{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:38:46Z","timestamp":1777657126937,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":66,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Key R&D Program of China","award":["No.2022ZD0118201"],"award-info":[{"award-number":["No.2022ZD0118201"]}]},{"name":"the Natural Science Foundation of Fujian Province of China","award":["No.2021J01002, No.2022J06001"],"award-info":[{"award-number":["No.2021J01002, No.2022J06001"]}]},{"name":"the National Natural Science Foundation of China","award":["No. U21B2037, No. U22B2051, No. 62176222, No. 62176223, No. 62176226, No. 62072386, No. 62072387, No. 62072389, No. 62002305, No. 62272401"],"award-info":[{"award-number":["No. U21B2037, No. U22B2051, No. 62176222, No. 62176223, No. 62176226, No. 62072386, No. 62072387, No. 62072389, No. 62002305, No. 62272401"]}]},{"name":"the National Science Fund for Distinguished Young Scholars","award":["No.62025603"],"award-info":[{"award-number":["No.62025603"]}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["No.2023M732948"],"award-info":[{"award-number":["No.2023M732948"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3611767","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:40Z","timestamp":1698391660000},"page":"3403-3414","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["Beyond First Impressions: Integrating Joint Multi-modal Cues for Comprehensive 3D Representation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-0289-9672","authenticated-orcid":false,"given":"Haowei","family":"Wang","sequence":"first","affiliation":[{"name":"Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9581-8790","authenticated-orcid":false,"given":"Jiji","family":"Tang","sequence":"additional","affiliation":[{"name":"Netease Inc., Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9956-6308","authenticated-orcid":false,"given":"Jiayi","family":"Ji","sequence":"additional","affiliation":[{"name":"Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3912-9306","authenticated-orcid":false,"given":"Xiaoshuai","family":"Sun","sequence":"additional","affiliation":[{"name":"Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1248-2090","authenticated-orcid":false,"given":"Rongsheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Netease Inc., Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8744-3423","authenticated-orcid":false,"given":"Yiwei","family":"Ma","sequence":"additional","affiliation":[{"name":"Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8736-272X","authenticated-orcid":false,"given":"Minda","family":"Zhao","sequence":"additional","affiliation":[{"name":"Netease Inc., Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3626-4094","authenticated-orcid":false,"given":"Lincheng","family":"Li","sequence":"additional","affiliation":[{"name":"Netease Inc., Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7292-876X","authenticated-orcid":false,"given":"Zeng","family":"Zhao","sequence":"additional","affiliation":[{"name":"Netease Inc., Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9858-809X","authenticated-orcid":false,"given":"Tangjie","family":"Lv","sequence":"additional","affiliation":[{"name":"Netease Inc., Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9163-2932","authenticated-orcid":false,"given":"Rongrong","family":"Ji","sequence":"additional","affiliation":[{"name":"Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"International conference on machine learning. PMLR, 40--49","author":"Achlioptas Panos","year":"2018","unstructured":"Panos Achlioptas, Olga Diamanti, Ioannis Mitliagkas, and Leonidas Guibas. 2018. Learning representations and generative models for 3d point clouds. In International conference on machine learning. PMLR, 40--49."},{"key":"e_1_3_2_1_2_1","first-page":"23716","article-title":"Flamingo: a visual language model for few-shot learning","volume":"35","author":"Alayrac Jean-Baptiste","year":"2022","unstructured":"Jean-Baptiste Alayrac, Jeff Donahue, Pauline Luc, Antoine Miech, Iain Barr, Yana Hasson, Karel Lenc, Arthur Mensch, Katherine Millican, Malcolm Reynolds, et al. 2022. Flamingo: a visual language model for few-shot learning. Advances in Neural Information Processing Systems, Vol. 35 (2022), 23716--23736.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.170"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2011.6130444"},{"key":"e_1_3_2_1_5_1","volume-title":"Jamie Ryan Kiros, and Geoffrey E. Hinton","author":"Ba Jimmy Lei","year":"2016","unstructured":"Jimmy Lei Ba, Jamie Ryan Kiros, and Geoffrey E. Hinton. 2016. Layer Normalization. arxiv: 1607.06450"},{"key":"e_1_3_2_1_6_1","volume-title":"Scale-invariant heat kernel signatures for non-rigid shape recognition. In 2010 IEEE computer society conference on computer vision and pattern recognition","author":"Bronstein Michael M","unstructured":"Michael M Bronstein and Iasonas Kokkinos. 2010. Scale-invariant heat kernel signatures for non-rigid shape recognition. In 2010 IEEE computer society conference on computer vision and pattern recognition. IEEE, 1704--1711."},{"key":"e_1_3_2_1_7_1","volume-title":"Shapenet: An information-rich 3d model repository. arXiv preprint arXiv:1512.03012","author":"Chang Angel X","year":"2015","unstructured":"Angel X Chang, Thomas Funkhouser, Leonidas Guibas, Pat Hanrahan, Qixing Huang, Zimo Li, Silvio Savarese, Manolis Savva, Shuran Song, Hao Su, et al. 2015. Shapenet: An information-rich 3d model repository. arXiv preprint arXiv:1512.03012 (2015)."},{"key":"e_1_3_2_1_8_1","volume-title":"UK","author":"Chen Yen-Chun","year":"2020","unstructured":"Yen-Chun Chen, Linjie Li, Licheng Yu, Ahmed El Kholy, Faisal Ahmed, Zhe Gan, Yu Cheng, and Jingjing Liu. 2020. Uniter: Universal image-text representation learning. In Computer Vision-ECCV 2020: 16th European Conference, Glasgow, UK, August 23-28, 2020, Proceedings, Part XXX. Springer, 104--120."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.5244\/C.35.217"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.329"},{"key":"e_1_3_2_1_11_1","volume-title":"Proceedings of the International Conference on Machine Learning, ICML. 6373--6391","author":"Fei Hao","year":"2022","unstructured":"Hao Fei, Shengqiong Wu, Yafeng Ren, and Meishan Zhang. 2022. Matching Structure for Dual Learning. In Proceedings of the International Conference on Machine Learning, ICML. 6373--6391."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.383"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-021-0229-5"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00007"},{"key":"e_1_3_2_1_15_1","volume-title":"Jeya Maria Jose Valanarasu, and Vishal M Patel","author":"Hegde Deepti","year":"2023","unstructured":"Deepti Hegde, Jeya Maria Jose Valanarasu, and Vishal M Patel. 2023. CLIP goes 3D: Leveraging Prompt Tuning for Language Grounded 3D Recognition. arXiv preprint arXiv:2303.11313 (2023)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01709"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00263"},{"key":"e_1_3_2_1_18_1","volume-title":"Tel Aviv","author":"Ju Chen","year":"2022","unstructured":"Chen Ju, Tengda Han, Kunhao Zheng, Ya Zhang, and Weidi Xie. 2022. Prompting visual-language models for efficient video understanding. In Computer Vision-ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part XXXV. Springer, 105--124."},{"key":"e_1_3_2_1_19_1","first-page":"23580","article-title":"Sagemix: Saliency-guided mixup for point clouds","volume":"35","author":"Lee Sanghyeok","year":"2022","unstructured":"Sanghyeok Lee, Minkyu Jeon, Injae Kim, Yunyang Xiong, and Hyunwoo J Kim. 2022. Sagemix: Saliency-guided mixup for point clouds. Advances in Neural Information Processing Systems, Vol. 35 (2022), 23580--23592.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00490"},{"key":"e_1_3_2_1_21_1","volume-title":"Visualbert: A simple and performant baseline for vision and language. arXiv preprint arXiv:1908.03557","author":"Li Liunian Harold","year":"2019","unstructured":"Liunian Harold Li, Mark Yatskar, Da Yin, Cho-Jui Hsieh, and Kai-Wei Chang. 2019. Visualbert: A simple and performant baseline for vision and language. arXiv preprint arXiv:1908.03557 (2019)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"e_1_3_2_1_23_1","volume-title":"Oscar: Object-semantics aligned pre-training for vision-language tasks. In Computer Vision-ECCV 2020: 16th European Conference","author":"Li Xiujun","year":"2020","unstructured":"Xiujun Li, Xi Yin, Chunyuan Li, Pengchuan Zhang, Xiaowei Hu, Lei Zhang, Lijuan Wang, Houdong Hu, Li Dong, Furu Wei, et al. 2020. Oscar: Object-semantics aligned pre-training for vision-language tasks. In Computer Vision-ECCV 2020: 16th European Conference, Glasgow, UK, August 23-28, 2020, Proceedings, Part XXX 16. Springer, 121--137."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-18916-6_42"},{"key":"e_1_3_2_1_25_1","volume-title":"Tel Aviv","author":"Liu Haotian","year":"2022","unstructured":"Haotian Liu, Mu Cai, and Yong Jae Lee. 2022. Masked discrimination for self-supervised learning on point clouds. In Computer Vision-ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part II. Springer, 657--675."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00534"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58592-1_20"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00294"},{"key":"e_1_3_2_1_29_1","volume-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. Advances in neural information processing systems","author":"Lu Jiasen","year":"2019","unstructured":"Jiasen Lu, Dhruv Batra, Devi Parikh, and Stefan Lee. 2019. Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"e_1_3_2_1_31_1","volume-title":"Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework. In International Conference on Learning Representations.","author":"Ma Xu","unstructured":"Xu Ma, Can Qin, Haoxuan You, Haoxi Ran, and Yun Fu. [n.,d.]. Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547910"},{"key":"e_1_3_2_1_33_1","volume-title":"X-Mesh: Towards Fast and Accurate Text-driven 3D Stylization via Dynamic Textual Guidance. arXiv preprint arXiv:2303.15764","author":"Ma Yiwei","year":"2023","unstructured":"Yiwei Ma, Xiaioqing Zhang, Xiaoshuai Sun, Jiayi Ji, Haowei Wang, Guannan Jiang, Weilin Zhuang, and Rongrong Ji. 2023. X-Mesh: Towards Fast and Accurate Text-driven 3D Stylization via Dynamic Textual Guidance. arXiv preprint arXiv:2303.15764 (2023)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7353481"},{"key":"e_1_3_2_1_35_1","volume-title":"Tel Aviv","author":"Mu Norman","year":"2022","unstructured":"Norman Mu, Alexander Kirillov, David Wagner, and Saining Xie. 2022. Slip: Self-supervision meets language-image pre-training. In Computer Vision-ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part XXVI. Springer, 529--544."},{"key":"e_1_3_2_1_36_1","volume-title":"Tel Aviv","author":"Pang Yatian","year":"2022","unstructured":"Yatian Pang, Wenxiao Wang, Francis EH Tay, Wei Liu, Yonghong Tian, and Li Yuan. 2022. Masked autoencoders for point cloud self-supervised learning. In Computer Vision-ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part II. Springer, 604--621."},{"key":"e_1_3_2_1_37_1","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition. 652--660","author":"Qi Charles R","year":"2017","unstructured":"Charles R Qi, Hao Su, Kaichun Mo, and Leonidas J Guibas. 2017a. Pointnet: Deep learning on point sets for 3d classification and segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition. 652--660."},{"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. 2017b. 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","first-page":"23192","article-title":"Pointnext: Revisiting pointnet with improved training and scaling strategies","volume":"35","author":"Qian Guocheng","year":"2022","unstructured":"Guocheng Qian, Yuchen Li, Houwen Peng, Jinjie Mai, Hasan Hammoud, Mohamed Elhoseiny, and Bernard Ghanem. 2022. Pointnext: Revisiting pointnet with improved training and scaling strategies. Advances in Neural Information Processing Systems, Vol. 35 (2022), 23192--23204.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_40_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_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01837"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01054"},{"key":"e_1_3_2_1_43_1","volume-title":"Computer graphics forum","author":"Sun Jian","unstructured":"Jian Sun, Maks Ovsjanikov, and Leonidas Guibas. 2009. A concise and provably informative multi-scale signature based on heat diffusion. In Computer graphics forum, Vol. 28. Wiley Online Library, 1383--1392."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"e_1_3_2_1_45_1","volume-title":"Mlp-mixer: An all-mlp architecture for vision. Advances in neural information processing systems","author":"Tolstikhin Ilya O","year":"2021","unstructured":"Ilya O Tolstikhin, Neil Houlsby, Alexander Kolesnikov, Lucas Beyer, Xiaohua Zhai, Thomas Unterthiner, Jessica Yung, Andreas Steiner, Daniel Keysers, Jakob Uszkoreit, et al. 2021. Mlp-mixer: An all-mlp architecture for vision. Advances in neural information processing systems, Vol. 34 (2021), 24261--24272."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00167"},{"key":"e_1_3_2_1_47_1","volume-title":"Attention is all you need. Advances in neural information processing systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, ?ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00273"},{"key":"e_1_3_2_1_49_1","volume-title":"Towards real-time panoptic narrative grounding by an end-to-end grounding network. arXiv preprint arXiv:2301.03160","author":"Wang Haowei","year":"2023","unstructured":"Haowei Wang, Jiayi Ji, Yiyi Zhou, Yongjian Wu, and Xiaoshuai Sun. 2023. Towards real-time panoptic narrative grounding by an end-to-end grounding network. arXiv preprint arXiv:2301.03160 (2023)."},{"key":"e_1_3_2_1_50_1","volume-title":"P2p: Tuning pre-trained image models for point cloud analysis with point-to-pixel prompting. Advances in neural information processing systems","author":"Wang Ziyi","year":"2022","unstructured":"Ziyi Wang, Xumin Yu, Yongming Rao, Jie Zhou, and Jiwen Lu. 2022. P2p: Tuning pre-trained image models for point cloud analysis with point-to-pixel prompting. Advances in neural information processing systems, Vol. 35 (2022), 14388--14402."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.09.008"},{"key":"e_1_3_2_1_52_1","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition. 1912--1920","author":"Wu Zhirong","year":"2015","unstructured":"Zhirong Wu, Shuran Song, Aditya Khosla, Fisher Yu, Linguang Zhang, Xiaoou Tang, and Jianxiong Xiao. 2015. 3d shapenets: A deep representation for volumetric shapes. In Proceedings of the IEEE conference on computer vision and pattern recognition. 1912--1920."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3262786"},{"key":"e_1_3_2_1_54_1","volume-title":"UK","author":"Xie Haozhe","year":"2020","unstructured":"Haozhe Xie, Hongxun Yao, Shangchen Zhou, Jiageng Mao, Shengping Zhang, and Wenxiu Sun. 2020. Grnet: Gridding residual network for dense point cloud completion. In Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23-28, 2020, Proceedings, Part IX. Springer, 365--381."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.544"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00319"},{"key":"e_1_3_2_1_57_1","volume-title":"Juan Carlos Niebles, and Silvio Savarese","author":"Xue Le","year":"2022","unstructured":"Le Xue, Mingfei Gao, Chen Xing, Roberto Mart\u00edn-Mart\u00edn, Jiajun Wu, Caiming Xiong, Ran Xu, Juan Carlos Niebles, and Silvio Savarese. 2022. ULIP: Learning Unified Representation of Language, Image and Point Cloud for 3D Understanding. arXiv preprint arXiv:2212.05171 (2022)."},{"key":"e_1_3_2_1_58_1","unstructured":"Xu Yan Heshen Zhan Chaoda Zheng Jiantao Gao Ruimao Zhang Shuguang Cui and Zhen Li. [n. d.]. Let Images Give You More: Point Cloud Cross-Modal Training for Shape Analysis. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01871"},{"key":"e_1_3_2_1_61_1","first-page":"36067","article-title":"Glipv2: Unifying localization and vision-language understanding","volume":"35","author":"Zhang Haotian","year":"2022","unstructured":"Haotian Zhang, Pengchuan Zhang, Xiaowei Hu, Yen-Chun Chen, Liunian Li, Xiyang Dai, Lijuan Wang, Lu Yuan, Jenq-Neng Hwang, and Jianfeng Gao. 2022b. Glipv2: Unifying localization and vision-language understanding. Advances in Neural Information Processing Systems, Vol. 35 (2022), 36067--36080.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_62_1","volume-title":"CLIP-FO3D: Learning Free Open-world 3D Scene Representations from 2D Dense CLIP. arXiv preprint arXiv:2303.04748","author":"Zhang Junbo","year":"2023","unstructured":"Junbo Zhang, Runpei Dong, and Kaisheng Ma. 2023. CLIP-FO3D: Learning Free Open-world 3D Scene Representations from 2D Dense CLIP. arXiv preprint arXiv:2303.04748 (2023)."},{"key":"e_1_3_2_1_63_1","unstructured":"Renrui Zhang Ziyu Guo Peng Gao Rongyao Fang Bin Zhao Dong Wang Yu Qiao and Hongsheng Li. [n. d.]. Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00836"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.442"}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611767","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3611767","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:13:39Z","timestamp":1755821619000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611767"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":66,"alternative-id":["10.1145\/3581783.3611767","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3611767","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}