{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T11:46:10Z","timestamp":1762429570446,"version":"3.28.0"},"reference-count":66,"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\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","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\/icra57147.2024.10610767","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"9455-9462","source":"Crossref","is-referenced-by-count":3,"title":["Fine-Tuning Point Cloud Transformers with Dynamic Aggregation"],"prefix":"10.1109","author":[{"given":"Jiajun","family":"Fei","sequence":"first","affiliation":[{"name":"Tsinghua University,Institute for Artificial Intelligence, Tsinghua University (THUAI), State Key Laboratory of Intelligent Technology and Systems, Beijing National Research Center for Information Science and Technology (BNRist),Department of Computer Science and Technology,Beijing,China,100084"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhidong","family":"Deng","sequence":"additional","affiliation":[{"name":"Tsinghua University,Institute for Artificial Intelligence, Tsinghua University (THUAI), State Key Laboratory of Intelligent Technology and Systems, Beijing National Research Center for Information Science and Technology (BNRist),Department of Computer Science and Technology,Beijing,China,100084"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Pointnet: Deep learning on point sets for 3d classification and segmentation","volume-title":"Proc. of the IEEE\/CVF Conf. on Computer Vision and Pattern Recognition (CVPR)","author":"Qi","key":"ref1"},{"key":"ref2","article-title":"Pointnet++: Deep hierarchical feature learning on point sets in a metric space","volume":"30","author":"Qi","year":"2017","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3326362"},{"article-title":"Rethinking network design and local geometry in point cloud: A simple residual MLP framework","volume-title":"Int. Conf. on Learning Representations (ICLR)","author":"Ma","key":"ref4"},{"key":"ref5","first-page":"23192","article-title":"Pointnext: Revisiting pointnet++ with improved training and scaling strategies","volume":"35","author":"Qian","year":"2022","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58526-6_37"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_34"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01533"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01871"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20086-1_35"},{"key":"ref11","first-page":"27061","article-title":"Point-m2ae: Multi-scale masked autoencoders for hierarchical point cloud pre-training","volume":"35","author":"Zhang","year":"2022","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref13","first-page":"40","article-title":"Learning representations and generative models for 3D point clouds","volume-title":"Proc. of the Int. Conf. on Machine Learning (ICML)","volume":"80","author":"Achlioptas"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00029"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00464"},{"key":"ref16","first-page":"11285","article-title":"Tinytl: Reduce memory, not parameters for efficient on-device learning","volume":"33","author":"Cai","year":"2020","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-short.1"},{"key":"ref18","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. of the Int. Conf. on Machine Learning (ICML)","volume":"97","author":"Houlsby"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.7"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.39"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.47"},{"key":"ref22","article-title":"Learning multiple visual domains with residual adapters","volume":"30","author":"Rebuffi","year":"2017","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref23","first-page":"16664","article-title":"Adaptformer: Adapting vision transformers for scalable visual recognition","volume":"35","author":"Chen","year":"2022","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref24","first-page":"109","article-title":"Scaling & shifting your features: A new baseline for efficient model tuning","volume":"35","author":"Lian","year":"2022","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref25","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"article-title":"Exploring visual prompts for adapting large-scale models","year":"2022","author":"Bahng","key":"ref29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01047"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01302"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Int. Conf. on Learning Representations (ICLR)","author":"Dosovitskiy","key":"ref32"},{"article-title":"Improving language understanding by generative pre-training","year":"2018","author":"Radford","key":"ref33"},{"key":"ref34","first-page":"4171","article-title":"BERT: Pretraining of deep bidirectional transformers for language understanding","volume-title":"Proc. of the Conf. of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"Devlin"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s11023-020-09548-1"},{"key":"ref36","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"Proc. of the Int. Conf. on Machine Learning (ICML)","volume":"119","author":"Chen"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"article-title":"Point cloud GAN","volume-title":"Int. Conf. on Learning Representations Workshop","author":"Li","key":"ref40"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00110"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298801"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"article-title":"Contrast with reconstruct: contrastive 3d representation learning guided by generative pretraining","volume-title":"Proc. of the Int. Conf. on Machine Learning (ICML)","author":"Qi","key":"ref44"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3142440"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3224370"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3226029"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160539"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CRV60082.2023.00042"},{"key":"ref50","article-title":"How transferable are features in deep neural networks?","volume":"27","author":"Yosinski","year":"2014","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_5"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_40"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00494"},{"article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Int. Conf. on Learning Representations (ICLR)","author":"Hu","key":"ref54"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_29"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00836"},{"key":"ref57","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. of the Int. Conf. on Machine Learning (ICML)","volume":"139","author":"Radford"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-short.8"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"ref60","first-page":"14388","article-title":"P2p: Tuning pre-trained image models for point cloud analysis with point-to-pixel prompting","volume":"35","author":"Wang","year":"2022","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3435939"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00167"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19939"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298801"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/2980179.2980238"},{"issue":"11","key":"ref66","article-title":"Visualizing data using t-sne","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. of machine learning research"}],"event":{"name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2024,5,13]]},"location":"Yokohama, Japan","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\/10610767.pdf?arnumber=10610767","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,10]],"date-time":"2024-08-10T05:55:10Z","timestamp":1723269310000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10610767\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10610767","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}