{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:24:03Z","timestamp":1776885843185,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":49,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,5,30]],"date-time":"2024-05-30T00:00:00Z","timestamp":1717027200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,5,30]]},"DOI":"10.1145\/3652583.3658041","type":"proceedings-article","created":{"date-parts":[[2024,6,7]],"date-time":"2024-06-07T06:30:40Z","timestamp":1717741840000},"page":"1061-1069","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Parametric CAD Primitive Retrieval via Multi-Modal Fusion and Deep Hashing"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-3616-5058","authenticated-orcid":false,"given":"Minyang","family":"Xu","sequence":"first","affiliation":[{"name":"School of Computer Science, Fudan University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2386-0017","authenticated-orcid":false,"given":"Yunzhong","family":"Lou","sequence":"additional","affiliation":[{"name":"School of Computer Science, Fudan University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-0650-6448","authenticated-orcid":false,"given":"Weijian","family":"Ma","sequence":"additional","affiliation":[{"name":"School of Computer Science, Fudan University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7833-0170","authenticated-orcid":false,"given":"Xueyang","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science, Fudan University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5538-7367","authenticated-orcid":false,"given":"Xiangdong","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Computer Science, Fudan University, Shanghai, China"}]}],"member":"320","published-online":{"date-parts":[[2024,6,7]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"International conference on machine learning. PMLR, 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. PMLR, 40--49."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00140"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.598"},{"key":"e_1_3_2_1_4_1","first-page":"16351","article-title":"Deepsvg: A hierarchical generative network for vector graphics animation","volume":"33","author":"Carlier Alexandre","year":"2020","unstructured":"Alexandre Carlier, Martin Danelljan, Alexandre Alahi, and Radu Timofte. 2020. Deepsvg: A hierarchical generative network for vector graphics animation. Advances in Neural Information Processing Systems 33 (2020), 16351--16361.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2020.104003"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859900"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cad.2023.103655"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3095140.3095148"},{"key":"e_1_3_2_1_9_1","first-page":"1","article-title":"Self-supervised multi-view learning via auto-encoding 3D transformations","volume":"20","author":"Gao Xiang","year":"2023","unstructured":"Xiang Gao, Wei Hu, and Guo-Jun Qi. 2023. Self-supervised multi-view learning via auto-encoding 3D transformations. ACM Transactions on Multimedia Computing, Communications and Applications 20, 1 (2023), 1--23.","journal-title":"ACM Transactions on Multimedia Computing, Communications and Applications"},{"key":"e_1_3_2_1_10_1","volume-title":"Exploring deep learning for view-based 3D model retrieval. ACM transactions on multimedia computing, communications, and applications (TOMM) 16, 1","author":"Gao Zan","year":"2020","unstructured":"Zan Gao, Yinming Li, and Shaohua Wan. 2020. Exploring deep learning for view-based 3D model retrieval. ACM transactions on multimedia computing, communications, and applications (TOMM) 16, 1 (2020), 1--21."},{"key":"e_1_3_2_1_11_1","volume-title":"ASR Error Detection, and ASR Error Correction. arXiv preprint arXiv:2401.13260","author":"He Jiajun","year":"2024","unstructured":"Jiajun He, Xiaohan Shi, Xingfeng Li, and Tomoki Toda. 2024. MF-AED-AEC: Speech Emotion Recognition by Leveraging Multimodal Fusion, ASR Error Detection, and ASR Error Correction. arXiv preprint arXiv:2401.13260 (2024)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2866771"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3073867"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_21"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2883522"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746805"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/1126004.1126005"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16296"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.227"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.5555\/2354409.2355047"},{"key":"e_1_3_2_1_21_1","volume-title":"CrossVideo: Self-supervised Cross-modal Contrastive Learning for Point Cloud Video Understanding. arXiv preprint arXiv:2401.09057","author":"Liu Yunze","year":"2024","unstructured":"Yunze Liu, Changxi Chen, Zifan Wang, and Li Yi. 2024. CrossVideo: Self-supervised Cross-modal Contrastive Learning for Point Cloud Video Understanding. arXiv preprint arXiv:2401.09057 (2024)."},{"key":"e_1_3_2_1_22_1","volume-title":"Generative Multi-Modal Knowledge Retrieval with Large Language Models. arXiv preprint arXiv:2401.08206","author":"Long Xinwei","year":"2024","unstructured":"Xinwei Long, Jiali Zeng, Fandong Meng, Zhiyuan Ma, Kaiyan Zhang, Bowen Zhou, and Jie Zhou. 2024. Generative Multi-Modal Knowledge Retrieval with Large Language Models. arXiv preprint arXiv:2401.08206 (2024)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV57658.2022.00050"},{"key":"e_1_3_2_1_24_1","volume-title":"A survey on deep hashing methods. ACM Transactions on Knowledge Discovery from Data 17, 1","author":"Luo Xiao","year":"2023","unstructured":"Xiao Luo, Haixin Wang, Daqing Wu, Chong Chen, Minghua Deng, Jianqiang Huang, and Xian-Sheng Hua. 2023. A survey on deep hashing methods. ACM Transactions on Knowledge Discovery from Data 17, 1 (2023), 1--50."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3614982"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cag.2021.07.001"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3132847.3132914"},{"key":"e_1_3_2_1_28_1","first-page":"5077","article-title":"Sketchgen: Generating constrained cad sketches","volume":"34","author":"Para Wamiq","year":"2021","unstructured":"Wamiq Para, Shariq Bhat, Paul Guerrero, Tom Kelly, Niloy Mitra, Leonidas J Guibas, and Peter Wonka. 2021. Sketchgen: Generating constrained cad sketches. Advances in Neural Information Processing Systems 34 (2021), 5077--5088.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","unstructured":"Thomas Paviot. 2022. pythonocc (7.7.2). https:\/\/doi.org\/10.5281\/zenodo.3605364","DOI":"10.5281\/zenodo.3605364"},{"key":"e_1_3_2_1_30_1","volume-title":"Pointnet: Deep hierarchical feature learning on point sets in a metric space. Advances in neural information processing systems 30","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 30 (2017)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080842"},{"key":"e_1_3_2_1_32_1","volume-title":"Vitruvion: A generative model of parametric cad sketches. arXiv preprint arXiv:2109.14124","author":"Seff Ari","year":"2021","unstructured":"Ari Seff, Wenda Zhou, Nick Richardson, and Ryan P Adams. 2021. Vitruvion: A generative model of parametric cad sketches. arXiv preprint arXiv:2109.14124 (2021)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298598"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00289"},{"key":"e_1_3_2_1_35_1","volume-title":"SemTra: A Semantic Skill Translator for Cross-Domain Zero-Shot Policy Adaptation. arXiv preprint arXiv:2402.07418","author":"Shin Sangwoo","year":"2024","unstructured":"Sangwoo Shin, Minjong Yoo, Jeongwoo Lee, and Honguk Woo. 2024. SemTra: A Semantic Skill Translator for Cross-Domain Zero-Shot Policy Adaptation. arXiv preprint arXiv:2402.07418 (2024)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3015554"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3243608"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01154"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00239"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00670"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v28i1.8952"},{"key":"e_1_3_2_1_42_1","volume-title":"GauU-Scene: A Scene Reconstruction Benchmark on Large Scale 3D Reconstruction Dataset Using Gaussian Splatting. arXiv preprint arXiv:2401.14032","author":"Xiong Butian","year":"2024","unstructured":"Butian Xiong, Zhuo Li, and Zhen Li. 2024. GauU-Scene: A Scene Reconstruction Benchmark on Large Scale 3D Reconstruction Dataset Using Gaussian Splatting. arXiv preprint arXiv:2401.14032 (2024)."},{"key":"e_1_3_2_1_43_1","volume-title":"Joseph G Lambourne, Karl DD Willis, and Yasutaka Furukawa.","author":"Xu Xiang","year":"2023","unstructured":"Xiang Xu, Pradeep Kumar Jayaraman, Joseph G Lambourne, Karl DD Willis, and Yasutaka Furukawa. 2023. Hierarchical neural coding for controllable cad model generation. arXiv preprint arXiv:2307.00149 (2023)."},{"key":"e_1_3_2_1_44_1","volume-title":"Joseph G Lambourne, Chin-Yi Cheng, Pradeep Kumar Jayaraman, and Yasutaka Furukawa.","author":"Xu Xiang","year":"2022","unstructured":"Xiang Xu, Karl DD Willis, Joseph G Lambourne, Chin-Yi Cheng, Pradeep Kumar Jayaraman, and Yasutaka Furukawa. 2022. SkexGen: Autoregressive generation of CAD construction sequences with disentangled codebooks. arXiv preprint arXiv:2207.04632 (2022)."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10719"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2897249"},{"key":"e_1_3_2_1_47_1","unstructured":"Hai-Tao Yu and Mofei Song. 2024. MM-Point: Multi-View Information-Enhanced Multi-Modal Self-Supervised 3D Point Cloud Understanding. arXiv:2402.10002 [cs.CV]"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i5.16592"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412086"}],"event":{"name":"ICMR '24: International Conference on Multimedia Retrieval","location":"Phuket Thailand","acronym":"ICMR '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia","SIGSOFT ACM Special Interest Group on Software Engineering"]},"container-title":["Proceedings of the 2024 International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3652583.3658041","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3652583.3658041","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T08:54:42Z","timestamp":1755766482000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3652583.3658041"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,30]]},"references-count":49,"alternative-id":["10.1145\/3652583.3658041","10.1145\/3652583"],"URL":"https:\/\/doi.org\/10.1145\/3652583.3658041","relation":{},"subject":[],"published":{"date-parts":[[2024,5,30]]},"assertion":[{"value":"2024-06-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}