{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,7]],"date-time":"2025-04-07T22:10:03Z","timestamp":1744063803824,"version":"3.40.3"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":["61673142"],"award-info":[{"award-number":["61673142"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Foundation of Hei Longjiang Province of China","award":["LH2022F029"],"award-info":[{"award-number":["LH2022F029"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2024.3521816","type":"journal-article","created":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T19:23:06Z","timestamp":1734981786000},"page":"1926-1936","source":"Crossref","is-referenced-by-count":0,"title":["Semantic-Enhanced ULIP for Zero-Shot 3D Shape Recognition"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9154-776X","authenticated-orcid":false,"given":"Bo","family":"Ding","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Harbin University of Science and Technology, Harbin, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5130-013X","authenticated-orcid":false,"given":"Libao","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin University of Science and Technology, Harbin, China"}]},{"given":"Hongbo","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin University of Science and Technology, Harbin, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5156-651X","authenticated-orcid":false,"given":"Yongjun","family":"He","sequence":"additional","affiliation":[{"name":"Faculty of Computing, Harbin Institute of Technology, Harbin, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8791-0370","authenticated-orcid":false,"given":"Jian","family":"Qin","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Anhui University of Technology, Maanshan, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3146714"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00920"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00401"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3156820"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01759"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3293318"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2857768"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref9","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00120"},{"key":"ref11","first-page":"7241","article-title":"mPLUG: Effective and efficient vision-language learning by cross-modal skip-connections","volume-title":"Proc. 2022 Conf. Emp. Methods Natural Lang. Process.","author":"Li","year":"2022"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298801"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00167"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.114"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.25"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1111\/1467-8659.00669"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00035"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108774"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2022.104405"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3071687"},{"key":"ref22","first-page":"652","article-title":"PointNet: Deep learning on point sets for 3D classification and segmentation","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Qi","year":"2017"},{"key":"ref23","first-page":"5105","article-title":"PointNet : Deep hierarchical feature learning on point sets in a metric space","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Qi","year":"2017"},{"key":"ref24","first-page":"23192","article-title":"PointNeXt: Revisiting pointnet with improved training and scaling strategies","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Qian","year":"2022"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00517"},{"key":"ref26","first-page":"828","article-title":"PointCNN: Convolution on X-transformed points","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li","year":"2018"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00985"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3326362"},{"key":"ref29","article-title":"Rethinking network design and local geometry in point cloud: A simple residual MLP framework","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ma","year":"2022"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3198318"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-021-0229-5"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.23919\/MVA.2019.8758063"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093545"},{"article-title":"Mitigating the hubness problem for zero-shot learning of 3D objects","year":"2019","author":"Cheraghian","key":"ref36"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01650-4"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00836"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02025"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00249"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25152"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00217"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02558"},{"key":"ref44","first-page":"44860","article-title":"Openshape: Scaling up 3D shape representation towards open-world understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Liu","year":"2023"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00107"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/DICTA56598.2022.10034623"},{"key":"ref47","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Brown","year":"2020"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3386252"},{"key":"ref49","first-page":"3816","article-title":"Making pre-trained language models better few-shot learners","volume-title":"Proc. 59th Annu. Meeting Assoc. Comput. Linguistics 11th Int. Joint Conf. Natural Lang. Process.","author":"Gao","year":"2021"},{"key":"ref50","first-page":"819","article-title":"An information-theoretic approach to prompt engineering without ground truth labels","volume-title":"Proc. 60th Annu. Meeting Assoc. Comput. Linguistics","author":"Sorensen","year":"2022"},{"key":"ref51","first-page":"2","article-title":"Contrastive learning of medical visual representations from paired images and text","volume-title":"Proc. Mach. Learn. Healthcare Conf.","author":"Zhang","year":"2022"},{"article-title":"Conditioned natural language generation using only unconditioned language model: An exploration","year":"2020","author":"Sun","key":"ref52"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_30"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","year":"2020","author":"Dosovitskiy","key":"ref55"},{"key":"ref56","first-page":"3809","article-title":"Revisiting point cloud shape classification with a simple and effective Baseline","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Goyal","year":"2021"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00571"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01871"},{"article-title":"Shapenet: An information-rich 3D model repository","year":"2015","author":"Chang","key":"ref59"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_4"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00651"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01175"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00979"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01519"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00007"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/10812844.pdf?arnumber=10812844","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,7]],"date-time":"2025-04-07T21:56:09Z","timestamp":1744062969000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10812844\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":65,"URL":"https:\/\/doi.org\/10.1109\/tmm.2024.3521816","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"type":"print","value":"1520-9210"},{"type":"electronic","value":"1941-0077"}],"subject":[],"published":{"date-parts":[[2025]]}}}