{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:21:17Z","timestamp":1750220477760,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":80,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,10,17]],"date-time":"2021-10-17T00:00:00Z","timestamp":1634428800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072268"],"award-info":[{"award-number":["62072268"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key R&D Program of China","award":["2020YFF0304100"],"award-info":[{"award-number":["2020YFF0304100"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,10,17]]},"DOI":"10.1145\/3474085.3475172","type":"proceedings-article","created":{"date-parts":[[2021,10,18]],"date-time":"2021-10-18T17:45:27Z","timestamp":1634579127000},"page":"3862-3871","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Hierarchical View Predictor: Unsupervised 3D Global Feature Learning through Hierarchical Prediction among Unordered Views"],"prefix":"10.1145","author":[{"given":"Zhizhong","family":"Han","sequence":"first","affiliation":[{"name":"Tsinghua University & Wayne State University, Detroit, MI, USA"}]},{"given":"Xiyang","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"given":"Yu-Shen","family":"Liu","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"given":"Matthias","family":"Zwicker","sequence":"additional","affiliation":[{"name":"University of Maryland, College Park, College Park, MD, USA"}]}],"member":"320","published-online":{"date-parts":[[2021,10,17]]},"reference":[{"volume-title":"International Conference on Machine Learning. 40--49","author":"Achlioptas Panos","key":"e_1_3_2_1_1_1"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2652071"},{"key":"e_1_3_2_1_3_1","unstructured":"Andrew Brock Theodore Lim J.M. Ritchie and Nick Weston. 2016. Generative and discriminative voxel modeling with convolutional neural networks. In 3D deep learning workshop (NIPS).  Andrew Brock Theodore Lim J.M. Ritchie and Nick Weston. 2016. Generative and discriminative voxel modeling with convolutional neural networks. In 3D deep learning workshop (NIPS)."},{"volume-title":"IEEE International Conference on Computer Vision.","year":"2021","author":"Chen Chao","key":"e_1_3_2_1_4_1"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1111\/1467-8659.00669"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_38"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2567384"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475458"},{"volume-title":"The IEEE Conference on Computer Vision and Pattern Recognition.","year":"2016","author":"Flynn John","key":"e_1_3_2_1_9_1"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_7"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00719"},{"volume-title":"Self-Supervised Multi-View Learning via Auto-Encoding 3D Transformations. ArXiv","year":"2021","author":"Gao Xiang","key":"e_1_3_2_1_12_1"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_29"},{"volume-title":"International Conference on Machine Learning.","year":"2020","author":"Han Zhizhong","key":"e_1_3_2_1_14_1"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.5555\/3367032.3367142"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2582532"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2017.2778764"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2605920"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2816821"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2904460"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3018865"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58586-0_36"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"crossref","unstructured":"Zhizhong Han Mingyang Shang Yu-Shen Liu and Matthias Zwicker. 2019 d. View Inter-Prediction GAN: Unsupervised Representation Learning for 3D Shapes by Learning Global Shape Memories to Support Local View Predictions. In AAAI. 8376--8384.  Zhizhong Han Mingyang Shang Yu-Shen Liu and Matthias Zwicker. 2019 d. View Inter-Prediction GAN: Unsupervised Representation Learning for 3D Shapes by Learning Global Shape Memories to Support Local View Predictions. In AAAI. 8376--8384.","DOI":"10.1609\/aaai.v33i01.33018376"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2868426"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"crossref","unstructured":"Zhizhong Han Mingyang Shang Xiyang Wang Yu-Shen Liu and Matthias Zwicker. 2019 f. Y2Seq2Seq: Cross-Modal Representation Learning for 3D Shape and Text by Joint Reconstruction and Prediction of View and Word Sequences. In AAAI. 126--133.  Zhizhong Han Mingyang Shang Xiyang Wang Yu-Shen Liu and Matthias Zwicker. 2019 f. Y2Seq2Seq: Cross-Modal Representation Learning for 3D Shape and Text by Joint Reconstruction and Prediction of View and Word Sequences. In AAAI. 126--133.","DOI":"10.1609\/aaai.v33i01.3301126"},{"volume-title":"IEEE International Conference on Computer Vision.","year":"2019","author":"Han Zhizhong","key":"e_1_3_2_1_26_1"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.5555\/3367032.3367141"},{"volume-title":"Unsupervised Multi-Task Feature Learning on Point Clouds. In IEEE International Conference on Computer Vision.","year":"2019","author":"Hassani Kaveh","key":"e_1_3_2_1_28_1"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00208"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","unstructured":"Tao Hu Zhizhong Han and Matthias Zwicker. 2020. 3D Shape Completion with Multi-view Consistent Inference. In AAAI.  Tao Hu Zhizhong Han and Matthias Zwicker. 2020. 3D Shape Completion with Multi-view Consistent Inference. In AAAI.","DOI":"10.1609\/aaai.v34i07.6734"},{"key":"e_1_3_2_1_31_1","unstructured":"H. Huang E. Kalegorakis S. Chaudhuri D. Ceylan V. Kim and E. Yumer. 2017. Learning Local Shape Descriptors with View-based Convolutional Neural Networks. ACM Transactions on Graphics (2017).  H. Huang E. Kalegorakis S. Chaudhuri D. Ceylan V. Kim and E. Yumer. 2017. Learning Local Shape Descriptors with View-based Convolutional Neural Networks. ACM Transactions on Graphics (2017)."},{"volume-title":"Deep View Morphing. The IEEE Conference on Computer Vision and Pattern Recognition","year":"2017","author":"Ji Dinghuang","key":"e_1_3_2_1_32_1"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00133"},{"volume-title":"Pairwise Decomposition of Image Sequences for Active Multi-view Recognition. In IEEE Conference on Computer Vision and Pattern Recognition. 3813--3822","author":"Johns Edward","key":"e_1_3_2_1_34_1"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00526"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.5555\/882370.882392"},{"volume-title":"Point Cloud GAN. CoRR","year":"2018","author":"Li Chun-Liang","key":"e_1_3_2_1_37_1"},{"volume-title":"2018 International Conference on 3D Vision (3DV).","author":"Liu Shikun","key":"e_1_3_2_1_38_1"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cagd.2020.101859"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"crossref","unstructured":"Xinhai Liu Zhizhong Han Yu-Shen Liu and Matthias Zwicker. 2019 a. Point2Sequence: Learning the Shape Representation of 3D Point Clouds with an Attention-based Sequence to Sequence Network. In AAAI. 8778--8785.  Xinhai Liu Zhizhong Han Yu-Shen Liu and Matthias Zwicker. 2019 a. Point2Sequence: Learning the Shape Representation of 3D Point Clouds with an Attention-based Sequence to Sequence Network. In AAAI. 8778--8785.","DOI":"10.1609\/aaai.v33i01.33018778"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3048623"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350960"},{"volume-title":"International Conference on Machine Learning.","year":"2021","author":"Ma Baorui","key":"e_1_3_2_1_43_1"},{"volume-title":"International Conference on Intelligent Robots and Systems. 922--928","author":"Maturana D.","key":"e_1_3_2_1_44_1"},{"volume-title":"Asia-Pacific Signal and Information Processing Association Annual Summit and Conference.","year":"2017","author":"Miyagi Ryo","key":"e_1_3_2_1_45_1"},{"volume-title":"Context Encoders: Feature Learning by Inpainting. In Computer Vision and Pattern Recognition.","year":"2016","author":"Pathak Deepak","key":"e_1_3_2_1_46_1"},{"volume-title":"Kim","year":"2020","author":"Poursaeed Omid","key":"e_1_3_2_1_47_1"},{"volume-title":"IEEE Conference on Computer Vision and Pattern Recognition.","author":"Qi Charles R.","key":"e_1_3_2_1_48_1"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.609"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.609"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295263"},{"volume-title":"NeuralSampler: Euclidean Point Cloud Auto-Encoder and Sampler. CoRR","year":"2019","author":"Remelli Edoardo","key":"e_1_3_2_1_52_1"},{"key":"e_1_3_2_1_53_1","unstructured":"Danilo Jimenez Rezende S. M. Ali Eslami Shakir Mohamed Peter Battaglia Max Jaderberg and Nicolas Heess. 2016. Unsupervised Learning of 3D Structure from Images. In Advances in Neural Information Processing Systems. 4997--5005.  Danilo Jimenez Rezende S. M. Ali Eslami Shakir Mohamed Peter Battaglia Max Jaderberg and Nicolas Heess. 2016. Unsupervised Learning of 3D Structure from Images. In Advances in Neural Information Processing Systems. 4997--5005."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3455448"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.5555\/3056462.3056479"},{"volume-title":"British Machine Vision Conference.","author":"Sedaghat N.","key":"e_1_3_2_1_56_1"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.2312\/3dor.20171045"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-49409-8_20"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2015.2480802"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_14"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.114"},{"volume-title":"Sarma","year":"2018","author":"Sun Yongbin","key":"e_1_3_2_1_62_1"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.64"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073608"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01288"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3019925"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413829"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00201"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00736"},{"key":"e_1_3_2_1_70_1","unstructured":"Lotter William Kreiman Gabriel and Cox David. 2016. Unsupervised Learning of Visual Structure using Predictive Generative Networks. In ICLR.  Lotter William Kreiman Gabriel and Cox David. 2016. Unsupervised Learning of Visual Structure using Predictive Generative Networks. In ICLR."},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.5555\/3157096.3157106"},{"volume-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. 1912--1920","year":"2015","author":"Wu Zhirong","key":"e_1_3_2_1_72_1"},{"volume-title":"IEEE International Conference on Computer Vision.","year":"2021","author":"Xiang Peng","key":"e_1_3_2_1_73_1"},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00900"},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00383"},{"key":"e_1_3_2_1_76_1","doi-asserted-by":"publisher","DOI":"10.5555\/3157096.3157287"},{"key":"e_1_3_2_1_77_1","doi-asserted-by":"crossref","unstructured":"Yaoqing Yang Chen Feng Yiru Shen and Dong Tian. 2018. FoldingNet: Point Cloud Auto-encoder via Deep Grid Deformation. In CVPR.  Yaoqing Yang Chen Feng Yiru Shen and Dong Tian. 2018. FoldingNet: Point Cloud Auto-encoder via Deep Grid Deformation. In CVPR.","DOI":"10.1109\/CVPR.2018.00029"},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"crossref","unstructured":"L. Zhang and Z. Zhu. 2019. Unsupervised Feature Learning for Point Cloud Understanding by Contrasting and Clustering Using Graph Convolutional Neural Networks. In 3DV. 395--404.  L. Zhang and Z. Zhu. 2019. Unsupervised Feature Learning for Point Cloud Understanding by Contrasting and Clustering Using Graph Convolutional Neural Networks. In 3DV. 395--404.","DOI":"10.1109\/3DV.2019.00051"},{"volume-title":"3D Point-Capsule Networks. CoRR","year":"2018","author":"Zhao Yongheng","key":"e_1_3_2_1_79_1"},{"volume":"9908","volume-title":"European Conference on Computer Vision","author":"Zhou Tinghui","key":"e_1_3_2_1_80_1"}],"event":{"name":"MM '21: ACM Multimedia Conference","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Virtual Event China","acronym":"MM '21"},"container-title":["Proceedings of the 29th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3474085.3475172","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3474085.3475172","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:48:47Z","timestamp":1750193327000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3474085.3475172"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,17]]},"references-count":80,"alternative-id":["10.1145\/3474085.3475172","10.1145\/3474085"],"URL":"https:\/\/doi.org\/10.1145\/3474085.3475172","relation":{},"subject":[],"published":{"date-parts":[[2021,10,17]]},"assertion":[{"value":"2021-10-17","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}