{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T00:04:15Z","timestamp":1774051455419,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":74,"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:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Wafer-scale silicon optical switching interconnected on-chip computing system","award":["2022YFB2804100"],"award-info":[{"award-number":["2022YFB2804100"]}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["20211710187"],"award-info":[{"award-number":["20211710187"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681343","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:49Z","timestamp":1729925989000},"page":"4709-4718","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["Point-GCC: Universal Self-supervised 3D Scene Pre-training via Geometry-Color Contrast"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-3094-7621","authenticated-orcid":false,"given":"Guofan","family":"Fan","sequence":"first","affiliation":[{"name":"Xi'an Jiaotong University & IIISCT, Xi'an, Shaanxi, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2554-5141","authenticated-orcid":false,"given":"Zekun","family":"Qi","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong University & IIISCT, Xi'an, Shaanxi, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1475-3107","authenticated-orcid":false,"given":"Wenkai","family":"Shi","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong University, Xi'an, Shaanxi, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9226-3366","authenticated-orcid":false,"given":"Kaisheng","family":"Ma","sequence":"additional","affiliation":[{"name":"IIIS, Tsinghua University, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00967"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.170"},{"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","volume-title":"8th International Conference on Learning Representations, ICLR 2020","author":"Asano Yuki Markus","year":"2020","unstructured":"Yuki Markus Asano, Christian Rupprecht, and Andrea Vedaldi. 2020. Self-labelling via simultaneous clustering and representation learning. In 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26--30, 2020. OpenReview.net. https:\/\/openreview.net\/forum?id=Hyx-jyBFPr"},{"key":"e_1_3_2_1_5_1","volume-title":"Learning representations by maximizing mutual information across views. Advances in neural information processing systems","author":"Bachman Philip","year":"2019","unstructured":"Philip Bachman, R Devon Hjelm, and William Buchwalter. 2019. Learning representations by maximizing mutual information across views. Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_6_1","volume-title":"BEiT: BERT Pre-Training of Image Transformers. In Int. Conf. Learn. Represent. (ICLR). OpenReview.net.","author":"Bao Hangbo","year":"2022","unstructured":"Hangbo Bao, Li Dong, Songhao Piao, and Furu Wei. 2022. BEiT: BERT Pre-Training of Image Transformers. In Int. Conf. Learn. Represent. (ICLR). OpenReview.net."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_9"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/978--3-030-01264--9_9"},{"key":"e_1_3_2_1_9_1","volume-title":"Unsupervised learning of visual features by contrasting cluster assignments. Advances in neural information processing systems","author":"Caron Mathilde","year":"2020","unstructured":"Mathilde Caron, Ishan Misra, Julien Mairal, Priya Goyal, Piotr Bojanowski, and Armand Joulin. 2020. Unsupervised learning of visual features by contrasting cluster assignments. Advances in neural information processing systems, Vol. 33 (2020), 9912--9924."},{"key":"e_1_3_2_1_10_1","volume-title":"Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020","author":"Caron Mathilde","year":"2020","unstructured":"Mathilde Caron, Ishan Misra, Julien Mairal, Priya Goyal, Piotr Bojanowski, and Armand Joulin. 2020. Unsupervised Learning of Visual Features by Contrasting Cluster Assignments. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6--12, 2020, virtual, Hugo Larochelle, Marc'Aurelio Ranzato, Raia Hadsell, Maria-Florina Balcan, and Hsuan-Tien Lin (Eds.). https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/70feb62b69f16e0238f741fab228fec2-Abstract.html"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2210.16810"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.626"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01518"},{"key":"e_1_3_2_1_14_1","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML) (Proceedings of Machine Learning Research","volume":"1607","author":"Chen Ting","unstructured":"Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey E. Hinton. 2020. A Simple Framework for Contrastive Learning of Visual Representations. In Proc. Int. Conf. Mach. Learn. (ICML) (Proceedings of Machine Learning Research, Vol. 119). PMLR, 1597--1607."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978--3-031--19824--3_32"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00319"},{"key":"e_1_3_2_1_17_1","unstructured":"MMDetection3D Contributors. 2020. MMDetection3D: OpenMMLab next-generation platform for general 3D object detection. https:\/\/github.com\/open-mmlab\/mmdetection3d."},{"key":"e_1_3_2_1_18_1","volume-title":"Weinberger (Eds.)","volume":"26","author":"Cuturi Marco","year":"2013","unstructured":"Marco Cuturi. 2013. Sinkhorn Distances: Lightspeed Computation of Optimal Transport. In Advances in Neural Information Processing Systems, C.J. Burges, L. Bottou, M. Welling, Z. Ghahramani, and K.Q. Weinberger (Eds.), Vol. 26. Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2013\/file\/af21d0c97db2e27e13572cbf59eb343d-Paper.pdf"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"e_1_3_2_1_21_1","volume-title":"Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks 1, NeurIPS Datasets and Benchmarks 2021","author":"Dehghan Afshin","year":"2021","unstructured":"Afshin Dehghan, Gilad Baruch, Zhuoyuan Chen, Yuri Feigin, Peter Fu, Thomas Gebauer, Daniel Kurz, Tal Dimry, Brandon Joffe, Arik Schwartz, and Elad Shulman. 2021. ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data. In Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks 1, NeurIPS Datasets and Benchmarks 2021, December 2021, virtual, Joaquin Vanschoren and Sai-Kit Yeung (Eds.). https:\/\/datasets-benchmarks-proceedings.neurips.cc\/paper\/2021\/hash\/66f041e16a60928b05a7e228a89c3799-Abstract-round1.html"},{"key":"e_1_3_2_1_22_1","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019","volume":"1","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019, Minneapolis, MN, USA, June 2--7, 2019, Volume 1 (Long and Short Papers). Association for Computational Linguistics, 4171--4186."},{"key":"e_1_3_2_1_23_1","volume-title":"DreamLLM: Synergistic Multimodal Comprehension and Creation. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=y01KGvd9Bw","author":"Dong Runpei","year":"2024","unstructured":"Runpei Dong, Chunrui Han, Yuang Peng, Zekun Qi, Zheng Ge, Jinrong Yang, Liang Zhao, Jianjian Sun, Hongyu Zhou, Haoran Wei, Xiangwen Kong, Xiangyu Zhang, Kaisheng Ma, and Li Yi. 2024. DreamLLM: Synergistic Multimodal Comprehension and Creation. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=y01KGvd9Bw"},{"key":"e_1_3_2_1_24_1","volume-title":"Int. Conf. Learn. Represent. (ICLR).","author":"Dong Runpei","year":"2023","unstructured":"Runpei Dong, Zekun Qi, Linfeng Zhang, Junbo Zhang, Jianjian Sun, Zheng Ge, Li Yi, and Kaisheng Ma. 2023. Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?. In Int. Conf. Learn. Represent. (ICLR)."},{"key":"e_1_3_2_1_25_1","volume-title":"Masked Autoencoders Are Scalable Vision Learners. In IEEE\/CVF Conf. Comput. Vis. Pattern Recog. (CVPR).","author":"He Kaiming","unstructured":"Kaiming He, Xinlei Chen, Saining Xie, Yanghao Li, Piotr Doll\u00e1r, and Ross B. Girshick. 2022. Masked Autoencoders Are Scalable Vision Learners. In IEEE\/CVF Conf. Comput. Vis. Pattern Recog. (CVPR)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00455"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01533"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2301.00157"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00647"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00492"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2302.02871"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01163"},{"key":"e_1_3_2_1_33_1","volume-title":"Masked Discrimination for Self-Supervised Learning on Point Clouds. In Eur. Conf. Comput. Vis. (ECCV).","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 Eur. Conf. Comput. Vis. (ECCV)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00294"},{"key":"e_1_3_2_1_35_1","volume-title":"International conference on machine learning. PMLR, 97--105","author":"Long Mingsheng","year":"2015","unstructured":"Mingsheng Long, Yue Cao, Jianmin Wang, and Michael Jordan. 2015. Learning transferable features with deep adaptation networks. In International conference on machine learning. PMLR, 97--105."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00290"},{"key":"e_1_3_2_1_37_1","volume-title":"Masked Autoencoders for Point Cloud Self-supervised Learning. In Eur. Conf. Comput. Vis. (ECCV).","author":"Pang Yatian","year":"2022","unstructured":"Yatian Pang, Wenxiao Wang, Francis E. H. Tay, Wei Liu, Yonghong Tian, and Li Yuan. 2022. Masked Autoencoders for Point Cloud Self-supervised Learning. In Eur. Conf. Comput. Vis. (ECCV)."},{"key":"e_1_3_2_1_38_1","volume-title":"DreamBench: A Human-Aligned Benchmark for Personalized Image Generation. ArXiv","author":"Peng Yuang","year":"2024","unstructured":"Yuang Peng, Yuxin Cui, Haomiao Tang, Zekun Qi, Runpei Dong, Jing Bai, Chunrui Han, Zheng Ge, Xiangyu Zhang, and Shu-Tao Xia. 2024. DreamBench: A Human-Aligned Benchmark for Personalized Image Generation. ArXiv, Vol. abs\/2406.16855 (2024). https:\/\/api.semanticscholar.org\/CorpusID:270702690"},{"key":"e_1_3_2_1_39_1","volume-title":"Int. Conf. Comput. Vis. (ICCV). IEEE, 9276--9285","author":"Qi Charles R.","unstructured":"Charles R. Qi, Or Litany, Kaiming He, and Leonidas J. Guibas. 2019. Deep Hough Voting for 3D Object Detection in Point Clouds. In Int. Conf. Comput. Vis. (ICCV). IEEE, 9276--9285."},{"key":"e_1_3_2_1_40_1","volume-title":"Guibas","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. In Adv. Neural Inform. Process. Syst. (NIPS). 5099--5108."},{"key":"e_1_3_2_1_41_1","volume-title":"International Conference on Machine Learning (ICML).","author":"Qi Zekun","year":"2023","unstructured":"Zekun Qi, Runpei Dong, Guofan Fan, Zheng Ge, Xiangyu Zhang, Kaisheng Ma, and Li Yi. 2023. Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining. In International Conference on Machine Learning (ICML)."},{"key":"e_1_3_2_1_42_1","volume-title":"ShapeLLM: Universal 3D Object Understanding for Embodied Interaction. arXiv preprint arXiv:2402.17766","author":"Qi Zekun","year":"2024","unstructured":"Zekun Qi, Runpei Dong, Shaochen Zhang, Haoran Geng, Chunrui Han, Zheng Ge, He Wang, Li Yi, and Kaisheng Ma. 2024. ShapeLLM: Universal 3D Object Understanding for Embodied Interaction. arXiv preprint arXiv:2402.17766 (2024)."},{"key":"e_1_3_2_1_43_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Qi Zekun","year":"2024","unstructured":"Zekun Qi, Muzhou Yu, Runpei Dong, and Kaisheng Ma. 2024. Vpp: Efficient conditional 3d generation via voxel-point progressive representation. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_44_1","volume-title":"Mohamed Elhoseiny, and Bernard Ghanem.","author":"Qian Guocheng","year":"2022","unstructured":"Guocheng Qian, Yuchen Li, Houwen Peng, Jinjie Mai, Hasan Abed Al Kader Hammoud, Mohamed Elhoseiny, and Bernard Ghanem. 2022. PointNeXt: Revisiting PointNet with Improved Training and Scaling Strategies. In Adv. Neural Inform. Process. Syst. (NeurIPS)."},{"key":"e_1_3_2_1_45_1","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML) (Proceedings of Machine Learning Research","volume":"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, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. In Proc. Int. Conf. Mach. Learn. (ICML) (Proceedings of Machine Learning Research, Vol. 139). PMLR, 8748--8763."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01837"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01300"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1007\/978--3-031--19827--4_8"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1007\/978--3-031--20080--9_28"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2302.02858"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00273"},{"key":"e_1_3_2_1_53_1","volume-title":"Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022","author":"Wang Haiyang","year":"2022","unstructured":"Haiyang Wang, Lihe Ding, Shaocong Dong, Shaoshuai Shi, Aoxue Li, Jianan Li, Zhenguo Li, and Liwei Wang. 2022. CAGroup3D: Class-Aware Grouping for 3D Object Detection on Point Clouds. In Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28 - December 9, 2022, Sanmi Koyejo, S. Mohamed, A. Agarwal, Danielle Belgrave, K. Cho, and A. Oh (Eds.). http:\/\/papers.nips.cc\/paper_files\/paper\/2022\/hash\/c1aaf7c3f306fe94f77236dc0756d771-Abstract-Conference.html"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01187"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00444"},{"key":"e_1_3_2_1_56_1","volume-title":"Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022","author":"Wu Xiaoyang","year":"2022","unstructured":"Xiaoyang Wu, Yixing Lao, Li Jiang, Xihui Liu, and Hengshuang Zhao. 2022. Point Transformer V2: Grouped Vector Attention and Partition-based Pooling. In Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28 - December 9, 2022, Sanmi Koyejo, S. Mohamed, A. Agarwal, Danielle Belgrave, K. Cho, and A. Oh (Eds.)."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00908"},{"key":"e_1_3_2_1_58_1","volume-title":"International conference on machine learning. PMLR, 478--487","author":"Xie Junyuan","year":"2016","unstructured":"Junyuan Xie, Ross Girshick, and Ali Farhadi. 2016. Unsupervised deep embedding for clustering analysis. In International conference on machine learning. PMLR, 478--487."},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1007\/978--3-030--58580--8_34"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2205.13543"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00120"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01336"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2207.10589"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01871"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i16.17689"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00219"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"crossref","unstructured":"Junbo Zhang Guofan Fan Guanghan Wang Zhengyuan Su Kaisheng Ma and Li Yi. 2023. Language-Assisted 3D Feature Learning for Semantic Scene Understanding. In AAAI.","DOI":"10.1609\/aaai.v37i3.25453"},{"key":"e_1_3_2_1_69_1","unstructured":"Renrui Zhang Ziyu Guo Peng Gao Rongyao Fang Bin Zhao Dong Wang Yu Qiao and Hongsheng Li. 2022. Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training. In Adv. Neural Inform. Process. Syst. (NeurIPS)."},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02085"},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01009"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01690"},{"key":"e_1_3_2_1_73_1","volume-title":"Point Transformer. In Int. Conf. Comput. Vis. (ICCV). IEEE, 16239--16248","author":"Zhao Hengshuang","year":"2021","unstructured":"Hengshuang Zhao, Li Jiang, Jiaya Jia, Philip H. S. Torr, and Vladlen Koltun. 2021. Point Transformer. In Int. Conf. Comput. Vis. (ICCV). IEEE, 16239--16248."},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1007\/978--3-030--58545--7_30"}],"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\/3664647.3681343","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681343","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:43Z","timestamp":1750295863000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681343"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":74,"alternative-id":["10.1145\/3664647.3681343","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681343","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"}}]}}