{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T16:23:13Z","timestamp":1783614193358,"version":"3.55.0"},"publisher-location":"Cham","reference-count":68,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729690","type":"print"},{"value":"9783031729706","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,23]],"date-time":"2024-11-23T00:00:00Z","timestamp":1732320000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,23]],"date-time":"2024-11-23T00:00:00Z","timestamp":1732320000000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-72970-6_5","type":"book-chapter","created":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T10:51:23Z","timestamp":1732272683000},"page":"73-89","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["OV-Uni3DETR: Towards Unified Open-Vocabulary 3D Object Detection via\u00a0Cycle-Modality Propagation"],"prefix":"10.1007","author":[{"given":"Zhenyu","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yali","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Taichi","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hengshuang","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shengjin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,23]]},"reference":[{"key":"5_CR1","unstructured":"Bangalath, H., Maaz, M., Khattak, M.U., Khan, S.H., Shahbaz\u00a0Khan, F.: Bridging the gap between object and image-level representations for open-vocabulary detection. In: NeurIPS (2022)"},{"key":"5_CR2","doi-asserted-by":"crossref","unstructured":"Brazil, G., Kumar, A., Straub, J., Ravi, N., Johnson, J., Gkioxari, G.: Omni3D: a large benchmark and model for 3D object detection in the wild. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01264"},{"key":"5_CR3","doi-asserted-by":"crossref","unstructured":"Caesar, H., et al.: nuScenes: a multimodal dataset for autonomous driving. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"5_CR4","unstructured":"Cao, Y., Zeng, Y., Xu, H., Xu, D.: Coda: collaborative novel box discovery and cross-modal alignment for open-vocabulary 3D object detection. In: NeurIPS (2023)"},{"key":"5_CR5","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"5_CR6","doi-asserted-by":"crossref","unstructured":"Cen, J., Yun, P., Cai, J., Wang, M.Y., Liu, M.: Open-set 3D object detection. In: 3DV (2021)","DOI":"10.1109\/3DV53792.2021.00095"},{"key":"5_CR7","unstructured":"Contributors, M.: Mmdetection3D: openmmlab next-generation platform for general 3D object detection (2020)"},{"key":"5_CR8","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 (2017)","DOI":"10.1109\/CVPR.2017.261"},{"key":"5_CR9","doi-asserted-by":"crossref","unstructured":"Ding, R., Yang, J., Xue, C., Zhang, W., Bai, S., Qi, X.: PLA: language-driven open-vocabulary 3D scene understanding. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00677"},{"key":"5_CR10","doi-asserted-by":"crossref","unstructured":"Du, Y., Wei, F., Zhang, Z., Shi, M., Gao, Y., Li, G.: Learning to prompt for open-vocabulary object detection with vision-language model. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01369"},{"key":"5_CR11","doi-asserted-by":"crossref","unstructured":"Ge, C., et al.: MetaBEV: solving sensor failures for 3D detection and map segmentation. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00801"},{"key":"5_CR12","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Stiller, C., Urtasun, R.: Vision meets robotics: the KITTI dataset. IJRR (2013)","DOI":"10.1177\/0278364913491297"},{"key":"5_CR13","unstructured":"Gu, X., Lin, T.Y., Kuo, W., Cui, Y.: Open-vocabulary object detection via vision and language knowledge distillation. In: ICLR (2022)"},{"key":"5_CR14","doi-asserted-by":"crossref","unstructured":"Gupta, A., Dollar, P., Girshick, R.: LVIS: a dataset for large vocabulary instance segmentation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00550"},{"key":"5_CR15","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"5_CR16","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: ICML (2021)"},{"key":"5_CR17","doi-asserted-by":"crossref","unstructured":"Kim, D., Lin, T.Y., Angelova, A., Kweon, I.S., Kuo, W.: Learning open-world object proposals without learning to classify. RAL (2022)","DOI":"10.1109\/LRA.2022.3146922"},{"key":"5_CR18","doi-asserted-by":"crossref","unstructured":"Kuznetsova, A., et\u00a0al.: The open images dataset v4. IJCV (2020)","DOI":"10.1007\/s11263-020-01316-z"},{"key":"5_CR19","doi-asserted-by":"crossref","unstructured":"Li, L.H., et\u00a0al.: Grounded language-image pre-training. In: CVPR (2022)","DOI":"10.1109\/CVPR52729.2023.02240"},{"key":"5_CR20","doi-asserted-by":"crossref","unstructured":"Li, Z., et al.: BEVFormer: learning bird\u2019s-eye-view representation from multi-camera images via spatiotemporal transformers. In: ECCV (2022)","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"5_CR21","unstructured":"Liang, T., et al.: BEVFusion: a simple and robust lidar-camera fusion framework. In: NeurIPS (2022)"},{"key":"5_CR22","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"5_CR23","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., et al.: Microsoft coco: common objects in context. In: ECCV (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"5_CR24","doi-asserted-by":"crossref","unstructured":"Liu, S., et\u00a0al.: Grounding DINO: marrying DINO with grounded pre-training for open-set object detection. arXiv preprint arXiv:2303.05499 (2023)","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"5_CR25","doi-asserted-by":"crossref","unstructured":"Liu, Z., Zhang, Z., Cao, Y., Hu, H., Tong, X.: Group-free 3D object detection via transformers. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00294"},{"key":"5_CR26","doi-asserted-by":"crossref","unstructured":"Liu, Z., Wu, Z., T\u00f3th, R.: Smoke: single-stage monocular 3D object detection via keypoint estimation. In: CVPRW (2020)","DOI":"10.1109\/CVPRW50498.2020.00506"},{"key":"5_CR27","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: ICLR (2019)"},{"key":"5_CR28","doi-asserted-by":"crossref","unstructured":"Lu, Y., et al.: Geometry uncertainty projection network for monocular 3D object detection. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00310"},{"key":"5_CR29","unstructured":"Lu, Y., et al.: Open-set 3D detection via image-level class and debiased cross-modal contrastive learning (2022)"},{"key":"5_CR30","doi-asserted-by":"crossref","unstructured":"Lu, Y., et al.: Open-vocabulary point-cloud object detection without 3D annotation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00121"},{"key":"5_CR31","unstructured":"Ma, Z., et al.: Open-vocabulary one-stage detection with hierarchical visual-language knowledge distillation. In: CVPR (2022)"},{"key":"5_CR32","doi-asserted-by":"crossref","unstructured":"Minderer, M., et\u00a0al.: Simple open-vocabulary object detection with vision transformers. In: ECCV (2022)","DOI":"10.1007\/978-3-031-20080-9_42"},{"key":"5_CR33","doi-asserted-by":"crossref","unstructured":"Qi, C.R., Chen, X., Litany, O., Guibas, L.J.: ImVoteNet: boosting 3D object detection in point clouds with image votes. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00446"},{"key":"5_CR34","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 (2019)","DOI":"10.1109\/ICCV.2019.00937"},{"key":"5_CR35","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"5_CR36","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NeurIPS (2015)"},{"key":"5_CR37","doi-asserted-by":"crossref","unstructured":"Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., Savarese, S.: Generalized intersection over union: a metric and a loss for bounding box regression. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00075"},{"key":"5_CR38","doi-asserted-by":"crossref","unstructured":"Rozenberszki, D., Litany, O., Dai, A.: Language-grounded indoor 3d semantic segmentation in the wild. In: ECCV (2022)","DOI":"10.1007\/978-3-031-19827-4_8"},{"key":"5_CR39","doi-asserted-by":"crossref","unstructured":"Rukhovich, D., Vorontsova, A., Konushin, A.: FCAF3D: fully convolutional anchor-free 3D object detection. In: ECCV (2022)","DOI":"10.1007\/978-3-031-20080-9_28"},{"key":"5_CR40","doi-asserted-by":"crossref","unstructured":"Rukhovich, D., Vorontsova, A., Konushin, A.: ImVoxelNet: image to voxels projection for monocular and multi-view general-purpose 3D object detection. In: WACV (2022)","DOI":"10.1109\/WACV51458.2022.00133"},{"key":"5_CR41","doi-asserted-by":"crossref","unstructured":"Saito, K., Hu, P., Darrell, T., Saenko, K.: Learning to detect every thing in an open world. In: ECCV (2022)","DOI":"10.1007\/978-3-031-20053-3_16"},{"key":"5_CR42","doi-asserted-by":"crossref","unstructured":"Shao, S., et al.: Objects365: a large-scale, high-quality dataset for object detection. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00852"},{"key":"5_CR43","doi-asserted-by":"crossref","unstructured":"Sheng, H., et al.: Improving 3D object detection with channel-wise transformer. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00274"},{"key":"5_CR44","doi-asserted-by":"crossref","unstructured":"Shi, S., et al.: PV-RCNN: point-voxel feature set abstraction for 3D object detection. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01054"},{"key":"5_CR45","doi-asserted-by":"crossref","unstructured":"Shi, S., Wang, Z., Shi, J., Wang, X., Li, H.: From points to parts: 3D object detection from point cloud with part-aware and part-aggregation network. TPAMI (2020)","DOI":"10.1109\/TPAMI.2020.2977026"},{"key":"5_CR46","doi-asserted-by":"crossref","unstructured":"Shi, X., Ye, Q., Chen, X., Chen, C., Chen, Z., Kim, T.K.: Geometry-based distance decomposition for monocular 3D object detection. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01489"},{"key":"5_CR47","doi-asserted-by":"crossref","unstructured":"Sindagi, V.A., Zhou, Y., Tuzel, O.: MVX-net: multimodal voxelnet for 3D object detection. In: ICRA (2019)","DOI":"10.1109\/ICRA.2019.8794195"},{"key":"5_CR48","doi-asserted-by":"crossref","unstructured":"Song, S., Lichtenberg, S.P., Xiao, J.: Sun RGB-D: a RGB-D scene understanding benchmark suite. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"5_CR49","unstructured":"Wang, H., et\u00a0al.: Cagroup3D: class-aware grouping for 3d object detection on point clouds. In: NeurIPS (2022)"},{"key":"5_CR50","unstructured":"Wang, T., Xinge, Z., Pang, J., Lin, D.: Probabilistic and geometric depth: detecting objects in perspective. In: CoRL (2022)"},{"key":"5_CR51","doi-asserted-by":"crossref","unstructured":"Wang, T., Zhu, X., Pang, J., Lin, D.: Fcos3D: fully convolutional one-stage monocular 3D object detection. In: ICCVW (2021)","DOI":"10.1109\/ICCVW54120.2021.00107"},{"key":"5_CR52","doi-asserted-by":"crossref","unstructured":"Wang, Y., Chen, X., Cao, L., Huang, W., Sun, F., Wang, Y.: Multimodal token fusion for vision transformers. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01187"},{"key":"5_CR53","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: Detecting everything in the open world: towards universal object detection. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01100"},{"key":"5_CR54","unstructured":"Wang, Z., Li, Y., Chen, X., Zhao, H., Wang, S.: Uni3DETR: unified 3D detection transformer. In: NeurIPS (2023)"},{"key":"5_CR55","doi-asserted-by":"crossref","unstructured":"Xue, L., et al.: ULIP: learning a unified representation of language, images, and point clouds for 3D understanding. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00120"},{"key":"5_CR56","doi-asserted-by":"crossref","unstructured":"Yan, Y., Mao, Y., Li, B.: Second: sparsely embedded convolutional detection. Sensors (2018)","DOI":"10.3390\/s18103337"},{"key":"5_CR57","doi-asserted-by":"crossref","unstructured":"Yin, T., Zhou, X., Krahenbuhl, P.: Center-based 3D object detection and tracking. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"5_CR58","doi-asserted-by":"crossref","unstructured":"Zareian, A., Rosa, K.D., Hu, D.H., Chang, S.F.: Open-vocabulary object detection using captions. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01416"},{"key":"5_CR59","doi-asserted-by":"crossref","unstructured":"Zeng, Y., et al.: Clip2: contrastive language-image-point pretraining from real-world point cloud data. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01463"},{"key":"5_CR60","doi-asserted-by":"crossref","unstructured":"Zhai, X., et al.: Lit: zero-shot transfer with locked-image text tuning. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01759"},{"key":"5_CR61","unstructured":"Zhang, H., et al.: Glipv2: unifying localization and vision-language understanding. In: NeurIPS (2022)"},{"key":"5_CR62","doi-asserted-by":"crossref","unstructured":"Zhang, R., et al.: Pointclip: point cloud understanding by clip. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00836"},{"key":"5_CR63","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Lu, J., Zhou, J.: Objects are different: Flexible monocular 3D object detection. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00330"},{"key":"5_CR64","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Sun, B., Yang, H., Huang, Q.: H3DNet: 3D object detection using hybrid geometric primitives. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58610-2_19"},{"key":"5_CR65","doi-asserted-by":"crossref","unstructured":"Zhong, Y., et\u00a0al.: Regionclip: region-based language-image pretraining. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"5_CR66","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 (2022)","DOI":"10.1007\/978-3-031-20077-9_21"},{"key":"5_CR67","unstructured":"Zhu, B., Jiang, Z., Zhou, X., Li, Z., Yu, G.: Class-balanced grouping and sampling for point cloud 3D object detection. arXiv:1908.09492 (2019)"},{"key":"5_CR68","doi-asserted-by":"crossref","unstructured":"Zhu, X., et al.: Pointclip v2: prompting clip and GPT for powerful 3D open-world learning. In: CVPR (2023)","DOI":"10.1109\/ICCV51070.2023.00249"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72970-6_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T20:49:02Z","timestamp":1733086142000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72970-6_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,23]]},"ISBN":["9783031729690","9783031729706"],"references-count":68,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72970-6_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,23]]},"assertion":[{"value":"23 November 2024","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":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}