00370"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3358415"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01189"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475397"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20062-5_14"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01684"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01485"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16253"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01508"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611902"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680758"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_24"},{"key":"e_1_3_2_1_28_1","volume-title":"Consistency-based semi-supervised learning for object detection. Advances in neural information processing systems","author":"Jeong Jisoo","year":"2019","unstructured":"Jisoo Jeong, Seungeui Lee, Jeesoo Kim, and Nojun Kwak. 2019. Consistency-based semi-supervised learning for object detection. Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_31"},{"key":"e_1_3_2_1_30_1","volume-title":"Rouge: A package for automatic evaluation of summaries. In Text summarization branches out. 74--81.","author":"Lin Chin-Yew","year":"2004","unstructured":"Chin-Yew Lin. 2004. Rouge: A package for automatic evaluation of summaries. In Text summarization branches out. 74--81."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3193449"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28146"},{"key":"e_1_3_2_1_33_1","volume-title":"Point cloud attacks in graph spectral domain: When 3d geometry meets graph signal processing","author":"Liu Daizong","year":"2023","unstructured":"Daizong Liu, Wei Hu, and Xin Li. 2023. Point cloud attacks in graph spectral domain: When 3d geometry meets graph signal processing. IEEE Transactions on Pattern Analysis and Machine Intelligence (2023)."},{"key":"e_1_3_2_1_34_1","volume-title":"Robust geometry-dependent attack for 3D point clouds","author":"Liu Daizong","year":"2023","unstructured":"Daizong Liu, Wei Hu, and Xin Li. 2023. Robust geometry-dependent attack for 3D point clouds. IEEE Transactions on Multimedia (2023)."},{"key":"e_1_3_2_1_35_1","volume-title":"Recent Advances, and Future Directions. arXiv preprint arXiv:2406.05785","author":"Liu Daizong","year":"2024","unstructured":"Daizong Liu, Yang Liu, Wencan Huang, and Wei Hu. 2024. A Survey on Text-guided 3D Visual Grounding: Elements, Recent Advances, and Future Directions. arXiv preprint arXiv:2406.05785 (2024)."},{"key":"e_1_3_2_1_36_1","volume-title":"Unbiased teacher for semi-supervised object detection. arXiv preprint arXiv:2102.09480","author":"Liu Yen-Cheng","year":"2021","unstructured":"Yen-Cheng Liu, Chih-Yao Ma, Zijian He, Chia-Wen Kuo, Kan Chen, Peizhao Zhang, Bichen Wu, Zsolt Kira, and Peter Vajda. 2021. Unbiased teacher for semi-supervised object detection. arXiv preprint arXiv:2102.09480 (2021)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00959"},{"key":"e_1_3_2_1_38_1","unstructured":"Ilya Loshchilov and Frank Hutter. 2018. Fixing weight decay regularization in adam. (2018)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01596"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01408"},{"key":"e_1_3_2_1_41_1","volume-title":"Proceedings of the 40th annual meeting of the Association for Computational Linguistics. 311--318","author":"Papineni Kishore","year":"2002","unstructured":"Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. Bleu: a method for automatic evaluation of machine translation. In Proceedings of the 40th annual meeting of the Association for Computational Linguistics. 311--318."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00937"},{"key":"e_1_3_2_1_44_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_45_1","volume-title":"Regularization with stochastic transformations and perturbations for deep semi-supervised learning. Advances in neural information processing systems","author":"Sajjadi Mehdi","year":"2016","unstructured":"Mehdi Sajjadi, Mehran Javanmardi, and Tolga Tasdizen. 2016. Regularization with stochastic transformations and perturbations for deep semi-supervised learning. Advances in neural information processing systems, Vol. 29 (2016)."},{"key":"e_1_3_2_1_46_1","volume-title":"Alexey Kurakin, and Chun-Liang Li.","author":"Sohn Kihyuk","year":"2020","unstructured":"Kihyuk Sohn, David Berthelot, Nicholas Carlini, Zizhao Zhang, Han Zhang, Colin A Raffel, Ekin Dogus Cubuk, Alexey Kurakin, and Chun-Liang Li. 2020. Fixmatch: Simplifying semi-supervised learning with consistency and confidence. Advances in neural information processing systems, Vol. 33 (2020), 596--608."},{"key":"e_1_3_2_1_47_1","volume-title":"A simple semi-supervised learning framework for object detection. arXiv preprint arXiv:2005.04757","author":"Sohn Kihyuk","year":"2020","unstructured":"Kihyuk Sohn, Zizhao Zhang, Chun-Liang Li, Han Zhang, Chen-Yu Lee, and Tomas Pfister. 2020. A simple semi-supervised learning framework for object detection. arXiv preprint arXiv:2005.04757 (2020)."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01835"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01319"},{"key":"e_1_3_2_1_50_1","volume-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. Advances in neural information processing systems","author":"Tarvainen Antti","year":"2017","unstructured":"Antti Tarvainen and Harri Valpola. 2017. Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01438"},{"key":"e_1_3_2_1_54_1","volume-title":"Spatiality-guided transformer for 3d dense captioning on point clouds. arXiv preprint arXiv:2204.10688","author":"Wang Heng","year":"2022","unstructured":"Heng Wang, Chaoyi Zhang, Jianhui Yu, and Weidong Cai. 2022. Spatiality-guided transformer for 3d dense captioning on point clouds. arXiv preprint arXiv:2204.10688 (2022)."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00251"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01843"},{"key":"e_1_3_2_1_57_1","volume-title":"Unsupervised data augmentation for consistency training. Advances in neural information processing systems","author":"Xie Qizhe","year":"2020","unstructured":"Qizhe Xie, Zihang Dai, Eduard Hovy, Thang Luong, and Quoc Le. 2020. Unsupervised data augmentation for consistency training. Advances in neural information processing systems, Vol. 33 (2020), 6256--6268."},{"key":"e_1_3_2_1_58_1","volume-title":"International conference on machine learning. PMLR","author":"Xu Kelvin","year":"2015","unstructured":"Kelvin Xu, Jimmy Ba, Ryan Kiros, Kyunghyun Cho, Aaron Courville, Ruslan Salakhudinov, Rich Zemel, and Yoshua Bengio. 2015. Show, attend and tell: Neural image caption generation with visual attention. In International conference on machine learning. PMLR, 2048--2057."},{"key":"e_1_3_2_1_59_1","volume-title":"Weakly-Supervised 3D Visual Grounding based on Visual Linguistic Alignment. arXiv preprint arXiv:2312.09625","author":"Xu Xiaoxu","year":"2023","unstructured":"Xiaoxu Xu, Yitian Yuan, Qiudan Zhang, Wenhui Wu, Zequn Jie, Lin Ma, and Xu Wang. 2023. Weakly-Supervised 3D Visual Grounding based on Visual Linguistic Alignment. arXiv preprint arXiv:2312.09625 (2023)."},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00187"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00837"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00181"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00292"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01109"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00472"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680614","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680614","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:56Z","timestamp":1750295876000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680614"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":65,"alternative-id":["10.1145\/3664647.3680614","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680614","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}