{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T16:09:51Z","timestamp":1783526991059,"version":"3.55.0"},"reference-count":64,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"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","award":["U1909207"],"award-info":[{"award-number":["U1909207"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key Research and Development Program of China","award":["2022ZD0160100"],"award-info":[{"award-number":["2022ZD0160100"]}]},{"DOI":"10.13039\/100007219","name":"Shanghai Natural Science Foundation","doi-asserted-by":"publisher","award":["23ZR1402900"],"award-info":[{"award-number":["23ZR1402900"]}],"id":[{"id":"10.13039\/100007219","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Zhejiang Laboratory"},{"name":"Agency for Science, Technology, and Research (A*STAR) Advanced Manufacturing and Engineering (AME) Programmatic Funding","award":["A18A2b0046"],"award-info":[{"award-number":["A18A2b0046"]}]},{"name":"RobotHTPO Seed Fund"},{"name":"Economic Development Board (EDB) Space Technology Development Grant","award":["S22-19016-STDP"],"award-info":[{"award-number":["S22-19016-STDP"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,7]]},"DOI":"10.1109\/tcsvt.2023.3343495","type":"journal-article","created":{"date-parts":[[2023,12,15]],"date-time":"2023-12-15T19:58:55Z","timestamp":1702670335000},"page":"5951-5962","source":"Crossref","is-referenced-by-count":6,"title":["Multi-View Vision Fusion Network: Can 2D Pre-Trained Model Boost 3D Point Cloud Data-Scarce Learning?"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-7126-0253","authenticated-orcid":false,"given":"Haoyang","family":"Peng","sequence":"first","affiliation":[{"name":"Embedded Deep Learning and Visual Analysis Group, School of Information Science and Technology, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9032-3991","authenticated-orcid":false,"given":"Baopu","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8052-782X","authenticated-orcid":false,"given":"Bo","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9347-1367","authenticated-orcid":false,"given":"Xin","family":"Chen","sequence":"additional","affiliation":[{"name":"Tencent PCG, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0779-9818","authenticated-orcid":false,"given":"Tao","family":"Chen","sequence":"additional","affiliation":[{"name":"Embedded Deep Learning and Visual Analysis Group, School of Information Science and Technology, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5177-8320","authenticated-orcid":false,"given":"Hongyuan","family":"Zhu","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research (I2R) and the Centre for Frontier AI Research (CFAR), Agency for Science, Technology, and Research (A*STAR), Fusionopolis, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Target-driven visual navigation in indoor scenes using deep reinforcement learning","author":"Zhu","year":"2016","journal-title":"arXiv:1609.05143"},{"key":"ref2","article-title":"AD-PT: Autonomous driving pre-training with large-scale point cloud dataset","author":"Yuan","year":"2023","journal-title":"arXiv:2306.00612"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/1877808.1877821"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2016.7727386"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1706.02413"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2018.09.001"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01070"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3069034"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3248656"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3250970"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3297620"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3131120"},{"key":"ref13","first-page":"3596","article-title":"Stimulative training of residual networks: A social psychology perspective of loafing","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ye"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811945"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3260903"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3124954"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref20","article-title":"Deep residual learning for image recognition","author":"He","year":"2015","journal-title":"arXiv:1512.03385"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref22","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref23","article-title":"3D ShapeNets: A deep representation for volumetric shapes","author":"Wu","year":"2014","journal-title":"arXiv:1406.5670"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00167"},{"key":"ref25","article-title":"ShapeNet: An information-rich 3D model repository","author":"Chang","year":"2015","journal-title":"arXiv:1512.03012"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2537337"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3284032"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3186740"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3071687"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475371"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_39"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3193449"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00034"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01731-4"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2995754"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01880"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00836"},{"key":"ref38","article-title":"PointCLIP v2: Prompting CLIP and GPT for powerful 3D open-world learning","author":"Zhu","year":"2022","journal-title":"arXiv:2211.11682"},{"key":"ref39","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"arXiv:2103.00020"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3265842"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3245584"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00893"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2900467"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2910208"},{"key":"ref45","article-title":"Masked autoencoders are scalable vision learners","author":"He","year":"2021","journal-title":"arXiv:2111.06377"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01070"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2020.1003324"},{"key":"ref48","article-title":"Revisiting point cloud shape classification with a simple and effective baseline","author":"Goyal","year":"2021","journal-title":"arXiv:2106.05304"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_34"},{"key":"ref50","article-title":"Point-BERT: Pre-training 3D point cloud transformers with masked point modeling","author":"Yu","year":"2021","journal-title":"arXiv:2111.14819"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20086-1_35"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref53","article-title":"Prefix-tuning: Optimizing continuous prompts for generation","author":"Lisa Li","year":"2021","journal-title":"arXiv:2101.00190"},{"key":"ref54","article-title":"P-tuning v2: Prompt tuning can be comparable to fine-tuning universally across scales and tasks","author":"Liu","year":"2021","journal-title":"arXiv:2110.07602"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref56","article-title":"P2P: Tuning pre-trained image models for point cloud analysis with point-to-pixel prompting","author":"Wang","year":"2022","journal-title":"arXiv:2208.02812"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01497"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2015.114"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.609"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00494"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref62","article-title":"Gaussian error linear units (GELUs)","author":"Hendrycks","year":"2016","journal-title":"arXiv:1606.08415"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.01.103"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1214\/13-aos1140"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10582818\/10360874.pdf?arnumber=10360874","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,5]],"date-time":"2024-07-05T04:00:26Z","timestamp":1720152026000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10360874\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7]]},"references-count":64,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3343495","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7]]}}}