{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T16:21:40Z","timestamp":1770394900528,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":31,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819557578","type":"print"},{"value":"9789819557585","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\/978-981-95-5758-5_35","type":"book-chapter","created":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T05:00:19Z","timestamp":1770354019000},"page":"486-500","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Disambiguating Holistic Language for\u00a03D Visual Grounding via\u00a0Neural-Symbolic Reasoning"],"prefix":"10.1007","author":[{"given":"Yunze","family":"Wu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yufan","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fangfang","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingtao","family":"Feng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weisheng","family":"Dong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,2,7]]},"reference":[{"key":"35_CR1","unstructured":"Achiam, J., et\u00a0al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"35_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":"35_CR3","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13154\u201313164 (2023)","DOI":"10.1109\/CVPR52729.2023.01264"},{"key":"35_CR4","doi-asserted-by":"publisher","unstructured":"Chen, D.Z., Chang, A.X., Niesner, M.: ScanRefer: 3D object localization in RGB-D scans using natural language. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, JM. (eds.) European Conference on Computer Vision, pp. 202\u2013221. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58565-5_13","DOI":"10.1007\/978-3-030-58565-5_13"},{"key":"35_CR5","first-page":"5834","volume":"34","author":"S Chen","year":"2021","unstructured":"Chen, S., Guhur, P.L., Schmid, C., Laptev, I.: History aware multimodal transformer for vision-and-language navigation. Adv. Neural. Inf. Process. Syst. 34, 5834\u20135847 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"35_CR6","doi-asserted-by":"crossref","unstructured":"Chen, S., Guhur, P.L., Tapaswi, M., Schmid, C., Laptev, I.: Think global, act local: dual-scale graph transformer for vision-and-language navigation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16537\u201316547 (2022)","DOI":"10.1109\/CVPR52688.2022.01604"},{"key":"35_CR7","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":"35_CR8","doi-asserted-by":"crossref","unstructured":"Feng, C., Hsu, J., Liu, W., Wu, J.: Naturally supervised 3d visual grounding with language-regularized concept learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13269\u201313278 (2024)","DOI":"10.1109\/CVPR52733.2024.01260"},{"key":"35_CR9","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":"35_CR10","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"35_CR11","doi-asserted-by":"crossref","unstructured":"Hsu, J., Mao, J., Wu, J.: NS3D: neuro-symbolic grounding of 3D objects and relations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2614\u20132623 (2023)","DOI":"10.1109\/CVPR52729.2023.00257"},{"key":"35_CR12","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":"35_CR13","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: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) European Conference on Computer Vision, pp. 417\u2013433. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20059-5_24","DOI":"10.1007\/978-3-031-20059-5_24"},{"key":"35_CR14","unstructured":"Jocher, G., Ultralytics: Ultralytics YOLOv8 (2023). https:\/\/github.com\/ultralytics\/ultralytics"},{"key":"35_CR15","doi-asserted-by":"crossref","unstructured":"Kamath, A., Singh, M., LeCun, Y., Synnaeve, G., Misra, I., Carion, N.: MDETR -modulated detection for end-to-end multi-modal understanding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1780\u20131790 (2021)","DOI":"10.1109\/ICCV48922.2021.00180"},{"issue":"1","key":"35_CR16","doi-asserted-by":"publisher","first-page":"e13315","DOI":"10.1049\/ipr2.13315","volume":"19","author":"Q Lei","year":"2025","unstructured":"Lei, Q., Sun, S., Song, X., Song, H., Feng, M., Wu, C.: Bootstrapping vision-language transformer for monocular 3d visual grounding. IET Image Proc. 19(1), e13315 (2025)","journal-title":"IET Image Proc."},{"key":"35_CR17","unstructured":"Liu, Y., et al.: RoBERTa: a robustly optimized BERT pretraining approach. arXiv preprint arXiv:1907.11692 (2019)"},{"key":"35_CR18","unstructured":"Mao, J., Gan, C., Kohli, P., Tenenbaum, J.B., Wu, J.: The neuro-symbolic concept learner: interpreting scenes, words, and sentences from natural supervision. arXiv preprint arXiv:1904.12584 (2019)"},{"key":"35_CR19","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"},{"issue":"2","key":"35_CR20","doi-asserted-by":"publisher","first-page":"1181","DOI":"10.1109\/TPAMI.2023.3328185","volume":"46","author":"F Shi","year":"2023","unstructured":"Shi, F., Gao, R., Huang, W., Wang, L.: Dynamic MDETR: a dynamic multimodal transformer decoder for visual grounding. IEEE Trans. Pattern Anal. Mach. Intell. 46(2), 1181\u20131198 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"35_CR21","unstructured":"Shijie Sun, H.W., Huang, Y.: Semantic-aware 3d visual grounding: a dataset for cross-modal visual grounding (2025). https:\/\/github.com\/shijieS"},{"key":"35_CR22","doi-asserted-by":"crossref","unstructured":"Wang, H., Liang, W., Van Gool, L., Wang, W.: DREAMWALKER: mental planning for continuous vision-language navigation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10873\u201310883 (2023)","DOI":"10.1109\/ICCV51070.2023.00998"},{"key":"35_CR23","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\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19231\u201319242 (2023)","DOI":"10.1109\/CVPR52729.2023.01843"},{"key":"35_CR24","first-page":"49542","volume":"36","author":"L Yang","year":"2023","unstructured":"Yang, L., et al.: Exploiting contextual objects and relations for 3D visual grounding. Adv. Neural. Inf. Process. Syst. 36, 49542\u201349554 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"35_CR25","doi-asserted-by":"crossref","unstructured":"Yang, L., Kang, B., Huang, Z., Xu, X., Feng, J., Zhao, H.: Depth anything: unleashing the power of large-scale unlabeled data. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10371\u201310381 (2024)","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"35_CR26","doi-asserted-by":"crossref","unstructured":"Yang, S., Li, G., Yu, Y.: Dynamic graph attention for referring expression comprehension. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4644\u20134653 (2019)","DOI":"10.1109\/ICCV.2019.00474"},{"issue":"8","key":"35_CR27","doi-asserted-by":"publisher","first-page":"2765","DOI":"10.1109\/TPAMI.2020.2973983","volume":"43","author":"S Yang","year":"2020","unstructured":"Yang, S., Li, G., Yu, Y.: Relationship-embedded representation learning for grounding referring expressions. IEEE Trans. Pattern Anal. Mach. Intell. 43(8), 2765\u20132779 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"35_CR28","doi-asserted-by":"crossref","unstructured":"Yang, X., Feng, F., Ji, W., Wang, M., Chua, T.S.: Deconfounded video moment retrieval with causal intervention. In: Proceedings of the 44th international ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 1\u201310 (2021)","DOI":"10.1145\/3404835.3462823"},{"key":"35_CR29","doi-asserted-by":"crossref","unstructured":"Zhan, Y., Yuan, Y., Xiong, Z.: Mono3DVG: 3D visual grounding in monocular images. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 6988\u20136996 (2024)","DOI":"10.1609\/aaai.v38i7.28525"},{"key":"35_CR30","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"},{"key":"35_CR31","doi-asserted-by":"publisher","unstructured":"Zhu, C., et al.: SeqTR: a simple yet universal network for visual grounding. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) European Conference on Computer Vision. LNCS, pp. 598\u2013615. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19833-5_35","DOI":"10.1007\/978-3-031-19833-5_35"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-5758-5_35","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T05:00:25Z","timestamp":1770354025000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-5758-5_35"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819557578","9789819557585"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-5758-5_35","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":"7 February 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shanghai","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2025.prcv.cn\/index.asp","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}