{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T21:32:27Z","timestamp":1771882347975,"version":"3.50.1"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100007219","name":"Natural Science Foundation of Shanghai Municipality","doi-asserted-by":"publisher","award":["22ZR1443700"],"award-info":[{"award-number":["22ZR1443700"]}],"id":[{"id":"10.13039\/100007219","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Sci. Eng."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tase.2026.3659154","type":"journal-article","created":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T21:10:52Z","timestamp":1770671452000},"page":"4693-4703","source":"Crossref","is-referenced-by-count":0,"title":["OpenVL: Bridging 2-D and 3-D Worlds for Open-Vocabulary 3-D Scene Understanding"],"prefix":"10.1109","volume":"23","author":[{"given":"Xiao","family":"Jin","sequence":"first","affiliation":[{"name":"University of Shanghai for Science and Technology, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3242-0857","authenticated-orcid":false,"given":"Yongxiong","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Shanghai for Science and Technology, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5341-5105","authenticated-orcid":false,"given":"Shuai","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Shanghai for Science and Technology, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nan","family":"Zhang","sequence":"additional","affiliation":[{"name":"China Pacific Life Insurance (Group) Company Ltd., Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Han","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Shanghai for Science and Technology, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8040-2792","authenticated-orcid":false,"given":"Hui","family":"Yang","sequence":"additional","affiliation":[{"name":"Innovation Center of Intelligent Ophtalmic Technologies and Equipment, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiming","family":"Li","sequence":"additional","affiliation":[{"name":"Innovation Center of Intelligent Ophtalmic Technologies and Equipment, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"3D object detection for autonomous driving: A comprehensive survey","author":"Mao","year":"2022","journal-title":"arXiv:2206.09474"},{"key":"ref2","first-page":"10901","article-title":"Language-driven semantic segmentation","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Li"},{"key":"ref3","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.127649","article-title":"OFMPNet: Deep end-to-end model for occupancy and flow prediction in urban environment","volume":"586","author":"Murhij","year":"2024","journal-title":"Neurocomputing"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2025.3531504"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"142","DOI":"10.1016\/j.neucom.2016.11.085","article-title":"Grounding the experience of a visual field through sensorimotor contingencies","volume":"268","author":"Laflaqui\u00e8re","year":"2017","journal-title":"Neurocomputing"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1016\/j.neucom.2021.05.027","article-title":"LIFT-SLAM: A deep-learning feature-based monocular visual SLAM method","volume":"455","author":"Bruno","year":"2021","journal-title":"Neurocomputing"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2025.129963"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2023.3313228"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.082"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2024.3374823"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW63481.2024.10645462"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01345"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2025.130113"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2023.3345927"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2024.3470799"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/tase.2023.3322710"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00085"},{"key":"ref18","article-title":"Kosmos-2: Grounding multimodal large language models to the world","author":"Peng","year":"2023","journal-title":"arXiv:2306.14824"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00677"},{"key":"ref20","first-page":"1244","article-title":"Weakly supervised 3D open-vocabulary segmentation","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref21","first-page":"71569","article-title":"Transient neural radiance fields for LiDAR view synthesis and 3D reconstruction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Malik"},{"key":"ref22","first-page":"25278","article-title":"LAION-5B: An open large-scale dataset for training next generation image-text models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Schuhmann"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3410324"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00533"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01874"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_25"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01057"},{"key":"ref28","first-page":"14388","article-title":"Open-vocabulary object detection using captions","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Zareian"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2025.3604455"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2023.3342153"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01855"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01533"},{"key":"ref34","article-title":"LLaVA-NeXT-interleave: Tackling multi-image, video, and 3D in large multimodal models","author":"Li","year":"2024","journal-title":"arXiv:2407.07895"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72989-8_12"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00678"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72633-0_25"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00492"},{"key":"ref39","first-page":"75896","article-title":"Towards label-free scene understanding by vision foundation models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72698-9_8"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2023.3340027"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2024.3355225"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01463"},{"key":"ref44","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref45","first-page":"30146","article-title":"BLIP-diffusion: Pre-trained subject representation for controllable text-to-image generation and editing","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.775"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01313"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00065"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref50","first-page":"84","article-title":"nuScenes: A multimodal dataset for autonomous driving","volume-title":"Proc. CVPR","author":"Caesar"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_8"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00107"},{"issue":"10","key":"ref53","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":"ref54","article-title":"Cross-entropy loss functions: Theoretical analysis and applications","author":"Mao","year":"2023","journal-title":"arXiv:2304.07288"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01854"},{"key":"ref56","article-title":"3D-LLM: Injecting the 3D world into large language models","volume-title":"arXiv:2307.12981","author":"Hong","year":"2023"},{"key":"ref57","first-page":"4566","article-title":"CIDEr: Consensus-based image description evaluation","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Vedantam"},{"key":"ref58","first-page":"10984","article-title":"Bleu: A method for automatic evaluation of machine translation","volume-title":"Proc. Annu. Meeting Assoc. Comput. Linguistics","author":"Papineni"},{"key":"ref59","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proc. IEEvaluation@ACL","author":"Banerjee"},{"key":"ref60","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Proc. Annu. Meeting Assoc. Comput. Linguistics","author":"Lin"},{"key":"ref61","first-page":"9224","article-title":"3D semantic segmentation with submanifold sparse convolutional networks","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Graham"},{"key":"ref62","article-title":"OPT: Open pre-trained transformer language models","author":"Zhang","year":"2022","journal-title":"arXiv:2205.01068"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_40"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00272"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72784-9_11"},{"key":"ref66","article-title":"LL3DA: Visual interactive instruction tuning for omni-3D understanding, reasoning, and planning","author":"Chen","year":"2023","journal-title":"arXiv:2311.18651"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"}],"container-title":["IEEE Transactions on Automation Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8856\/11323516\/11381602.pdf?arnumber=11381602","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T20:50:49Z","timestamp":1771879849000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11381602\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":67,"URL":"https:\/\/doi.org\/10.1109\/tase.2026.3659154","relation":{},"ISSN":["1545-5955","1558-3783"],"issn-type":[{"value":"1545-5955","type":"print"},{"value":"1558-3783","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}