{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T16:03:21Z","timestamp":1778256201089,"version":"3.51.4"},"reference-count":70,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,5,13]]},"DOI":"10.1109\/icra57147.2024.10610093","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"9478-9486","source":"Crossref","is-referenced-by-count":8,"title":["Parameter-efficient Prompt Learning for 3D Point Cloud Understanding"],"prefix":"10.1109","author":[{"given":"Hongyu","family":"Sun","sequence":"first","affiliation":[{"name":"Renmin University of China,Department of Computer Science, School of Information,Beijing,China,100872"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongcai","family":"Wang","sequence":"additional","affiliation":[{"name":"Renmin University of China,Department of Computer Science, School of Information,Beijing,China,100872"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wang","family":"Chen","sequence":"additional","affiliation":[{"name":"Renmin University of China,Department of Computer Science, School of Information,Beijing,China,100872"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoran","family":"Deng","sequence":"additional","affiliation":[{"name":"Renmin University of China,Department of Computer Science, School of Information,Beijing,China,100872"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Deying","family":"Li","sequence":"additional","affiliation":[{"name":"Renmin University of China,Department of Computer Science, School of Information,Beijing,China,100872"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Pointnet: Deep learning on point sets for 3d classification and segmentation","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Qi"},{"key":"ref2","article-title":"Pointnet++: Deep hierarchical feature learning on point sets in a metric space","volume-title":"Advances in Neural Information Processing Systems","volume":"30","author":"Qi","year":"2017"},{"key":"ref3","article-title":"Pointcnn: Convolution on x-transformed points","volume-title":"Advances in Neural Information Processing Systems","volume":"31","author":"Li","year":"2018"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3326362"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00651"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00985"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00563"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01009"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01837"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00910"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-021-0229-5"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00095"},{"key":"ref14","article-title":"Rethinking network design and local geometry in point cloud: A simple residual MLP framework","volume-title":"International Conference on Learning Representations","author":"Ma"},{"key":"ref15","article-title":"Pointnext: Revisiting pointnet++ with improved training and scaling strategies","author":"Qian","year":"2022","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref16","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)","author":"Devlin"},{"key":"ref17","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Brown","year":"2020"},{"issue":"140","key":"ref18","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume-title":"Journal of Machine Learning Research","volume":"21","author":"Raffel","year":"2020"},{"key":"ref19","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of the 38th International Conference on Machine Learning","volume":"139","author":"Radford"},{"key":"ref20","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proceedings of the 38th International Conference on Machine Learning","volume":"139","author":"Jia"},{"key":"ref21","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref23","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"ICML","author":"Li"},{"key":"ref24","first-page":"7480","article-title":"Scaling vision transformers to 22 billion parameters","volume-title":"Proceedings of the 40th International Conference on Machine Learning","volume":"202","author":"Dehghani"},{"key":"ref25","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00836"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00249"},{"key":"ref28","article-title":"Autoencoders as cross-modal teachers: Can pretrained 2d image transformers help 3d representation learning?","volume-title":"The Eleventh International Conference on Learning Representations (ICLR)","author":"Dong"},{"key":"ref29","article-title":"Contrast with reconstruct: Contrastive 3d representation learning guided by generative pretraining","volume-title":"International Conference on Machine Learning (ICML)","author":"Qi"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01463"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00120"},{"key":"ref32","article-title":"Shapenet: An information-rich 3d model repository","volume-title":"CoRR","author":"Chang","year":"2015"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01871"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298801"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00167"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/2980179.2980238"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02240"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02085"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00084"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00088"},{"key":"ref42","article-title":"Ulip-2: Towards scalable multimodal pre-training for 3d understanding","author":"Xue","year":"2023"},{"key":"ref43","first-page":"4222","article-title":"AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts","volume-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)","author":"Shin"},{"key":"ref44","first-page":"423","article-title":"How can we know what language models know?","volume-title":"Transactions of the Association for Computational Linguistics","volume":"8","author":"Jiang","year":"2020"},{"key":"ref45","first-page":"4582","article-title":"Prefix-tuning: Optimizing continuous prompts for generation","volume-title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)","author":"Li"},{"key":"ref46","first-page":"5017","article-title":"Factual probing is [MASK]: Learning vs. learning to recall","volume-title":"Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"Zhong"},{"key":"ref47","first-page":"3045","article-title":"The power of scale for parameter-efficient prompt tuning","volume-title":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","author":"Lester"},{"key":"ref48","first-page":"3816","article-title":"Making pre-trained language models better few-shot learners","volume-title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)","author":"Gao"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2023.08.012"},{"key":"ref50","first-page":"1","article-title":"BitFit: Simple parameter-efficient fine-tuning for transformer-based masked language-models","volume-title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","author":"Ben Zaken"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01047"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01460"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01394"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_30"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_6"},{"key":"ref60","article-title":"Revisiting point cloud shape classification with a simple and effective baseline","volume-title":"International Conference on Machine Learning","author":"Goyal"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00007"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00964"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00967"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20086-1_38"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20086-1_35"},{"key":"ref66","article-title":"Let images give you more: Point cloud cross-modal training for shape analysis","volume-title":"NeurIPS","author":"Yan"},{"key":"ref67","first-page":"27 061","article-title":"Point-m2ae: Multi-scale masked autoencoders for hierarchical point cloud pre-training","volume-title":"Advances in Neural Information Processing Systems","volume":"35","author":"Zhang","year":"2022"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160658"},{"key":"ref70","first-page":"1715","article-title":"Neural machine translation of rare words with subword units","volume-title":"Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Sennrich"}],"event":{"name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","location":"Yokohama, Japan","start":{"date-parts":[[2024,5,13]]},"end":{"date-parts":[[2024,5,17]]}},"container-title":["2024 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10609961\/10609862\/10610093.pdf?arnumber=10610093","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,10]],"date-time":"2024-08-10T05:21:09Z","timestamp":1723267269000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10610093\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":70,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10610093","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}