{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:12:02Z","timestamp":1778080322675,"version":"3.51.4"},"publisher-location":"Cham","reference-count":72,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031727832","type":"print"},{"value":"9783031727849","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"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\/978-3-031-72784-9_11","type":"book-chapter","created":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T07:01:50Z","timestamp":1727593310000},"page":"188-206","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":27,"title":["Unifying 3D Vision-Language Understanding via\u00a0Promptable Queries"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1556-0791","authenticated-orcid":false,"given":"Ziyu","family":"Zhu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9965-4745","authenticated-orcid":false,"given":"Zhuofan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5609-3822","authenticated-orcid":false,"given":"Xiaojian","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7737-4287","authenticated-orcid":false,"given":"Xuesong","family":"Niu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8176-0241","authenticated-orcid":false,"given":"Yixin","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4968-3290","authenticated-orcid":false,"given":"Baoxiong","family":"Jia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9970-1023","authenticated-orcid":false,"given":"Zhidong","family":"Deng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1524-7148","authenticated-orcid":false,"given":"Siyuan","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1185-5365","authenticated-orcid":false,"given":"Qing","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,30]]},"reference":[{"key":"11_CR1","doi-asserted-by":"crossref","unstructured":"Abdelreheem, A., Olszewski, K., Lee, H.Y., Wonka, P., Achlioptas, P.: ScanEnts3D: exploiting phrase-to-3D-object correspondences for improved visio-linguistic models in 3D scenes. In: Proceedings of Winter Conference on Applications of Computer Vision (WACV), pp. 3524\u20133534 (2024)","DOI":"10.1109\/WACV57701.2024.00349"},{"key":"11_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"422","DOI":"10.1007\/978-3-030-58452-8_25","volume-title":"Computer Vision \u2013 ECCV 2020","author":"P Achlioptas","year":"2020","unstructured":"Achlioptas, P., Abdelreheem, A., Xia, F., Elhoseiny, M., Guibas, L.: ReferIt3D: neural listeners for fine-grained 3D object identification in real-world scenes. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 422\u2013440. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_25"},{"key":"11_CR3","doi-asserted-by":"crossref","unstructured":"Azuma, D., Miyanishi, T., Kurita, S., Kawanabe, M.: ScanQA: 3D question answering for spatial scene understanding. In: The IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01854"},{"key":"11_CR4","unstructured":"Brohan, A., et\u00a0al.: Do as I can, not as I say: grounding language in robotic affordances. In: Conference on Robot Learning (CoRL) (2022)"},{"key":"11_CR5","doi-asserted-by":"crossref","unstructured":"Cai, D., Zhao, L., Zhang, J., Sheng, L., Xu, D.: 3DJCG: a unified framework for joint dense captioning and visual grounding on 3D point clouds. In: The IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01597"},{"key":"11_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"202","DOI":"10.1007\/978-3-030-58565-5_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"DZ Chen","year":"2020","unstructured":"Chen, D.Z., Chang, A.X., Nie\u00dfner, M.: ScanRefer: 3D object localization in RGB-D scans using natural language. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12365, pp. 202\u2013221. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58565-5_13"},{"key":"11_CR7","unstructured":"Chen, S., Guhur, P.L., Tapaswi, M., Schmid, C., Laptev, I.: Language conditioned spatial relation reasoning for 3D object grounding. In: Advances in Neural Information Processing Systems (NeurIPS) (2022)"},{"key":"11_CR8","doi-asserted-by":"crossref","unstructured":"Chen, S., et al.: LL3DA: visual interactive instruction tuning for Omni-3D understanding reasoning and planning. In: The IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2024)","DOI":"10.1109\/CVPR52733.2024.02496"},{"key":"11_CR9","doi-asserted-by":"crossref","unstructured":"Chen, Z., Gholami, A., Nie\u00dfner, M., Chang, A.X.: Scan2Cap: context-aware dense captioning in RGB-D scans. In: The IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.00321"},{"key":"11_CR10","doi-asserted-by":"crossref","unstructured":"Chen, Z., Hu, R., Chen, X., Nie\u00dfner, M., Chang, A.X.: Unit3D: a unified transformer for 3D dense captioning and visual grounding. In: International Conference on Computer Vision (ICCV), pp. 18109\u201318119 (2023)","DOI":"10.1109\/ICCV51070.2023.01660"},{"key":"11_CR11","doi-asserted-by":"crossref","unstructured":"Cheng, B., Misra, I., Schwing, A.G., Kirillov, A., Girdhar, R.: Masked-attention mask transformer for universal image segmentation. In: The IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"11_CR12","unstructured":"Cho, J., Lei, J., Tan, H., Bansal, M.: Unifying vision-and-language tasks via text generation. In: International Conference on Machine Learning (ICML) (2021)"},{"key":"11_CR13","doi-asserted-by":"crossref","unstructured":"Ding, H., Liu, C., Wang, S., Jiang, X.: Vision-language transformer and query generation for referring segmentation. In: International Conference on Computer Vision (ICCV), pp. 16321\u201316330 (2021)","DOI":"10.1109\/ICCV48922.2021.01601"},{"key":"11_CR14","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: The IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7010\u20137019 (2023)","DOI":"10.1109\/CVPR52729.2023.00677"},{"key":"11_CR15","unstructured":"Dong, B., Zeng, F., Wang, T., Zhang, X., Wei, Y.: SOLQ: segmenting objects by learning queries. In: Advances in Neural Information Processing Systems (NeurIPS), vol. 34, pp. 21898\u201321909 (2021)"},{"issue":"2","key":"11_CR16","doi-asserted-by":"publisher","first-page":"230","DOI":"10.1109\/TETCI.2022.3141105","volume":"6","author":"J Duan","year":"2022","unstructured":"Duan, J., Yu, S., Tan, H.L., Zhu, H., Tan, C.: A survey of embodied AI: from simulators to research tasks. IEEE Trans. Emerging Top. Comput. Intell. 6(2), 230\u2013244 (2022)","journal-title":"IEEE Trans. Emerging Top. Comput. Intell."},{"key":"11_CR17","doi-asserted-by":"crossref","unstructured":"Fang, Y., et al.: Instances as queries. In: International Conference on Computer Vision (ICCV), pp. 6910\u20136919 (2021)","DOI":"10.1109\/ICCV48922.2021.00683"},{"key":"11_CR18","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1023\/B:VISI.0000022288.19776.77","volume":"59","author":"PF Felzenszwalb","year":"2004","unstructured":"Felzenszwalb, P.F., Huttenlocher, D.P.: Efficient graph-based image segmentation. Int. J. Comput. Vis. (IJCV) 59, 167\u2013181 (2004)","journal-title":"Int. J. Comput. Vis. (IJCV)"},{"key":"11_CR19","doi-asserted-by":"publisher","unstructured":"Ghiasi, G., Gu, X., Cui, Y., Lin, T.Y.: Scaling open-vocabulary image segmentation with image-level labels. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13696, pp. 540\u2013557. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20059-5_31","DOI":"10.1007\/978-3-031-20059-5_31"},{"key":"11_CR20","unstructured":"Guo, J., Ma, X., Fan, Y., Liu, H., Li, Q.: Semantic Gaussians: open-vocabulary scene understanding with 3D Gaussian splatting. arXiv preprint arXiv:2403.15624 (2024)"},{"key":"11_CR21","doi-asserted-by":"crossref","unstructured":"Guo, Z., et al.: ViewRefer: grasp the multi-view knowledge for 3D visual grounding. In: International Conference on Computer Vision (ICCV), pp. 15372\u201315383 (2023)","DOI":"10.1109\/ICCV51070.2023.01410"},{"key":"11_CR22","unstructured":"Ha, H., Song, S.: Semantic abstraction: open-world 3D scene understanding from 2D vision-language models. In: Conference on Robot Learning (CoRL) (2022)"},{"key":"11_CR23","doi-asserted-by":"crossref","unstructured":"He, D., et al.: TransRefer3D: entity-and-relation aware transformer for fine-grained 3D visual grounding. In: Proceedings of the 29th ACM International Conference on Multimedia (2021)","DOI":"10.1145\/3474085.3475397"},{"key":"11_CR24","doi-asserted-by":"crossref","unstructured":"He, J., Li, P., Geng, Y., Xie, X.: FastInst: a simple query-based model for real-time instance segmentation. In: The IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 23663\u201323672 (2023)","DOI":"10.1109\/CVPR52729.2023.02266"},{"key":"11_CR25","unstructured":"Hong, Y., et al.: 3D-LLM: injecting the 3D world into large language models. In: Advances in Neural Information Processing Systems (NeurIPS), vol. 36, pp. 20482\u201320494 (2023)"},{"key":"11_CR26","unstructured":"Hu, J., et al.: ISTR: end-to-end instance segmentation with transformers. arXiv preprint arXiv:2105.00637 (2021)"},{"key":"11_CR27","unstructured":"Huang, J., et al.: An embodied generalist agent in 3D world. In: International Conference on Machine Learning (ICML) (2024)"},{"key":"11_CR28","doi-asserted-by":"crossref","unstructured":"Huang, S., Chen, Y., Jia, J., Wang, L.: Multi-view transformer for 3D visual grounding. In: The IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01508"},{"key":"11_CR29","unstructured":"Huang, W., Abbeel, P., Pathak, D., Mordatch, I.: Language models as zero-shot planners: extracting actionable knowledge for embodied agents. In: International Conference on Machine Learning (ICML), pp. 9118\u20139147. PMLR (2022)"},{"key":"11_CR30","unstructured":"Jaegle, A., et\u00a0al.: Perceiver IO: a general architecture for structured inputs & outputs. arXiv preprint arXiv:2107.14795 (2021)"},{"key":"11_CR31","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"417","DOI":"10.1007\/978-3-031-20059-5_24","volume-title":"ECCV 2022","author":"A Jain","year":"2022","unstructured":"Jain, A., Gkanatsios, N., Mediratta, I., Fragkiadaki, K.: Bottom up top down detection transformers for language grounding in images and point clouds. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13696, pp. 417\u2013433. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20059-5_24"},{"key":"11_CR32","doi-asserted-by":"crossref","unstructured":"Jia, B., et al.: SceneVerse: scaling 3D vision-language learning for grounded scene understanding. arXiv preprint arXiv:2401.09340 (2024)","DOI":"10.1007\/978-3-031-72673-6_16"},{"key":"11_CR33","doi-asserted-by":"crossref","unstructured":"Kerr, J., Kim, C.M., Goldberg, K., Kanazawa, A., Tancik, M.: LERF: language embedded radiance fields. In: International Conference on Computer Vision (ICCV), pp. 19729\u201319739 (2023)","DOI":"10.1109\/ICCV51070.2023.01807"},{"key":"11_CR34","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et\u00a0al.: Segment anything. In: International Conference on Computer Vision (ICCV), pp. 4015\u20134026 (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"11_CR35","unstructured":"Li, B., Weinberger, K.Q., Belongie, S., Koltun, V., Ranftl, R.: Language-driven semantic segmentation (2022)"},{"key":"11_CR36","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597 (2023)"},{"key":"11_CR37","doi-asserted-by":"crossref","unstructured":"Liang, F., et al.: Open-vocabulary semantic segmentation with mask-adapted CLIP. In: The IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7061\u20137070 (2023)","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"11_CR38","doi-asserted-by":"crossref","unstructured":"Lin, Z., Zhang, Z., Chen, L.Z., Cheng, M.M., Lu, S.P.: Interactive image segmentation with first click attention. In: International Conference on Computer Vision (ICCV), pp. 13339\u201313348 (2020)","DOI":"10.1109\/CVPR42600.2020.01335"},{"key":"11_CR39","doi-asserted-by":"crossref","unstructured":"Liu, Q., Xu, Z., Bertasius, G., Niethammer, M.: SimpleClick: interactive image segmentation with simple vision transformers. In: International Conference on Computer Vision (ICCV), pp. 22290\u201322300 (2023)","DOI":"10.1109\/ICCV51070.2023.02037"},{"key":"11_CR40","doi-asserted-by":"crossref","unstructured":"Luo, J., et al.: 3D-SPS: single-stage 3D visual grounding via referred point progressive selection. In: The IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01596"},{"key":"11_CR41","unstructured":"Ma, X., et al.: SQA3D: situated question answering in 3D scenes. In: International Conference on Learning Representations (ICLR) (2023)"},{"key":"11_CR42","unstructured":"Majumdar, A., et\u00a0al.: Where are we in the search for an artificial visual cortex for embodied intelligence? arXiv preprint arXiv:2303.18240 (2023)"},{"key":"11_CR43","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"728","DOI":"10.1007\/978-3-031-20080-9_42","volume-title":"ECCV 2022","author":"M Minderer","year":"2022","unstructured":"Minderer, M., et al.: Simple open-vocabulary object detection. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13670, pp. 728\u2013755. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20080-9_42"},{"key":"11_CR44","doi-asserted-by":"crossref","unstructured":"Padmakumar, A., et al.: TEACh: task-driven embodied agents that chat. In: AAAI Conference on Artificial Intelligence (AAAI) (2022)","DOI":"10.1609\/aaai.v36i2.20097"},{"key":"11_CR45","doi-asserted-by":"crossref","unstructured":"Peng, S., et\u00a0al.: OpenScene: 3D scene understanding with open vocabularies. In: The IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 815\u2013824 (2023)","DOI":"10.1109\/CVPR52729.2023.00085"},{"key":"11_CR46","unstructured":"Qi, C.R., Su, H., Mo, K., Guibas, L.J.: PointNet: deep learning on point sets for 3D classification and segmentation. In: The IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 652\u2013660 (2017)"},{"key":"11_CR47","unstructured":"Qi, C.R., Yi, L., Su, H., Guibas, L.J.: PointNet++: deep hierarchical feature learning on point sets in a metric space. In: Advances in Neural Information Processing Systems (NeurIPS) (2017)"},{"key":"11_CR48","doi-asserted-by":"crossref","unstructured":"Qin, J., et\u00a0al.: FreeSeg: unified, universal and open-vocabulary image segmentation. In: The IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 19446\u201319455 (2023)","DOI":"10.1109\/CVPR52729.2023.01863"},{"key":"11_CR49","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning (ICML), pp. 8748\u20138763. PMLR (2021)"},{"issue":"1","key":"11_CR50","first-page":"5485","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21(1), 5485\u20135551 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"11_CR51","unstructured":"Rana, K., Haviland, J., Garg, S., Abou-Chakra, J., Reid, I., Suenderhauf, N.: SayPlan: grounding large language models using 3D scene graphs for scalable task planning. In: 7th Annual Conference on Robot Learning (2023)"},{"key":"11_CR52","doi-asserted-by":"crossref","unstructured":"Rozenberszki, D., Litany, O., Dai, A.: Language-grounded indoor 3D semantic segmentation in the wild. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13693, pp. 125\u2013141. Springer, Cham (2022)","DOI":"10.1007\/978-3-031-19827-4_8"},{"key":"11_CR53","doi-asserted-by":"crossref","unstructured":"Savva, M., et\u00a0al.: Habitat: a platform for embodied AI research. In: The IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9339\u20139347 (2019)","DOI":"10.1109\/ICCV.2019.00943"},{"key":"11_CR54","doi-asserted-by":"crossref","unstructured":"Schult, J., Engelmann, F., Hermans, A., Litany, O., Tang, S., Leibe, B.: Mask3D: mask transformer for 3D semantic instance segmentation. In: International Conference on Robotics and Automation (ICRA), pp. 8216\u20138223. IEEE (2023)","DOI":"10.1109\/ICRA48891.2023.10160590"},{"key":"11_CR55","unstructured":"Straub, J., et\u00a0al.: The replica dataset: a digital replica of indoor spaces. arXiv preprint arXiv:1906.05797 (2019)"},{"key":"11_CR56","unstructured":"Takmaz, A., Fedele, E., Sumner, R.W., Pollefeys, M., Tombari, F., Engelmann, F.: OpenMask3D: open-vocabulary 3D instance segmentation. In: Advances in Neural Information Processing Systems (NeurIPS) (2023)"},{"key":"11_CR57","doi-asserted-by":"crossref","unstructured":"Wu, J., Jiang, Y., Sun, P., Yuan, Z., Luo, P.: Language as queries for referring video object segmentation. In: The IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4974\u20134984 (2022)","DOI":"10.1109\/CVPR52688.2022.00492"},{"key":"11_CR58","doi-asserted-by":"crossref","unstructured":"Wu, Y., Cheng, X., Zhang, R., Cheng, Z., Zhang, J.: EDA: explicit text-decoupling and dense alignment for 3D visual grounding. In: The IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 19231\u201319242 (2023)","DOI":"10.1109\/CVPR52729.2023.01843"},{"key":"11_CR59","doi-asserted-by":"crossref","unstructured":"Xu, J., et al.: Learning open-vocabulary semantic segmentation models from natural language supervision. In: The IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2935\u20132944 (2023)","DOI":"10.1109\/CVPR52729.2023.00287"},{"key":"11_CR60","doi-asserted-by":"crossref","unstructured":"Xu, X., Xiong, T., Ding, Z., Tu, Z.: MasQCLIP for open-vocabulary universal image segmentation. In: International Conference on Computer Vision (ICCV), pp. 887\u2013898 (2023)","DOI":"10.1109\/ICCV51070.2023.00088"},{"key":"11_CR61","doi-asserted-by":"crossref","unstructured":"Yang, Z., Jiang, L., Sun, Y., Schiele, B., Jia, J.: A unified query-based paradigm for point cloud understanding. In: The IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8541\u20138551 (2022)","DOI":"10.1109\/CVPR52688.2022.00835"},{"key":"11_CR62","doi-asserted-by":"crossref","unstructured":"Yang, Z., Zhang, S., Wang, L., Luo, J.: SAT: 2D semantics assisted training for 3D visual grounding. In: International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00187"},{"key":"11_CR63","unstructured":"Ye, S., Chen, D., Han, S., Liao, J.: 3D question answering. IEEE Trans. Vis. Comput. Graph. (2022)"},{"key":"11_CR64","doi-asserted-by":"crossref","unstructured":"Zareian, A., Rosa, K.D., Hu, D.H., Chang, S.F.: Open-vocabulary object detection using captions. In: The IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 14393\u201314402 (2021)","DOI":"10.1109\/CVPR46437.2021.01416"},{"key":"11_CR65","doi-asserted-by":"crossref","unstructured":"Zhang, T., He, S., Tao, D., Chen, B., Wang, Z., Xia, S.T.: Vision-language pre-training with object contrastive learning for 3D scene understanding. arXiv preprint arXiv:2305.10714 (2023)","DOI":"10.1609\/aaai.v38i7.28559"},{"key":"11_CR66","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Gong, Z., Chang, A.X.: Multi3DRefer: grounding text description to multiple 3D objects. In: International Conference on Computer Vision (ICCV), pp. 15225\u201315236 (2023)","DOI":"10.1109\/ICCV51070.2023.01397"},{"key":"11_CR67","doi-asserted-by":"crossref","unstructured":"Zhao, L., Cai, D., Sheng, L., Xu, D.: 3DVG-transformer: relation modeling for visual grounding on point clouds. In: International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00292"},{"key":"11_CR68","doi-asserted-by":"crossref","unstructured":"Zhao, L., et al.: Towards explainable 3D grounded visual question answering: a new benchmark and strong baseline. IEEE Trans. Circuits Syst. Video Technol. (2022)","DOI":"10.1109\/TCSVT.2022.3229081"},{"key":"11_CR69","doi-asserted-by":"crossref","unstructured":"Zhong, Y., et\u00a0al.: RegionCLIP: region-based language-image pretraining. In: The IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 16793\u201316803 (2022)","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"11_CR70","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: deformable transformers for end-to-end object detection. In: International Conference on Learning Representations (ICLR) (2020)"},{"key":"11_CR71","doi-asserted-by":"crossref","unstructured":"Zhu, Z., Ma, X., Chen, Y., Deng, Z., Huang, S., Li, Q.: 3D-VisTA: pre-trained transformer for 3D vision and text alignment. In: International Conference on Computer Vision (ICCV), pp. 2911\u20132921 (2023)","DOI":"10.1109\/ICCV51070.2023.00272"},{"key":"11_CR72","doi-asserted-by":"crossref","unstructured":"Zou, X., et\u00a0al.: Generalized decoding for pixel, image, and language. In: The IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 15116\u201315127 (2023)","DOI":"10.1109\/CVPR52729.2023.01451"}],"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\/978-3-031-72784-9_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T21:22:35Z","timestamp":1732828955000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72784-9_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,30]]},"ISBN":["9783031727832","9783031727849"],"references-count":72,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72784-9_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,30]]},"assertion":[{"value":"30 September 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"}}]}}