{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:33:22Z","timestamp":1775579602149,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":48,"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":"Institute of Information & Communications Technology Planning & Evaluation","award":["RS-2023-00229330"],"award-info":[{"award-number":["RS-2023-00229330"]}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["No. 2022R1F1A1062950"],"award-info":[{"award-number":["No. 2022R1F1A1062950"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100003725","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\/3664647.3680667","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:27Z","timestamp":1729925967000},"page":"1467-1475","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["MSTA3D: Multi-scale Twin-attention for 3D Instance Segmentation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-0061-4642","authenticated-orcid":false,"given":"Duc Dang Trung","family":"Tran","sequence":"first","affiliation":[{"name":"Department of Electrical and Information Engineering, Seoul National University of Science and Technology, Seoul, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2537-7720","authenticated-orcid":false,"given":"Byeongkeun","family":"Kang","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Seoul National University of Science and Technology, Seoul, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3439-5042","authenticated-orcid":false,"given":"Yeejin","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Electrical and Information Engineering, Seoul National University of Science and Technology, Seoul, Republic of Korea"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Joint 2d-3d-semantic data for indoor scene understanding. arXiv preprint arXiv:1702.01105","author":"Armeni I","year":"2017","unstructured":"I Armeni, S Sax, AR Zamir, S Savarese, A Sax, AR Zamir, and S Savarese. 2017. Joint 2d-3d-semantic data for indoor scene understanding. arXiv preprint arXiv:1702.01105 (2017)."},{"key":"e_1_3_2_2_2_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 preprint arXiv:1607.06450 (2016)."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01518"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20056-4_4"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00905"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00326"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00961"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00301"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00042"},{"key":"e_1_3_2_2_12_1","volume-title":"European Conference on Computer Vision. Springer, 286--302","author":"He Tong","unstructured":"Tong He, Wei Yin, Chunhua Shen, and Anton van den Hengel. 2022. Pointinst3d: Segmenting 3d instances by points. In European Conference on Computer Vision. Springer, 286--302."},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00455"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00492"},{"key":"e_1_3_2_2_15_1","volume-title":"Dual Path Transformer with Partition Attention. arXiv preprint arXiv:2305.14768","author":"Jiang Zhengkai","year":"2023","unstructured":"Zhengkai Jiang, Liang Liu, Jiangning Zhang, Yabiao Wang, Mingang Chen, and Chengjie Wang. 2023. Dual Path Transformer with Partition Attention. arXiv preprint arXiv:2305.14768 (2023)."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00353"},{"key":"e_1_3_2_2_17_1","volume-title":"The Hungarian method for the assignment problem. Naval research logistics quarterly","author":"Kuhn Harold W","year":"1955","unstructured":"Harold W Kuhn. 1955. The Hungarian method for the assignment problem. Naval research logistics quarterly, Vol. 2, 1--2 (1955), 83--97."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00935"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00342"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00479"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"crossref","unstructured":"Ville V Lehtola Harri Kaartinen Andreas N\u00fcchter Risto Kaijaluoto Antero Kukko Paula Litkey Eija Honkavaara Tomi Rosnell Matti T Vaaja Juho-Pekka Virtanen et al. 2017. Comparison of the selected state-of-the-art 3D indoor scanning and point cloud generation methods. Remote sensing Vol. 9 8 (2017) 796.","DOI":"10.3390\/rs9080796"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01325"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00278"},{"key":"e_1_3_2_2_24_1","volume-title":"Learning gaussian instance segmentation in point clouds. arXiv preprint arXiv:2007.09860","author":"Liu Shih-Hung","year":"2020","unstructured":"Shih-Hung Liu, Shang-Yi Yu, Shao-Chi Wu, Hwann-Tzong Chen, and Tyng-Luh Liu. 2020. Learning gaussian instance segmentation in point clouds. arXiv preprint arXiv:2007.09860 (2020)."},{"key":"e_1_3_2_2_25_1","volume-title":"Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101","author":"Loshchilov Ilya","year":"2017","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01697"},{"key":"e_1_3_2_2_27_1","volume-title":"V-net: Fully convolutional neural networks for volumetric medical image segmentation. In 2016 fourth international conference on 3D vision (3DV). Ieee, 565--571.","author":"Milletari Fausto","year":"2016","unstructured":"Fausto Milletari, Nassir Navab, and Seyed-Ahmad Ahmadi. 2016. V-net: Fully convolutional neural networks for volumetric medical image segmentation. In 2016 fourth international conference on 3D vision (3DV). Ieee, 565--571."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.232"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01302"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcim.2019.101887"},{"key":"e_1_3_2_2_31_1","unstructured":"Adam Paszke Sam Gross Soumith Chintala Gregory Chanan Edward Yang Zachary DeVito Zeming Lin Alban Desmaison Luca Antiga and Adam Lerer. 2017. Automatic differentiation in pytorch. (2017)."},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00903"},{"key":"e_1_3_2_2_33_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. 2017. 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_2_34_1","volume-title":"U-net: Convolutional networks for biomedical image segmentation. In Medical image computing and computer-assisted intervention--MICCAI 2015: 18th international conference","author":"Ronneberger Olaf","year":"2015","unstructured":"Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-net: Convolutional networks for biomedical image segmentation. In Medical image computing and computer-assisted intervention--MICCAI 2015: 18th international conference, Munich, Germany, October 5--9, 2015, proceedings, part III 18. Springer, 234--241."},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_8"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160590"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00562"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25335"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00062"},{"key":"e_1_3_2_2_40_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, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00273"},{"key":"e_1_3_2_2_42_1","volume-title":"Scalable SoftGroup for 3D Instance Segmentation on Point Clouds","author":"Vu Thang","year":"2023","unstructured":"Thang Vu, Kookhoi Kim, Thanh Nguyen, Tung M Luu, Junyeong Kim, and Chang D Yoo. 2023. Scalable SoftGroup for 3D Instance Segmentation on Point Clouds. IEEE Transactions on Pattern Analysis and Machine Intelligence (2023)."},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_14"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2021.3060341"},{"key":"e_1_3_2_2_45_1","volume-title":"Learning object bounding boxes for 3D instance segmentation on point clouds. Advances in neural information processing systems","author":"Yang Bo","year":"2019","unstructured":"Bo Yang, Jianan Wang, Ronald Clark, Qingyong Hu, Sen Wang, Andrew Markham, and Niki Trigoni. 2019. Learning object bounding boxes for 3D instance segmentation on point clouds. Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_2_46_1","volume-title":"A survey of autonomous driving: Common practices and emerging technologies","author":"Yurtsever Ekim","year":"2020","unstructured":"Ekim Yurtsever, Jacob Lambert, Alexander Carballo, and Kazuya Takeda. 2020. A survey of autonomous driving: Common practices and emerging technologies. IEEE access, Vol. 8 (2020), 58443--58469."},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00058"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859996"}],"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\/3664647.3680667","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680667","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:57Z","timestamp":1750295877000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680667"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":48,"alternative-id":["10.1145\/3664647.3680667","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680667","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"}}]}}