{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T11:09:18Z","timestamp":1789124958256,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":52,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032372802","type":"print"},{"value":"9783032372819","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-37281-9_18","type":"book-chapter","created":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T10:45:11Z","timestamp":1789123511000},"page":"300-317","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Open-Vocabulary 3D Object Detection with\u00a0Co-distillation Discovery and\u00a0Dual Guidance Robust Training"],"prefix":"10.1007","author":[{"given":"Shangbo","family":"Yuan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaofeng","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Na","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,12]]},"reference":[{"key":"18_CR1","first-page":"23716","volume":"35","author":"JB Alayrac","year":"2022","unstructured":"Alayrac, J.B., et al.: Flamingo: a visual language model for few-shot learning. NeurIPS 35, 23716\u201323736 (2022)","journal-title":"NeurIPS"},{"key":"18_CR2","unstructured":"Cao, S., Li, C., Xu, J., Li, T., Zhao, N.: Late-decoupled 3d hierarchical semantic segmentation with semantic prototype discrimination based bi-branch supervision. arXiv preprint arXiv:2511.16650 (2025)"},{"key":"18_CR3","first-page":"71862","volume":"36","author":"Y Cao","year":"2023","unstructured":"Cao, Y., Yihan, Z., Xu, H., Xu, D.: Coda: collaborative novel box discovery and cross-modal alignment for open-vocabulary 3d object detection. NeurIPS 36, 71862\u201371873 (2023)","journal-title":"NeurIPS"},{"issue":"11","key":"18_CR4","doi-asserted-by":"publisher","first-page":"10475","DOI":"10.1109\/TPAMI.2025.3593580","volume":"47","author":"Y Cao","year":"2025","unstructured":"Cao, Y., Zeng, Y., Xu, H., Xu, D.: Collaborative novel object discovery and box-guided cross-modal alignment for open-vocabulary 3d object detection. IEEE Trans. Pattern Anal. Mach. Intell. 47(11), 10475\u201310489 (2025)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"18_CR5","doi-asserted-by":"crossref","unstructured":"Dai, A., Chang, A.X., Savva, M., Halber, M., Funkhouser, T., Nie\u00dfner, M.: Scannet: richly-annotated 3d reconstructions of indoor scenes. In: CVPR, pp. 5828\u20135839 (2017)","DOI":"10.1109\/CVPR.2017.261"},{"key":"18_CR6","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: CVPR, pp. 248\u2013255 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"issue":"5","key":"18_CR7","doi-asserted-by":"publisher","first-page":"3580","DOI":"10.1109\/TPAMI.2025.3532637","volume":"47","author":"J Deng","year":"2025","unstructured":"Deng, J., Lu, J., Zhang, T.: Quantity-quality enhanced self-training network for weakly supervised point cloud semantic segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 47(5), 3580\u20133596 (2025)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"18_CR8","doi-asserted-by":"crossref","unstructured":"Deng, J., He, T., Jiang, L., Wang, T., Dayoub, F., Reid, I.: 3d-llava: towards generalist 3d lmms with omni superpoint transformer. In: CVPR, pp. 3772\u20133782 (2025)","DOI":"10.1109\/CVPR52734.2025.00357"},{"key":"18_CR9","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: ICLR (2021)"},{"key":"18_CR10","doi-asserted-by":"crossref","unstructured":"Etchegaray, D., Huang, Z., Harada, T., Luo, Y.: Find n\u2019propagate: open-vocabulary 3d object detection in urban environments. In: ECCV, vol. 15098, pp. 133\u2013151 (2024)","DOI":"10.1007\/978-3-031-73661-2_8"},{"issue":"2","key":"18_CR11","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham, M., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes (voc) challenge. Int. J. Comput. Vision 88(2), 303\u2013338 (2010)","journal-title":"Int. J. Comput. Vision"},{"key":"18_CR12","unstructured":"Gu, X., Lin, T.Y., Kuo, W., Cui, Y.: Open-vocabulary object detection via vision and language knowledge distillation. In: ICLR (2022)"},{"key":"18_CR13","doi-asserted-by":"crossref","unstructured":"Gupta, A., Dollar, P., Girshick, R.: Lvis: a dataset for large vocabulary instance segmentation. In: CVPR, pp, pp. 5356\u20135364 (2019)","DOI":"10.1109\/CVPR.2019.00550"},{"key":"18_CR14","doi-asserted-by":"crossref","unstructured":"Han, Y., Zhao, N., Chen, W., Ma, K.T., Zhang, H.: Dual-perspective knowledge enrichment for semi-supervised 3d object detection. In: AAAI, vol. 38, pp. 2049\u20132057 (2024)","DOI":"10.1609\/aaai.v38i3.27976"},{"key":"18_CR15","doi-asserted-by":"crossref","unstructured":"Huang, J., Zhang, J., Jiang, K., Lu, S.: Open-vocabulary object detection via language hierarchy. NeurIPS 37, 124951\u2013124978 (2024)","DOI":"10.52202\/079017-3968"},{"key":"18_CR16","doi-asserted-by":"crossref","unstructured":"Jiang, L., Shi, S., Schiele, B.: Open-vocabulary 3d semantic segmentation with foundation models. In: CVPR, pp. 21284\u201321294 (2024)","DOI":"10.1109\/CVPR52733.2024.02011"},{"key":"18_CR17","doi-asserted-by":"crossref","unstructured":"Jiao, P., Zhao, N., Chen, J., Jiang, Y.G.: Unlocking textual and visual wisdom: open-vocabulary 3d object detection enhanced by comprehensive guidance from text and image. In: ECCV, vol. 15106, pp. 376\u2013392 (2024)","DOI":"10.1007\/978-3-031-73195-2_22"},{"key":"18_CR18","first-page":"5574","volume":"30","author":"A Kendall","year":"2017","unstructured":"Kendall, A., Gal, Y.: What uncertainties do we need in bayesian deep learning for computer vision? NeurIPS 30, 5574\u20135584 (2017)","journal-title":"NeurIPS"},{"key":"18_CR19","doi-asserted-by":"crossref","unstructured":"Lazarow, J., Griffiths, D., Kohavi, G., Crespo, F., Dehghan, A.: Cubify anything: scaling indoor 3d object detection. In: CVPR, pp. 22225\u201322233. (2025)","DOI":"10.1109\/CVPR52734.2025.02070"},{"key":"18_CR20","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In: ICML, pp. 12888\u201312900 (2022)"},{"key":"18_CR21","doi-asserted-by":"crossref","unstructured":"Li, L.H., et\u00a0al.: Grounded language-image pre-training. In: CVPR, pp. 10965\u201310975 (2022)","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"18_CR22","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., et al.: Microsoft coco: common objects in context. In: ECCV, pp. 740\u2013755 (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"18_CR23","doi-asserted-by":"crossref","unstructured":"Liu, S., et\u00a0al.: Grounding dino: marrying dino with grounded pre-training for open-set object detection. In: ECCV, vol. 15105, pp. 38\u201355 (2024)","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"18_CR24","doi-asserted-by":"crossref","unstructured":"Lu, Y., Xu, C., Wei, X., Xie, X., Tomizuka, M., Keutzer, K., Zhang, S.: Open-vocabulary point-cloud object detection without 3d annotation. In: CVPR, pp. 1190\u20131199 (2023)","DOI":"10.1109\/CVPR52729.2023.00121"},{"key":"18_CR25","doi-asserted-by":"crossref","unstructured":"Misra, I., Girdhar, R., Joulin, A.: An end-to-end transformer model for 3d object detection. In: ICCV, pp. 2906\u20132917 (2021)","DOI":"10.1109\/ICCV48922.2021.00290"},{"key":"18_CR26","doi-asserted-by":"crossref","unstructured":"Qi, C.R., Litany, O., He, K., Guibas, L.J.: Deep hough voting for 3d object detection in point clouds. In: ICCV, pp. 9277\u20139286 (2019)","DOI":"10.1109\/ICCV.2019.00937"},{"key":"18_CR27","first-page":"5099","volume":"30","author":"CR Qi","year":"2017","unstructured":"Qi, C.R., Yi, L., Su, H., Guibas, L.J.: Pointnet++: deep hierarchical feature learning on point sets in a metric space. NeurIPS 30, 5099\u20135108 (2017)","journal-title":"NeurIPS"},{"key":"18_CR28","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML, pp. 8748\u20138763 (2021)"},{"issue":"6","key":"18_CR29","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2016","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137\u20131149 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"18_CR30","unstructured":"Seitzer, M., Tavakoli, A., Antic, D., Martius, G.: On the pitfalls of heteroscedastic uncertainty estimation with probabilistic neural networks. In: ICLR (2022)"},{"issue":"7","key":"18_CR31","doi-asserted-by":"publisher","first-page":"4817","DOI":"10.1007\/s11263-025-02404-8","volume":"133","author":"H Sheng","year":"2025","unstructured":"Sheng, H., et al.: Ct3d++: improving 3d object detection with keypoint-induced channel-wise transformer. Int. J. Comput. Vision 133(7), 4817\u20134836 (2025)","journal-title":"Int. J. Comput. Vision"},{"key":"18_CR32","unstructured":"Singh, A., et\u00a0al.: Openai gpt-5 system card. arXiv preprint arXiv:2601.03267 (2025)"},{"key":"18_CR33","doi-asserted-by":"crossref","unstructured":"Song, S., Lichtenberg, S.P., Xiao, J.: Sun rgb-d: A rgb-d scene understanding benchmark suite. In: CVPR, pp. 567\u2013576 (2015)","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"18_CR34","doi-asserted-by":"crossref","unstructured":"Tran, P.V.: Simltd: Simple supervised and semi-supervised long-tailed object detection. In: CVPR, pp. 4672\u20134681 (2025)","DOI":"10.1109\/CVPR52734.2025.00440"},{"key":"18_CR35","doi-asserted-by":"crossref","unstructured":"Wang, J., Zhao, N.: Uncertainty meets diversity: a comprehensive active learning framework for indoor 3d object detection. In: CVPR, pp. 20329\u201320339 (2025)","DOI":"10.1109\/CVPR52734.2025.01893"},{"key":"18_CR36","doi-asserted-by":"crossref","unstructured":"Wang, J., et al.: Ov-dquo: open-vocabulary detr with denoising text query training and open-world unknown objects supervision. In: AAAI, pp. 7762\u20137770 (2025)","DOI":"10.1609\/aaai.v39i7.32836"},{"key":"18_CR37","first-page":"21429","volume":"36","author":"X Wang","year":"2023","unstructured":"Wang, X., Li, S., Kallidromitis, K., Kato, Y., Kozuka, K., Darrell, T.: Hierarchical open-vocabulary universal image segmentation. NeurIPS 36, 21429\u201321453 (2023)","journal-title":"NeurIPS"},{"key":"18_CR38","first-page":"39876","volume":"36","author":"Z Wang","year":"2023","unstructured":"Wang, Z., Li, Y.L., Chen, X., Zhao, H., Wang, S.: Uni3detr: unified 3d detection transformer. NeurIPS 36, 39876\u201339896 (2023)","journal-title":"NeurIPS"},{"key":"18_CR39","doi-asserted-by":"crossref","unstructured":"Wang, Z., Li, Y., Liu, T., Zhao, H., Wang, S.: Ov-uni3detr: towards unified open-vocabulary 3d object detection via cycle-modality propagation. In: ECCV, vol. 15105, pp. 73\u201389 (2024)","DOI":"10.1007\/978-3-031-72970-6_5"},{"key":"18_CR40","unstructured":"Wu, Y., Wang, K., Pan, Y., Zhao, N.: Ccf: complementary collaborative fusion for domain generalized multi-modal 3d object detection. In: CVPR, pp. 18745\u201318754 (2026)"},{"key":"18_CR41","unstructured":"Xu, J., Zhao, N.: Stream3D: streaming zero-shot 3d instance segmentation with multi-view noise mask filtering and manifold refining. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Findings, pp. 327\u2013337 (2026)"},{"key":"18_CR42","doi-asserted-by":"crossref","unstructured":"Yao, L., et al.: Detclipv2: scalable open-vocabulary object detection pre-training via word-region alignment. In: CVPR, pp. 23497\u201323506 (2023)","DOI":"10.1109\/CVPR52729.2023.02250"},{"key":"18_CR43","first-page":"9125","volume":"35","author":"L Yao","year":"2022","unstructured":"Yao, L., et al.: Detclip: dictionary-enriched visual-concept paralleled pre-training for open-world detection. NeurIPS 35, 9125\u20139138 (2022)","journal-title":"NeurIPS"},{"key":"18_CR44","doi-asserted-by":"crossref","unstructured":"Yuan, S., Xu, J., Hu, P., Zhu, X., Zhao, N.: Graph smoothing for enhanced local geometry learning in point cloud analysis. In: AAAI, vol.\u00a040, pp. 12250\u201312258 (2026)","DOI":"10.1609\/aaai.v40i15.38216"},{"key":"18_CR45","doi-asserted-by":"crossref","unstructured":"Zareian, A., Rosa, K.D., Hu, D.H., Chang, S.F.: Open-vocabulary object detection using captions. In: CVPR, pp. 14393\u201314402 (2021)","DOI":"10.1109\/CVPR46437.2021.01416"},{"key":"18_CR46","doi-asserted-by":"crossref","unstructured":"Zeng, Y., et al.: Clip2: contrastive language-image-point pretraining from real-world point cloud data. In: CVPR, pp. 15244\u201315253 (2023)","DOI":"10.1109\/CVPR52729.2023.01463"},{"key":"18_CR47","doi-asserted-by":"crossref","unstructured":"Zhang, H., Li, F., Zou, X., Liu, S., Li, C., Yang, J., Zhang, L.: A simple framework for open-vocabulary segmentation and detection. In: ICCV, pp. 1020\u20131031 (2023)","DOI":"10.1109\/ICCV51070.2023.00100"},{"key":"18_CR48","doi-asserted-by":"crossref","unstructured":"Zhao, N., Chua, T.S., Lee, G.H.: Sess: self-ensembling semi-supervised 3d object detection. In: CVPR, pp. 11079\u201311087 (2020)","DOI":"10.1109\/CVPR42600.2020.01109"},{"key":"18_CR49","doi-asserted-by":"crossref","unstructured":"Zhao, N., Lee, G.H.: Static-dynamic co-teaching for class-incremental 3d object detection. In: AAAI, vol.\u00a036, pp. 3436\u20133445 (2022)","DOI":"10.1609\/aaai.v36i3.20254"},{"key":"18_CR50","doi-asserted-by":"crossref","unstructured":"Zhou, X., Girdhar, R., Joulin, A., Kr\u00e4henb\u00fchl, P., Misra, I.: Detecting twenty-thousand classes using image-level supervision. In: ECCV, vol. 13669, pp. 350\u2013368 (2022)","DOI":"10.1007\/978-3-031-20077-9_21"},{"key":"18_CR51","doi-asserted-by":"crossref","unstructured":"Zhu, X., et al.: Open-vocabulary 3d semantic segmentation with text-to-image diffusion models. In: ECCV, vol. 15087, pp. 357\u2013375 (2024)","DOI":"10.1007\/978-3-031-73397-0_21"},{"key":"18_CR52","unstructured":"Zhu, Y., Qian, J., Yang, J., Xie, J., Zhao, N.: Few-shot incremental 3d object detection in dynamic indoor environments. In: CVPR, pp. 18786\u201318795 (2026)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37281-9_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T10:45:20Z","timestamp":1789123520000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37281-9_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032372802","9783032372819"],"references-count":52,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37281-9_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"12 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}