{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T16:10:52Z","timestamp":1783613452934,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":45,"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 Natural Science Foundation of China","award":["62176124"],"award-info":[{"award-number":["62176124"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3612226","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:30Z","timestamp":1698391650000},"page":"4169-4177","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Transformer-based Point Cloud Generation Network"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-1364-6305","authenticated-orcid":false,"given":"Rui","family":"Xu","sequence":"first","affiliation":[{"name":"Nanjing University of Science and Techonology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0851-6805","authenticated-orcid":false,"given":"Le","family":"Hui","sequence":"additional","affiliation":[{"name":"Nanjing University of Science and Techonology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6099-1673","authenticated-orcid":false,"given":"Yuehui","family":"Han","sequence":"additional","affiliation":[{"name":"Nanjing University of Science and Techonology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0968-8556","authenticated-orcid":false,"given":"Jianjun","family":"Qian","sequence":"additional","affiliation":[{"name":"Nanjing University of Science and Techonology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6978-8834","authenticated-orcid":false,"given":"Jin","family":"Xie","sequence":"additional","affiliation":[{"name":"Nanjing University of Science and Techonology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"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. 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. 40--49."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00967"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00733"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_22"},{"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","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_7_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_1_8_1","volume-title":"Generative adversarial nets. Advances in neural information processing systems","author":"Goodfellow Ian","year":"2014","unstructured":"Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative adversarial nets. Advances in neural information processing systems, Vol. 27 (2014)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-021-0229-5"},{"key":"e_1_3_2_1_10_1","volume-title":"3D Siamese voxel-to-BEV tracker for sparse point clouds. Advances in neural information processing systems","author":"Hui Le","year":"2021","unstructured":"Le Hui, Lingpeng Wang, Mingmei Cheng, Jin Xie, and Jian Yang. 2021. 3D Siamese voxel-to-BEV tracker for sparse point clouds. Advances in neural information processing systems, Vol. 34 (2021), 28714--28727."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_24"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.99"},{"key":"e_1_3_2_1_13_1","volume-title":"Point cloud gan. arXiv preprint arXiv:1810.05795","author":"Li Chun-Liang","year":"2018","unstructured":"Chun-Liang Li, Manzil Zaheer, Yang Zhang, Barnabas Poczos, and Ruslan Salakhutdinov. 2018. Point cloud gan. arXiv preprint arXiv:1810.05795 (2018)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01451"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12278"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.34133\/cbsystems.0002"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00534"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2943235"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00286"},{"key":"e_1_3_2_1_20_1","volume-title":"3D-LMNet: Latent embedding matching for accurate and diverse 3D point cloud reconstruction from a single image. arXiv preprint arXiv:1807.07796","author":"Mandikal Priyanka","year":"2018","unstructured":"Priyanka Mandikal, KL Navaneet, Mayank Agarwal, and R Venkatesh Babu. 2018. 3D-LMNet: Latent embedding matching for accurate and diverse 3D point cloud reconstruction from a single image. arXiv preprint arXiv:1807.07796 (2018)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00117"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00166"},{"key":"e_1_3_2_1_23_1","volume-title":"Proceedings of the IEEE\/CVF 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\/CVF Conference on Computer Vision and Pattern Recognition. 652--660."},{"key":"e_1_3_2_1_24_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_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00636"},{"key":"e_1_3_2_1_26_1","volume-title":"C-C Jay Kuo, and Yun Fu","author":"Qin Can","year":"2019","unstructured":"Can Qin, Haoxuan You, Lichen Wang, C-C Jay Kuo, and Yun Fu. 2019. Pointdan: A multi-scale 3d domain adaption network for point cloud representation. Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00396"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00158"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00629"},{"key":"e_1_3_2_1_31_1","volume-title":"International conference on learning representations.","author":"Valsesia Diego","year":"2018","unstructured":"Diego Valsesia, Giulia Fracastoro, and Enrico Magli. 2018. Learning localized generative models for 3D point clouds via graph convolution. In International conference on learning representations."},{"key":"e_1_3_2_1_32_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_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01054"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00362"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3326362"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01013"},{"key":"e_1_3_2_1_37_1","volume-title":"SACF-net: Skip-attention based correspondence filtering network for point cloud registration","author":"Wu Yue","year":"2023","unstructured":"Yue Wu, Xidao Hu, Yue Zhang, Maoguo Gong, Wenping Ma, and Qiguang Miao. 2023. SACF-net: Skip-attention based correspondence filtering network for point cloud registration. IEEE Transactions on Circuits and Systems for Video Technology (2023)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_34"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00464"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2020.3033695"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_25"},{"key":"e_1_3_2_1_42_1","volume-title":"LION: Latent point diffusion models for 3D shape generation. arXiv preprint arXiv:2210.06978","author":"Zeng Xiaohui","year":"2022","unstructured":"Xiaohui Zeng, Arash Vahdat, Francis Williams, Zan Gojcic, Or Litany, Sanja Fidler, and Karsten Kreis. 2022. LION: Latent point diffusion models for 3D shape generation. arXiv preprint arXiv:2210.06978 (2022)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00962"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00571"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01595"}],"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\/3581783.3612226","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612226","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:05:38Z","timestamp":1755821138000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612226"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":45,"alternative-id":["10.1145\/3581783.3612226","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612226","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"}}]}}