{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T12:19:39Z","timestamp":1781007579246,"version":"3.54.1"},"reference-count":89,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2023YFB4502804"],"award-info":[{"award-number":["2023YFB4502804"]}]},{"DOI":"10.13039\/501100014219","name":"National Science Fund for Distinguished Young Scholars","doi-asserted-by":"publisher","award":["62025603"],"award-info":[{"award-number":["62025603"]}],"id":[{"id":"10.13039\/501100014219","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U22B2051"],"award-info":[{"award-number":["U22B2051"]}],"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":["62072389"],"award-info":[{"award-number":["62072389"]}],"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":["62302411"],"award-info":[{"award-number":["62302411"]}],"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":["624B2118"],"award-info":[{"award-number":["624B2118"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Foundation of Fujian Province of China","award":["2021J06003"],"award-info":[{"award-number":["2021J06003"]}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2023M732948"],"award-info":[{"award-number":["2023M732948"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1109\/tpami.2024.3523675","type":"journal-article","created":{"date-parts":[[2024,12,30]],"date-time":"2024-12-30T19:27:23Z","timestamp":1735586843000},"page":"2475-2492","source":"Crossref","is-referenced-by-count":11,"title":["JM3D & JM3D-LLM: Elevating 3D Representation With Joint Multi-Modal Cues"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9956-6308","authenticated-orcid":false,"given":"Jiayi","family":"Ji","sequence":"first","affiliation":[{"name":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0289-9672","authenticated-orcid":false,"given":"Haowei","family":"Wang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Changli","family":"Wu","sequence":"additional","affiliation":[{"name":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8744-3423","authenticated-orcid":false,"given":"Yiwei","family":"Ma","sequence":"additional","affiliation":[{"name":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3912-9306","authenticated-orcid":false,"given":"Xiaoshuai","family":"Sun","sequence":"additional","affiliation":[{"name":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9163-2932","authenticated-orcid":false,"given":"Rongrong","family":"Ji","sequence":"additional","affiliation":[{"name":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"40","article-title":"Learning representations and generative models for 3D point clouds","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Achlioptas"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00534"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58592-1_20"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01837"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_21"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00319"},{"key":"ref7","first-page":"14 388","article-title":"P2P: Tuning pre-trained image models for point cloud analysis with point-to-pixel prompting","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00294"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00273"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.170"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01667"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00217"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00120"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00219"},{"key":"ref16","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref17","first-page":"34 892","article-title":"Visual instruction tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref18","first-page":"1","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"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2011.6130444"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539838"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2009.01515.x"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298801"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7353481"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.442"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01054"},{"key":"ref26","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"},{"key":"ref27","first-page":"23 192","article-title":"PointNext: Revisiting pointnet++ with improved training and scaling strategies","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Qian"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-021-0229-5"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20086-1_38"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3262786"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01871"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20086-1_35"},{"key":"ref34","first-page":"27061","article-title":"Point-M2AE: Multi-scale masked autoencoders for hierarchical point cloud pre-training","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_34"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00470"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00463"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01849"},{"key":"ref39","article-title":"VisualBERT: A simple and performant baseline for vision and language","author":"Li","year":"2019"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.329"},{"key":"ref43","first-page":"13","article-title":"VilBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25350"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref47","first-page":"36 067","article-title":"GLIPv2: Unifying localization and vision-language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref48","first-page":"23 716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Alayrac"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00490"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.544"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_7"},{"key":"ref53","first-page":"6373","article-title":"Matching structure for dual learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fei"},{"key":"ref54","article-title":"Multimodal semi-supervised learning for 3D objects","volume-title":"Proc. 32nd Brit. Mach. Vis. Conf.","author":"Chen"},{"key":"ref55","first-page":"32 398","article-title":"Let images give you more: Point cloud cross-modal training for shape analysis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yan"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00258"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00836"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02558"},{"key":"ref59","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"issue":"8","key":"ref60","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"ref62","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Houlsby"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1250"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.20"},{"key":"ref65","first-page":"27 730","article-title":"Training language models to follow instructions with human feedback","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ouyang"},{"key":"ref66","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref67","first-page":"1","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Zhu"},{"key":"ref68","first-page":"1","article-title":"LLaMA-adapter: Efficient fine-tuning of language models with zero-init attention","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Zhang"},{"key":"ref69","article-title":"PointLLM: Empowering large language models to understand point clouds","author":"Xu","year":"2023"},{"key":"ref70","article-title":"Point-bind & point-llm: Aligning point cloud with multi-modality for 3D understanding, generation, and instruction following","author":"Guo","year":"2023"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref72","article-title":"ShapeNet: An information-rich 3D model repository","author":"Chang","year":"2015"},{"key":"ref73","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"},{"key":"ref74","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref75","first-page":"24 261","article-title":"MLP-Mixer: An all-MLP architecture for vision","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tolstikhin"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"ref77","first-page":"75307","article-title":"Scalable 3D captioning with pretrained models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Luo"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00167"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_30"},{"key":"ref81","article-title":"Vicuna: An open-source chatbot impressing GPT-4 with 90%* chatgpt quality","author":"Chiang","year":"2023"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_34"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00187"},{"key":"ref84","first-page":"23 580","article-title":"SageMix: Saliency-guided mixup for point clouds","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lee"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00054"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3206664"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.09.008"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00007"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.383"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10916529\/10817587.pdf?arnumber=10817587","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,7]],"date-time":"2025-03-07T18:41:50Z","timestamp":1741372910000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10817587\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":89,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3523675","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4]]}}}