{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:55:07Z","timestamp":1759334107110,"version":"build-2065373602"},"reference-count":63,"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":["62071127","62101137"],"award-info":[{"award-number":["62071127","62101137"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key Research and Development Program of China","award":["2022ZD0160101"],"award-info":[{"award-number":["2022ZD0160101"]}]},{"DOI":"10.13039\/100007219","name":"Natural Science Foundation of Shanghai Municipality","doi-asserted-by":"publisher","award":["23ZR1402900"],"award-info":[{"award-number":["23ZR1402900"]}],"id":[{"id":"10.13039\/100007219","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Municipal Science and Technology Major","award":["2021SHZDZX0103"],"award-info":[{"award-number":["2021SHZDZX0103"]}]},{"name":"A*STAR AME Programmatic Funding","award":["A18A2b0046"],"award-info":[{"award-number":["A18A2b0046"]}]},{"name":"RobotHTPO Seed Fund","award":["C211518008"],"award-info":[{"award-number":["C211518008"]}]},{"name":"EDB Space Technology Development Grant","award":["S22-19016-STDP"],"award-info":[{"award-number":["S22-19016-STDP"]}]},{"name":"Fudan University through CFFF Platform"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2025.3581776","type":"journal-article","created":{"date-parts":[[2025,6,20]],"date-time":"2025-06-20T13:29:00Z","timestamp":1750426140000},"page":"6273-6283","source":"Crossref","is-referenced-by-count":0,"title":["WI3D: Weakly Incremental 3D Detection via Vision Foundation Models"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-3758-0018","authenticated-orcid":false,"given":"Mingsheng","family":"Li","sequence":"first","affiliation":[{"name":"School of Information Science and Technology, Fudan University, Shanghai, China"}]},{"given":"Sijin","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, Fudan University, Shanghai, China"}]},{"given":"Shengji","family":"Tang","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, Fudan University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5177-8320","authenticated-orcid":false,"given":"Hongyuan","family":"Zhu","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research (I<sup>2<\/sup>R) &amp; Centre for Frontier AI Research (CFAR), A*STAR, Singapore"}]},{"given":"Yanyan","family":"Fang","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, Fudan University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9347-1367","authenticated-orcid":false,"given":"Xin","family":"Chen","sequence":"additional","affiliation":[{"name":"Tencent GY-Laboratory, Shanghai, China"}]},{"given":"Zhuoyuan","family":"Li","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, Fudan University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2623-1619","authenticated-orcid":false,"given":"Fukun","family":"Yin","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, Fudan University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0779-9818","authenticated-orcid":false,"given":"Tao","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, Fudan University, Shanghai, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00937"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00290"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_28"},{"key":"ref4","first-page":"29975","article-title":"CAGroup3D: Class-aware grouping for 3D object detection on point clouds","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Wang","year":"2022"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3275366"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3222934"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3109131"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3144183"},{"key":"ref9","first-page":"30492","article-title":"Bridging non co-occurrence with unlabeled in-the-wild data for incremental object detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Dong","year":"2021"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00433"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2773081"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.587"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00046"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3213473"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3410532"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3336243"},{"key":"ref17","article-title":"Beef: Bi-compatible class-incremental learning via energy-based expansion and fusion","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Wang","year":"2022"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3208743"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20254"},{"key":"ref20","article-title":"DA-CIL: Towards domain adaptive class-incremental 3D object detection","volume-title":"Proc. 33rd Brit. Mach. Vis. Conf.","author":"Zhao","year":"2022"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341834"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01300"},{"key":"ref23","first-page":"41","article-title":"M3DBENCH: Lets instruct large models with multi-modal 3D prompts","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Li","year":"2024"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref25","first-page":"36067","article-title":"Glipv2: Unifying localization and vision-language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Zhang","year":"2022"},{"key":"ref26","first-page":"9125","article-title":"DETClip: Dictionary-enriched visual-concept paralleled pre-training for open-world detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Yao","year":"2022"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02250"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00121"},{"key":"ref31","article-title":"WeakM3D: Towards weakly supervised monocular 3D object detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Peng","year":"2022"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2020.09.030"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00904"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00921"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02279"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00067"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00825"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01109"},{"key":"ref39","first-page":"71862","article-title":"CODA: Collaborative novel box discovery and cross-modal alignment for open-vocabulary 3D object detection","volume-title":"Proc. 37th Int. Conf. Neural Inf. Process. Syst.","author":"Cao","year":"2024"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_19"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01934-3"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02496"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01869-9"},{"key":"ref44","first-page":"51562","article-title":"Unleash the potential of image branch for cross-modal 3D object detection","volume-title":"Proc. 37th Int. Conf. Neural Inf. Process. Syst.","author":"Zhang","year":"2024"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00294"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3443335"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.5555\/3001460.3001507"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01070"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3387838"},{"key":"ref52","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":"ref53","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref54","article-title":"Learning object-language alignments for open-vocabulary object detection","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Lin","year":"2022"},{"key":"ref55","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":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref57","article-title":"Distilling the knowledge in a neural network","volume-title":"Proc. Deep Learn. Representation Learn. Workshop Conj. NIPS","author":"Hinton","year":"2014"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref60","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2014"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"article-title":"Fast segment anything","year":"2023","author":"Zhao","key":"ref62"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2006.479"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/11045442.pdf?arnumber=11045442","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T12:20:15Z","timestamp":1759234815000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11045442\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3581776","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"type":"print","value":"1520-9210"},{"type":"electronic","value":"1941-0077"}],"subject":[],"published":{"date-parts":[[2025]]}}}