{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:16:49Z","timestamp":1775578609988,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":35,"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":"the Natural Science Foundation of China","award":["62276242"],"award-info":[{"award-number":["62276242"]}]},{"name":"Dreams Foundation of Jianghuai Advance Technology Center","award":["2023-ZM01Z001"],"award-info":[{"award-number":["2023-ZM01Z001"]}]},{"name":"National Aviation Science Foundation","award":["2022Z071078001"],"award-info":[{"award-number":["2022Z071078001"]}]},{"name":"Beijing Municipal Science & Technology Commission, Administrative Commission of Zhongguancun Science Park","award":["Z231100005923035"],"award-info":[{"award-number":["Z231100005923035"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681324","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:27Z","timestamp":1729925967000},"page":"9980-9988","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Part-level Reconstruction for Self-Supervised Category-level 6D Object Pose Estimation with Coarse-to-Fine Correspondence Optimization"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-1976-0889","authenticated-orcid":false,"given":"Zerui","family":"Zhang","sequence":"first","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3197-8103","authenticated-orcid":false,"given":"Jun","family":"Yu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China & Jianghuai Advance Technology Center, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-9595-829X","authenticated-orcid":false,"given":"Liangxian","family":"Cui","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5688-4130","authenticated-orcid":false,"given":"Qiang","family":"Ling","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China & Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4845-8968","authenticated-orcid":false,"given":"Tianyu","family":"Liu","sequence":"additional","affiliation":[{"name":"Jianghuai Advance Technology Center, Hefei, 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":"Estimating or propagating gradients through stochastic neurons for conditional computation. arXiv preprint arXiv:1308.3432","author":"Bengio Yoshua","year":"2013","unstructured":"Yoshua Bengio, Nicholas L\u00e9onard, and Aaron Courville. 2013. Estimating or propagating gradients through stochastic neurons for conditional computation. arXiv preprint arXiv:1308.3432 (2013)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1460-2466.1992.tb00811.x"},{"key":"e_1_3_2_1_3_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_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01199"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00163"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58574-7_9"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20062-5_6"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00666"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"e_1_3_2_1_10_1","volume-title":"Towards self-supervised category-level object pose and size estimation. arXiv preprint arXiv:2203.02884","author":"He Yisheng","year":"2022","unstructured":"Yisheng He, Haoqiang Fan, Haibin Huang, Qifeng Chen, and Jian Sun. 2022. Towards self-supervised category-level object pose and size estimation. arXiv preprint arXiv:2203.02884 (2022)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISMAR.2007.4538852"},{"key":"e_1_3_2_1_12_1","volume-title":"So Kweon, and Kuk-Jin Yoon.","author":"Lee Taeyeop","year":"2022","unstructured":"Taeyeop Lee, Byeong-Uk Lee, Inkyu Shin, Jaesung Choe, Ukcheol Shin, In So Kweon, and Kuk-Jin Yoon. 2022. UDA-COPE: unsupervised domain adaptation for category-level object pose estimation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 14891--14900."},{"key":"e_1_3_2_1_13_1","volume-title":"So Kweon, and Kuk-Jin Yoon.","author":"Lee Taeyeop","year":"2023","unstructured":"Taeyeop Lee, Jonathan Tremblay, Valts Blukis, Bowen Wen, Byeong-Uk Lee, Inkyu Shin, Stan Birchfield, In So Kweon, and Kuk-Jin Yoon. 2023. TTA-COPE: Test-Time Adaptation for Category-Level Object Pose Estimation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 21285--21295."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_38"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_2"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00354"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00040"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00469"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20104"},{"key":"e_1_3_2_1_20_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. 2017. 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_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.413"},{"key":"e_1_3_2_1_22_1","volume-title":"Aaron Van den Oord, and Oriol Vinyals","author":"Razavi Ali","year":"2019","unstructured":"Ali Razavi, Aaron Van den Oord, and Oriol Vinyals. 2019. Generating diverse high-fidelity images with vq-vae-2. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"crossref","unstructured":"Olaf Ronneberger Philipp Fischer and Thomas Brox. 2015. U-Net: Convolutional Networks for Biomedical Image Segmentation. arXiv:1505.04597 [cs.CV]","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_3_2_1_24_1","volume-title":"Optimal pose and shape estimation for category-level 3d object perception. arXiv preprint arXiv:2104.08383","author":"Shi Jingnan","year":"2021","unstructured":"Jingnan Shi, Heng Yang, and Luca Carlone. 2021. Optimal pose and shape estimation for category-level 3d object perception. arXiv preprint arXiv:2104.08383 (2021)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_32"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/34.88573"},{"key":"e_1_3_2_1_27_1","unstructured":"Aaron Van Den Oord Oriol Vinyals et al. 2017. Neural discrete representation learning. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_28_1","first-page":"7207","article-title":"Neural view synthesis and matching for semi-supervised few-shot learning of 3d pose","volume":"34","author":"Wang Angtian","year":"2021","unstructured":"Angtian Wang, Shenxiao Mei, Alan L Yuille, and Adam Kortylewski. 2021. Neural view synthesis and matching for semi-supervised few-shot learning of 3d pose. Advances in Neural Information Processing Systems 34 (2021), 7207--7219.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00346"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01634"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00275"},{"key":"e_1_3_2_1_32_1","volume-title":"Posecnn: A convolutional neural network for 6d object pose estimation in cluttered scenes. arXiv preprint arXiv:1711.00199","author":"Xiang Yu","year":"2017","unstructured":"Yu Xiang, Tanner Schmidt, Venkatraman Narayanan, and Dieter Fox. 2017. Posecnn: A convolutional neural network for 6d object pose estimation in cluttered scenes. arXiv preprint arXiv:1711.00199 (2017)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00674"},{"key":"e_1_3_2_1_34_1","first-page":"27469","article-title":"Category-level 6d object pose estimation in the wild: A semi-supervised learning approach and a new dataset","volume":"35","author":"Ze Yanjie","year":"2022","unstructured":"Yanjie Ze and Xiaolong Wang. 2022. Category-level 6d object pose estimation in the wild: A semi-supervised learning approach and a new dataset. Advances in Neural Information Processing Systems 35 (2022), 27469--27483.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_35_1","volume-title":"Self-supervised geometric correspondence for category-level 6d object pose estimation in the wild. arXiv preprint arXiv:2210.07199","author":"Zhang Kaifeng","year":"2022","unstructured":"Kaifeng Zhang, Yang Fu, Shubhankar Borse, Hong Cai, Fatih Porikli, and Xiaolong Wang. 2022. Self-supervised geometric correspondence for category-level 6d object pose estimation in the wild. arXiv preprint arXiv:2210.07199 (2022)."}],"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\/3664647.3681324","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681324","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\/3664647.3681324"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":35,"alternative-id":["10.1145\/3664647.3681324","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681324","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"}}]}}