{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:14:18Z","timestamp":1777889658802,"version":"3.51.4"},"reference-count":70,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":["62302188,62225603,62276111,62076041"],"award-info":[{"award-number":["62302188,62225603,62276111,62076041"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2662023XXQD001"],"award-info":[{"award-number":["2662023XXQD001"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01954","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"21026-21036","source":"Crossref","is-referenced-by-count":0,"title":["Describe, Adapt and Combine: Empowering CLIP Encoders for Open-Set 3D Object Retrieval"],"prefix":"10.1109","author":[{"given":"Zhichuan","family":"Wang","sequence":"first","affiliation":[{"name":"Huazhong Agricultural University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Zhou","sequence":"additional","affiliation":[{"name":"Shenzhen University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhe","family":"Liu","sequence":"additional","affiliation":[{"name":"The University of Hong Kong,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Yu","sequence":"additional","affiliation":[{"name":"University of Louisville,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Song","family":"Bai","sequence":"additional","affiliation":[{"name":"ByteDance,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yulong","family":"Wang","sequence":"additional","affiliation":[{"name":"Huazhong Agricultural University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinwei","family":"He","sequence":"additional","affiliation":[{"name":"Huazhong Agricultural University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiang","family":"Bai","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref2","first-page":"40","author":"Achlioptas","year":"2018","journal-title":"Learning representations and generative models for 3d point clouds"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref4","article-title":"Qwen-vl: A frontier large vision-language model with versatile abilities","author":"Bai","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/34.993558"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1111\/1467-8659.00669"},{"key":"ref7","article-title":"Shikra: Unleashing multimodal 1lm\u2019s referential dialogue magic","author":"Chen","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02283"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3072214"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/93"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00165"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00035"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018279"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.cag.2022.07.020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2023.3332768"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/AICCSA.2017.101"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3005434"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2904460"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00208"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00761"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110413"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00217"},{"key":"ref24","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"ICLR","author":"Hu","year":"2022"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331213"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02025"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.cad.2006.06.007"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00316"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00526"},{"key":"ref30","first-page":"156","article-title":"Rotation invariant spherical harmonic representation of 3 d shape descriptors","volume-title":"Symposium on geometry processing","author":"Kazhdan","year":"2003"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/1658346.1658347"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018682"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20062-5_3"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref35","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"NeurIPS"},{"key":"ref36","article-title":"Openshape: Scaling up 3d shape representation towards open-world understanding","volume":"36","author":"Liu","year":"2023","journal-title":"NeurIPS"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018778"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00910"},{"key":"ref39","article-title":"An empirical study of scaling instruct-tuned large multimodal models","author":"Lu","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/VSMM.2017.8346266"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7353481"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351009"},{"key":"ref43","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv preprint arXiv"},{"key":"ref44","article-title":"Kosmos-2: Grounding multimodal large language models to the world","author":"Peng","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref45","first-page":"652","article-title":"Pointnet: Deep learning on point sets for 3d classification and segmentation","volume-title":"CVPR","author":"Qi","year":"2017"},{"key":"ref46","article-title":"Pointnet++: Deep hierarchical feature learning on point sets in a metric space","volume":"30","author":"Qi","year":"2017","journal-title":"NeurIPS"},{"key":"ref47","first-page":"8748","author":"Radford","year":"2021","journal-title":"Learning transferable visual models from natural language supervision"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00271"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00254"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2025.3551084"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.114"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/SMI.2004.1314502"},{"issue":"4","key":"ref53","first-page":"1","article-title":"O-cnn: Octree-based convolutional neural networks for 3d shape analysis","volume":"36","author":"Wang","year":"2017","journal-title":"ACM TOG"},{"key":"ref54","article-title":"The all-seeing project: Towards panoptic visual recognition and understanding of the open world","author":"Wang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref55","article-title":"Visionllm: Large language model is also an openended decoder for vision-centric tasks","volume":"36","author":"Wang","year":"2024","journal-title":"NeurIPS"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3326362"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3731715.3733442"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00192"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.11.042"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2015.7298801"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00120"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02558"},{"key":"ref63","article-title":"Tip-adapter: Training-free clip-adapter for better visionlanguage modeling","author":"Zhang","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00836"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00571"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3144885"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00438"},{"key":"ref68","article-title":"Uni3d: Exploring unified 3d representation at scale","volume-title":"ICLR","author":"Zhou","year":"2024"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00249"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11443448.pdf?arnumber=11443448","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:13:41Z","timestamp":1777612421000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443448\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":70,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01954","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}