{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T23:18:39Z","timestamp":1743031119048,"version":"3.40.3"},"publisher-location":"Cham","reference-count":30,"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_28","type":"book-chapter","created":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T17:02:05Z","timestamp":1733245325000},"page":"427-442","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing 3D Referential Grounding by\u00a0Learning Coarse Spatial Relationships"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8201-2253","authenticated-orcid":false,"given":"Soham","family":"Joshi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1667-9623","authenticated-orcid":false,"given":"Aditay","family":"Tripathi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7813-877X","authenticated-orcid":false,"given":"Viswanath","family":"Gopalakrishnan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6946-9152","authenticated-orcid":false,"given":"Anirban","family":"Chakraborty","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,4]]},"reference":[{"key":"28_CR1","doi-asserted-by":"crossref","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: 16th European Conference on Computer Vision (ECCV) (2020)","DOI":"10.1007\/978-3-030-58452-8_25"},{"key":"28_CR2","doi-asserted-by":"crossref","unstructured":"Chen, D., Chang, A., Nie\u00dfner, M.: ScanRefer: 3D object localization in RGB-D scans using natural language. In: 16th European Conference on Computer Vision (ECCV) (2020)","DOI":"10.1007\/978-3-030-58565-5_13"},{"key":"28_CR3","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16464\u201316473 (2022)","DOI":"10.1109\/CVPR52688.2022.01597"},{"key":"28_CR4","doi-asserted-by":"crossref","unstructured":"Zhao, L., Cai, D., Sheng, L., Xu, D.: 3DVG-transformer: relation modeling for visual grounding on point clouds. In: ICCV, pp. 2928\u20132937 (2021)","DOI":"10.1109\/ICCV48922.2021.00292"},{"key":"28_CR5","doi-asserted-by":"crossref","unstructured":"Kamath, A., Singh, M., LeCun, Y., Misra, I., Synnaeve, G., Carion, N.: MDETR - modulated detection for end-to-end multi-modal understanding. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 1760\u20131770 (2021). https:\/\/api.semanticscholar.org\/CorpusID:233393962","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"28_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-End object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"28_CR7","doi-asserted-by":"crossref","unstructured":"Dai, A., Chang, A., Savva, M., Halber, M., Funkhouser, T., Nie\u00dfner, M.: ScanNet: richly-annotated 3D reconstructions of indoor scenes. In: Proceedings Computer Vision and Pattern Recognition (CVPR). IEEE (2017)","DOI":"10.1109\/CVPR.2017.261"},{"key":"28_CR8","doi-asserted-by":"publisher","unstructured":"Jin, X., Han, J.: K-means clustering. In: Encyclopedia Of Machine Learning, pp. 563\u2013564 (2010). https:\/\/doi.org\/10.1007\/978-0-387-30164-8_425","DOI":"10.1007\/978-0-387-30164-8_425"},{"key":"28_CR9","doi-asserted-by":"crossref","unstructured":"Yuan, Z., Yan, X., Liao, Y., Zhang, R., Li, Z., Cui, S.: 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":"28_CR10","doi-asserted-by":"crossref","unstructured":"Liu, Z., Zhang, Z., Cao, Y., Hu, H., Tong, X.: Group-free 3D object detection via transformers. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 2929\u20132938 (2021)","DOI":"10.1109\/ICCV48922.2021.00294"},{"key":"28_CR11","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":"28_CR12","unstructured":"Chen, J., Luo, W., Wei, X., Ma, L., Zhang, W.: HAM: hierarchical attention model with high performance for 3D visual grounding (2022)"},{"key":"28_CR13","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.01843"},{"key":"28_CR14","doi-asserted-by":"crossref","unstructured":"Huang, S., Chen, Y., Jia, J., Wang, L.: Multi-view transformer for 3D visual grounding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15524\u201315533 (2022)","DOI":"10.1109\/CVPR52688.2022.01508"},{"key":"28_CR15","doi-asserted-by":"crossref","unstructured":"Huang, P., Lee, H., Chen, H., Liu, T.: Text-guided graph neural networks for referring 3D instance segmentation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 1610\u20131618 (2021). https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/16253","DOI":"10.1609\/aaai.v35i2.16253"},{"key":"28_CR16","doi-asserted-by":"publisher","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). https:\/\/doi.org\/10.1145\/3474085.3475397","DOI":"10.1145\/3474085.3475397"},{"key":"28_CR17","doi-asserted-by":"crossref","unstructured":"Yang, Z., Zhang, S., Wang, L., Luo, J.: SAT: 2D semantics assisted training for 3D visual grounding. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00187"},{"key":"28_CR18","unstructured":"Bao, H., Dong, L., Piao, S., Wei, F.: BERT pre-training of image transformers, BEiT (2022)"},{"key":"28_CR19","doi-asserted-by":"crossref","unstructured":"Dai, Z., Cai, B., Lin, Y., Chen, J.: UP-DETR: unsupervised pre-training for object detection with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1601\u20131610 (2021)","DOI":"10.1109\/CVPR46437.2021.00165"},{"key":"28_CR20","doi-asserted-by":"crossref","unstructured":"Lu, Z., Pei, Y., Wang, G., Yang, Y., Wang, Z., Shen, H.: ScanERU: interactive 3D visual grounding based on embodied reference understanding (2023)","DOI":"10.1609\/aaai.v38i4.28186"},{"key":"28_CR21","doi-asserted-by":"crossref","unstructured":"Rao, J., Bian, H., Xu, X., Chen, J.: Autonomous visual navigation system based on a single camera for floor-sweeping robot. Appl. Sci. 13 (2023). https:\/\/www.mdpi.com\/2076-3417\/13\/3\/1562","DOI":"10.3390\/app13031562"},{"key":"28_CR22","doi-asserted-by":"crossref","unstructured":"Xia, F., Zamir, A.R., He, Z., Sax, A., Malik, J., Savarese, S.: Gibson env: real-world perception for embodied agents. In: 2018 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00945"},{"key":"28_CR23","unstructured":"Szot, A., et al.: Habitat 2.0: training home assistants to rearrange their habitat. In: Advances in Neural Information Processing Systems (NeurIPS) (2021)"},{"key":"28_CR24","unstructured":"Qi, C., Yi, L., Su, H., Guibas, L.: PointNet++: deep hierarchical feature learning on point sets in a metric space. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, pp. 5105\u20135114 (2017)"},{"key":"28_CR25","doi-asserted-by":"crossref","unstructured":"Yin, P., Xu, L., Ji, J., Scherer, S., Choset, H.: 3D segmentation learning from sparse annotations and hierarchical descriptors (2021)","DOI":"10.1109\/LRA.2021.3088796"},{"key":"28_CR26","doi-asserted-by":"crossref","unstructured":"Behley, J., et al.: SemanticKITTI: a dataset for semantic scene understanding of LiDAR sequences. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00939"},{"key":"28_CR27","unstructured":"Liu, Y., et al.: A robustly optimized BERT pretraining approach, RoBERTa (2019)"},{"key":"28_CR28","doi-asserted-by":"crossref","unstructured":"Liu, S., et al.: Dual query detection transformer for phrase extraction and grounding, DQ-DETR (2022)","DOI":"10.1609\/aaai.v37i2.25261"},{"key":"28_CR29","doi-asserted-by":"publisher","unstructured":"Jain, A., Gkanatsios, N., Mediratta, I., Fragkiadaki, K.: Bottom up top down detection transformers for language grounding in images and point clouds. In: Computer Vision \u2013 ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part XXXVI, pp. 417\u2013433 (2022). https:\/\/doi.org\/10.1007\/978-3-031-20059-5_24","DOI":"10.1007\/978-3-031-20059-5_24"},{"key":"28_CR30","unstructured":"Chen, S., Guhur, P., Tapaswi, M., Schmid, C., Laptev, I.: Language conditioned spatial relation reasoning for 3D object grounding. In: NeurIPS (2022)"}],"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_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T17:07:36Z","timestamp":1733245656000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78113-1_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,4]]},"ISBN":["9783031781124","9783031781131"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78113-1_28","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"}}]}}