{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T09:09:04Z","timestamp":1765357744422,"version":"3.40.3"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031781124"},{"type":"electronic","value":"9783031781131"}],"license":[{"start":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T00:00:00Z","timestamp":1733270400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T00:00:00Z","timestamp":1733270400000},"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\/978-3-031-78113-1_17","type":"book-chapter","created":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T17:01:29Z","timestamp":1733245289000},"page":"249-264","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Joint Top-Down and\u00a0Bottom-Up Frameworks for\u00a03D Visual Grounding"],"prefix":"10.1007","author":[{"given":"Yang","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daizong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,4]]},"reference":[{"key":"17_CR1","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":"17_CR2","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":"17_CR3","doi-asserted-by":"crossref","unstructured":"Chen, S., Fang, J., Zhang, Q., Liu, W., Wang, X.: Hierarchical aggregation for 3D instance segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15467\u201315476 (2021)","DOI":"10.1109\/ICCV48922.2021.01518"},{"key":"17_CR4","doi-asserted-by":"crossref","unstructured":"Cheng, B., Sheng, L., Shi, S., Yang, M., Xu, D.: Back-tracing representative points for voting-based 3d object detection in point clouds. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8963\u20138972 (2021)","DOI":"10.1109\/CVPR46437.2021.00885"},{"key":"17_CR5","doi-asserted-by":"crossref","unstructured":"Deng, J., Yang, Z., Chen, T., Zhou, W., Li, H.: TranSVG: end-to-end visual grounding with transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1769\u20131779 (2021)","DOI":"10.1109\/ICCV48922.2021.00179"},{"key":"17_CR6","doi-asserted-by":"crossref","unstructured":"Feng, M., et al.: Free-form description guided 3D visual graph network for object grounding in point cloud. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3722\u20133731 (2021)","DOI":"10.1109\/ICCV48922.2021.00370"},{"key":"17_CR7","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, pp. 2344\u20132352 (2021)","DOI":"10.1145\/3474085.3475397"},{"key":"17_CR8","doi-asserted-by":"crossref","unstructured":"Huang, P.H., Lee, H.H., Chen, H.T., Liu, T.L.: Text-guided graph neural networks for referring 3d instance segmentation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a035, pp. 1610\u20131618 (2021)","DOI":"10.1609\/aaai.v35i2.16253"},{"key":"17_CR9","doi-asserted-by":"crossref","unstructured":"Jiang, L., Zhao, H., Shi, S., Liu, S., Fu, C.W., Jia, J.: Pointgroup: dual-set point grouping for 3D instance segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4867\u20134876 (2020)","DOI":"10.1109\/CVPR42600.2020.00492"},{"key":"17_CR10","unstructured":"Li, M., Sigal, L.: Referring transformer: a one-step approach to multi-task visual grounding. In: Advances in Neural Information Processing Systems, vol. 34, pp. 19652\u201319664 (2021)"},{"key":"17_CR11","doi-asserted-by":"crossref","unstructured":"Li, Q., Han, Z., Wu, X.M.: Deeper insights into graph convolutional networks for semi-supervised learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a032 (2018)","DOI":"10.1609\/aaai.v32i1.11604"},{"key":"17_CR12","unstructured":"Liu, D., Liu, Y., Huang, W., Hu, W.: A survey on text-guided 3D visual grounding: elements, recent advances, and future directions. arXiv preprint arXiv:2406.05785 (2024)"},{"key":"17_CR13","doi-asserted-by":"crossref","unstructured":"Liu, H., Lin, A., Han, X., Yang, L., Yu, Y., Cui, S.: Refer-it-in-RGBD: a bottom-up approach for 3D visual grounding in RGBD images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6032\u20136041 (2021)","DOI":"10.1109\/CVPR46437.2021.00597"},{"key":"17_CR14","doi-asserted-by":"crossref","unstructured":"Liu, Y., Liu, D., Guo, Z., Hu, W.: Cross-task knowledge transfer for semi-supervised joint 3D grounding and captioning. In: Proceedings of the 32st ACM International Conference on Multimedia. ACM (2024)","DOI":"10.1145\/3664647.3680614"},{"key":"17_CR15","doi-asserted-by":"crossref","unstructured":"Liu, Z., Zhang, Z., Cao, Y., Hu, H., Tong, X.: Group-free 3D object detection via transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2949\u20132958 (2021)","DOI":"10.1109\/ICCV48922.2021.00294"},{"key":"17_CR16","unstructured":"Loshchilov, I., Hutter, F.: Fixing weight decay regularization in ADAM (2018)"},{"key":"17_CR17","doi-asserted-by":"crossref","unstructured":"Luo, J., et al.: 3D-SPS: single-stage 3D visual grounding via referred point progressive selection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16454\u201316463 (2022)","DOI":"10.1109\/CVPR52688.2022.01596"},{"key":"17_CR18","doi-asserted-by":"crossref","unstructured":"Misra, I., Girdhar, R., Joulin, A.: An end-to-end transformer model for 3D object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2906\u20132917 (2021)","DOI":"10.1109\/ICCV48922.2021.00290"},{"key":"17_CR19","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: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9277\u20139286 (2019)","DOI":"10.1109\/ICCV.2019.00937"},{"key":"17_CR20","unstructured":"Qi, C.R., Su, H., Mo, K., Guibas, L.J.: Pointnet: deep learning on point sets for 3D classification and segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 652\u2013660 (2017)"},{"key":"17_CR21","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, vol. 30 (2017)"},{"key":"17_CR22","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"17_CR23","doi-asserted-by":"crossref","unstructured":"Radosavovic, I., Kosaraju, R.P., Girshick, R., He, K., Doll\u00e1r, P.: Designing network design spaces. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10428\u201310436 (2020)","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"17_CR24","doi-asserted-by":"crossref","unstructured":"Sadhu, A., Chen, K., Nevatia, R.: Zero-shot grounding of objects from natural language queries. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4694\u20134703 (2019)","DOI":"10.1109\/ICCV.2019.00479"},{"key":"17_CR25","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"17_CR26","doi-asserted-by":"crossref","unstructured":"Vu, T., Kim, K., Luu, T.M., Nguyen, T., Yoo, C.D.: Softgroup for 3D instance segmentation on point clouds. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2708\u20132717 (2022)","DOI":"10.1109\/CVPR52688.2022.00273"},{"issue":"2","key":"17_CR27","doi-asserted-by":"publisher","first-page":"394","DOI":"10.1109\/TPAMI.2018.2797921","volume":"41","author":"L Wang","year":"2018","unstructured":"Wang, L., Li, Y., Huang, J., Lazebnik, S.: Learning two-branch neural networks for image-text matching tasks. IEEE Trans. Pattern Anal. Mach. Intell. 41(2), 394\u2013407 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"17_CR28","doi-asserted-by":"crossref","unstructured":"Wang, P., Wu, Q., Cao, J., Shen, C., Gao, L., Hengel, A.v.d.: Neighbourhood watch: Referring expression comprehension via language-guided graph attention networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1960\u20131968 (2019)","DOI":"10.1109\/CVPR.2019.00206"},{"issue":"5","key":"17_CR29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3326362","volume":"38","author":"Y Wang","year":"2019","unstructured":"Wang, Y., Sun, Y., Liu, Z., Sarma, S.E., Bronstein, M.M., Solomon, J.M.: Dynamic graph CNN for learning on point clouds. ACM Trans. Graph. (tog) 38(5), 1\u201312 (2019)","journal-title":"ACM Trans. Graph. (tog)"},{"key":"17_CR30","doi-asserted-by":"crossref","unstructured":"Yang, A., Miech, A., Sivic, J., Laptev, I., Schmid, C.: TubeDeTR: spatio-temporal video grounding with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16442\u201316453 (2022)","DOI":"10.1109\/CVPR52688.2022.01595"},{"key":"17_CR31","doi-asserted-by":"crossref","unstructured":"Yang, S., Li, G., Yu, Y.: Cross-modal relationship inference for grounding referring expressions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4145\u20134154 (2019)","DOI":"10.1109\/CVPR.2019.00427"},{"key":"17_CR32","doi-asserted-by":"crossref","unstructured":"Yang, Z., Gong, B., Wang, L., Huang, W., Yu, D., Luo, J.: A fast and accurate one-stage approach to visual grounding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4683\u20134693 (2019)","DOI":"10.1109\/ICCV.2019.00478"},{"key":"17_CR33","doi-asserted-by":"crossref","unstructured":"Yang, Z., Zhang, S., Wang, L., Luo, J.: Sat: 2D semantics assisted training for 3D visual grounding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1856\u20131866 (2021)","DOI":"10.1109\/ICCV48922.2021.00187"},{"key":"17_CR34","doi-asserted-by":"crossref","unstructured":"Yuan, Z., et al.: InstanceRefer: cooperative holistic understanding for visual grounding on point clouds through instance multi-level contextual referring. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1791\u20131800 (2021)","DOI":"10.1109\/ICCV48922.2021.00181"},{"key":"17_CR35","doi-asserted-by":"crossref","unstructured":"Zhao, L., Cai, D., Sheng, L., Xu, D.: 3DVG-transformer: relation modeling for visual grounding on point clouds. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2928\u20132937 (2021)","DOI":"10.1109\/ICCV48922.2021.00292"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78113-1_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T17:05:54Z","timestamp":1733245554000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78113-1_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,4]]},"ISBN":["9783031781124","9783031781131"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78113-1_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,4]]},"assertion":[{"value":"4 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kolkata","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","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":"1 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}