{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T12:17:56Z","timestamp":1783167476998,"version":"3.54.6"},"reference-count":54,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62371235"],"award-info":[{"award-number":["62371235"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U25A20444"],"award-info":[{"award-number":["U25A20444"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013058","name":"Jiangsu Provincial Key Research and Development Program","doi-asserted-by":"publisher","award":["BE2023008-2"],"award-info":[{"award-number":["BE2023008-2"]}],"id":[{"id":"10.13039\/501100013058","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.neucom.2026.134265","type":"journal-article","created":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T15:28:44Z","timestamp":1781105324000},"page":"134265","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["CoTeach-CLIP: Cross-modal collaborative teachers for zero-shot point cloud recognition"],"prefix":"10.1016","volume":"697","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1004-8190","authenticated-orcid":false,"given":"Jiabao","family":"Zuo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4039-7618","authenticated-orcid":false,"given":"Haofeng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2879-7822","authenticated-orcid":false,"given":"Quanchen","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-9156-4301","authenticated-orcid":false,"given":"Yafei","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5576-3281","authenticated-orcid":false,"given":"Mingwu","family":"Ren","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"8","key":"10.1016\/j.neucom.2026.134265_bib0005","doi-asserted-by":"crossref","first-page":"1909","DOI":"10.1007\/s11263-023-01790-1","article-title":"3D object detection for autonomous driving: a comprehensive survey","volume":"131","author":"Mao","year":"2023","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.neucom.2026.134265_bib0010","author":"Chen"},{"issue":"4","key":"10.1016\/j.neucom.2026.134265_bib0015","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1007\/s00138-024-01543-1","article-title":"A comprehensive overview of deep learning techniques for 3D point cloud classification and semantic segmentation","volume":"35","author":"Sarker","year":"2024","journal-title":"Mach. Vis. Appl."},{"issue":"4","key":"10.1016\/j.neucom.2026.134265_bib0020","first-page":"4051","article-title":"A review of generalized zero-shot learning methods","volume":"45","author":"Pourpanah","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.neucom.2026.134265_bib0025","series-title":"International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.neucom.2026.134265_bib0030","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"1179","article-title":"Ulip: learning a unified representation of language, images, and point clouds for 3D understanding","author":"Xue","year":"2023"},{"key":"10.1016\/j.neucom.2026.134265_bib0035","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"27091","article-title":"Ulip-2: towards scalable multimodal pre-training for 3D understanding","author":"Xue","year":"2024"},{"key":"10.1016\/j.neucom.2026.134265_bib0040","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"8552","article-title":"Pointclip: point cloud understanding by clip","author":"Zhang","year":"2022"},{"key":"10.1016\/j.neucom.2026.134265_bib0045","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"7020","article-title":"Clip2scene: towards label-efficient 3D scene understanding by clip","author":"Chen","year":"2023"},{"key":"10.1016\/j.neucom.2026.134265_bib0050","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"22157","article-title":"Clip2point: transfer clip to point cloud classification with image-depth pre-training","author":"Huang","year":"2023"},{"key":"10.1016\/j.neucom.2026.134265_bib0055","author":"Zhu"},{"key":"10.1016\/j.neucom.2026.134265_bib0060","series-title":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","first-page":"4256","article-title":"DualCLIP: bridging 3D geometry and multimodal semantics for robotic perception","author":"Liu","year":"2025"},{"key":"10.1016\/j.neucom.2026.134265_bib0065","author":"Han"},{"key":"10.1016\/j.neucom.2026.134265_bib0070","author":"Shazeer"},{"issue":"2","key":"10.1016\/j.neucom.2026.134265_bib0075","first-page":"1","article-title":"A survey of zero-shot learning: settings, methods, and applications","volume":"10","author":"Wang","year":"2019","journal-title":"ACM Trans. Intell. Syst. Technol."},{"issue":"7","key":"10.1016\/j.neucom.2026.134265_bib0080","doi-asserted-by":"crossref","first-page":"1425","DOI":"10.1109\/TPAMI.2015.2487986","article-title":"Label-embedding for image classification","volume":"38","author":"Akata","year":"2015","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.neucom.2026.134265_bib0085","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"4582","article-title":"Zero-shot learning-the good, the bad and the ugly","author":"Xian","year":"2017"},{"issue":"10","key":"10.1016\/j.neucom.2026.134265_bib0090","doi-asserted-by":"crossref","first-page":"2364","DOI":"10.1007\/s11263-022-01650-4","article-title":"Zero-shot learning on 3D point cloud objects and beyond","volume":"130","author":"Cheraghian","year":"2022","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.neucom.2026.134265_bib0095","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2024.102601","article-title":"Advancing 3D point cloud understanding through deep transfer learning: a comprehensive survey","volume":"113","author":"Sohail","year":"2025","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.neucom.2026.134265_bib0100","series-title":"International Conference on Machine Learning","first-page":"12888","article-title":"BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation","author":"Li","year":"2022"},{"key":"10.1016\/j.neucom.2026.134265_bib0105","series-title":"International Conference on Machine Learning","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","author":"Jia","year":"2021"},{"key":"10.1016\/j.neucom.2026.134265_bib0110","doi-asserted-by":"crossref","first-page":"44860","DOI":"10.52202\/075280-1944","article-title":"Openshape: scaling up 3D shape representation towards open-world understanding","volume":"36","author":"Liu","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134265_bib0115","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"2028","article-title":"Clip goes 3D: leveraging prompt tuning for language grounded 3D recognition","author":"Hegde","year":"2023"},{"key":"10.1016\/j.neucom.2026.134265_bib0120","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"2639","article-title":"Pointclip v2: prompting clip and GPT for powerful 3D open-world learning","author":"Zhu","year":"2023"},{"key":"10.1016\/j.neucom.2026.134265_bib0125","series-title":"International Conference on Multimedia Modeling","first-page":"338","article-title":"MDT-net: a mask decoder tuning strategy for CLIP-based zero-shot 3D classification","author":"Yan","year":"2024"},{"key":"10.1016\/j.neucom.2026.134265_bib0130","series-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","first-page":"3596","article-title":"Diffclip: leveraging stable diffusion for language grounded 3D classification","author":"Shen","year":"2024"},{"key":"10.1016\/j.neucom.2026.134265_bib0135","doi-asserted-by":"crossref","first-page":"75307","DOI":"10.52202\/075280-3291","article-title":"Scalable 3D captioning with pretrained models","volume":"36","author":"Luo","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134265_bib0140","series-title":"European Conference on Computer Vision","first-page":"350","article-title":"Detecting twenty-thousand classes using image-level supervision","author":"Zhou","year":"2022"},{"key":"10.1016\/j.neucom.2026.134265_bib0145","author":"Hinton"},{"issue":"6","key":"10.1016\/j.neucom.2026.134265_bib0150","doi-asserted-by":"crossref","first-page":"1789","DOI":"10.1007\/s11263-021-01453-z","article-title":"Knowledge distillation: a survey","volume":"129","author":"Gou","year":"2021","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.neucom.2026.134265_bib0155","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"2827","article-title":"Cross modal distillation for supervision transfer","author":"Gupta","year":"2016"},{"key":"10.1016\/j.neucom.2026.134265_bib0160","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","first-page":"103","article-title":"Modality distillation with multiple stream networks for action recognition","author":"Garcia","year":"2018"},{"key":"10.1016\/j.neucom.2026.134265_bib0165","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113300","article-title":"Distilling vision-language pre-training models with modality-specific meta-learning","volume":"315","author":"Ma","year":"2025","journal-title":"Knowl.-based Syst."},{"key":"10.1016\/j.neucom.2026.134265_bib0170","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111351","article-title":"Cross-modal knowledge transfer for 3D point clouds via graph offset prediction","volume":"162","author":"Zhang","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.neucom.2026.134265_bib0175","author":"Li"},{"key":"10.1016\/j.neucom.2026.134265_bib0180","series-title":"Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","first-page":"1285","article-title":"Learning from multiple teacher networks","author":"You","year":"2017"},{"key":"10.1016\/j.neucom.2026.134265_bib0185","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"19390","article-title":"Cross-modal and uncertainty-aware agglomeration for open-vocabulary 3D scene understanding","author":"Li","year":"2025"},{"key":"10.1016\/j.neucom.2026.134265_bib0190","series-title":"2025 International Joint Conference on Neural Networks (IJCNN)","first-page":"1","article-title":"PointDico: contrastive 3D representation learning guided by diffusion models","author":"Li","year":"2025"},{"issue":"7","key":"10.1016\/j.neucom.2026.134265_bib0195","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3713070","article-title":"A survey of multimodal learning: methods, applications, and future","volume":"57","author":"Yuan","year":"2025","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.neucom.2026.134265_bib0200","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2025.103359","article-title":"Dual-domain decoupled fusion network for semantic segmentation of remote sensing images","volume":"124","author":"Li","year":"2025","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.neucom.2026.134265_bib0205","first-page":"1","article-title":"A frequency decoupling network for semantic segmentation of remote sensing images","volume":"63","author":"Li","year":"2025","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.neucom.2026.134265_bib0210","article-title":"Frequency domain-enhanced spectral-spatial fusion transformer for semantic segmentation of remote sensing images","author":"Li","year":"2026","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.neucom.2026.134265_bib0215","author":"Lepikhin"},{"issue":"120","key":"10.1016\/j.neucom.2026.134265_bib0220","first-page":"1","article-title":"Switch transformers: scaling to trillion parameter models with simple and efficient sparsity","volume":"23","author":"Fedus","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.neucom.2026.134265_bib0225","first-page":"8583","article-title":"Scaling vision with sparse mixture of experts","volume":"34","author":"Riquelme","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134265_bib0230","author":"Komatsuzaki"},{"key":"10.1016\/j.neucom.2026.134265_bib0235","doi-asserted-by":"crossref","first-page":"9564","DOI":"10.52202\/068431-0695","article-title":"Multimodal contrastive learning with limoe: the language-image mixture of experts","volume":"35","author":"Mustafa","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134265_bib0240","article-title":"Moe-llava: mixture of experts for large vision-language models","author":"Lin","year":"2026","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.neucom.2026.134265_bib0245","author":"Xing"},{"key":"10.1016\/j.neucom.2026.134265_bib0250","author":"Oord"},{"key":"10.1016\/j.neucom.2026.134265_bib0255","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"7482","article-title":"Multi-task learning using uncertainty to weigh losses for scene geometry and semantics","author":"Kendall","year":"2018"},{"key":"10.1016\/j.neucom.2026.134265_bib0260","author":"Chang"},{"key":"10.1016\/j.neucom.2026.134265_bib0265","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"1912","article-title":"3D shapenets: a deep representation for volumetric shapes","author":"Wu","year":"2015"},{"key":"10.1016\/j.neucom.2026.134265_bib0270","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"1588","article-title":"Revisiting point cloud classification: a new benchmark dataset and classification model on real-world data","author":"Uy","year":"2019"}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226016632?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226016632?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T11:39:18Z","timestamp":1783165158000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231226016632"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":54,"alternative-id":["S0925231226016632"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134265","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"CoTeach-CLIP: Cross-modal collaborative teachers for zero-shot point cloud recognition","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134265","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"134265"}}