{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T00:55:01Z","timestamp":1767315301612,"version":"3.48.0"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032101846","type":"print"},{"value":"9783032101853","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\/978-3-032-10185-3_13","type":"book-chapter","created":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T00:51:20Z","timestamp":1767315080000},"page":"156-167","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Deep Multimodal Fusion for\u00a02D-3D Vineyard Scene Understanding"],"prefix":"10.1007","author":[{"given":"Mirko","family":"Usuelli","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cristian","family":"Sbrolli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alessio","family":"Braccini","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matteo","family":"Frosi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matteo","family":"Matteucci","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,2]]},"reference":[{"key":"13_CR1","unstructured":"Caron, M., Misra, I., Mairal, J., Goyal, P., Bojanowski, P., Joulin, A.: Unsupervised learning of visual features by contrasting cluster assignments. In: Advances in Neural Information Processing Systems (NeurIPS), vol.\u00a033, pp. 9912\u20139924 (2020)"},{"key":"13_CR2","doi-asserted-by":"crossref","unstructured":"Chen, R., et al.: Clip2scene: towards label-efficient 3d scene understanding by clip (2023)","DOI":"10.1109\/CVPR52729.2023.00678"},{"key":"13_CR3","unstructured":"Chen, R., et al.: Zero-shot point cloud segmentation by transferring geometric primitives. arXiv preprint arXiv:2210.09923 (2022)"},{"key":"13_CR4","unstructured":"Chen, R., et al.: Towards 3d scene understanding by referring synthetic models. arXiv preprint arXiv:2203.10546 (2022)"},{"issue":"10","key":"13_CR5","doi-asserted-by":"publisher","first-page":"2364","DOI":"10.1007\/s11263-022-01650-4","volume":"130","author":"A Cheraghian","year":"2022","unstructured":"Cheraghian, A., Rahman, S., Chowdhury, T.F., Campbell, D., Petersson, L.: Zero-shot learning on 3d point cloud objects and beyond. Int. J. Comput. Vision 130(10), 2364\u20132384 (2022)","journal-title":"Int. J. Comput. Vision"},{"key":"13_CR6","unstructured":"Grill, J.B., et\u00a0al.: Bootstrap your own latent: a new approach to self-supervised learning. In: Advances in Neural Information Processing Systems (NeurIPS), vol.\u00a033, pp. 21271\u201321284 (2020)"},{"key":"13_CR7","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511811685","volume-title":"Multiple View Geometry in Computer Vision","author":"RI Hartley","year":"2004","unstructured":"Hartley, R.I., Zisserman, A.: Multiple View Geometry in Computer Vision, 2nd edn. Cambridge University Press, Cambridge (2004). ISBN: 0521540518","edition":"2"},{"key":"13_CR8","doi-asserted-by":"crossref","unstructured":"Jiang, Q., et al.: Understanding and constructing latent modality structures in multi-modal representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7661\u20137671 (2023)","DOI":"10.1109\/CVPR52729.2023.00740"},{"key":"13_CR9","unstructured":"Kirillov, A., et al.: Segment anything. arXiv preprint arXiv:2304.02643 (2023)"},{"key":"13_CR10","unstructured":"Liang, V.W., Zhang, Y., Kwon, Y., Yeung, S., Zou, J.Y.: Mind the gap: understanding the modality gap in multi-modal contrastive representation learning. In: Koyejo, S., Mohamed, S., Agarwal, A., Belgrave, D., Cho, K., Oh, A. (eds.) Advances in Neural Information Processing Systems, vol.\u00a035, pp. 17612\u201317625. Curran Associates, Inc. (2022)"},{"key":"13_CR11","doi-asserted-by":"crossref","unstructured":"Liu, S., et al.: 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":"13_CR12","unstructured":"Liu, Y.C., et al.: Learning from 2d: contrastive pixel-to-point knowledge transfer for 3d pretraining. arXiv preprint arXiv:2104.04687 (2021)"},{"key":"13_CR13","doi-asserted-by":"crossref","unstructured":"Michele, B., Boulch, A., Puy, G., Bucher, M., Marlet, R.: Generative zero-shot learning for semantic segmentation of 3d point clouds. In: Proceedings of the International Conference on 3D Vision (3DV), pp. 992\u20131002 (2021)","DOI":"10.1109\/3DV53792.2021.00107"},{"key":"13_CR14","unstructured":"Polvara, R., et al.: BLT dataset: acquisition of the agricultural bacchus long-term dataset with automated robot deployment. J. Field Rob. Agric. Rob. Ag 4.0 (2024)"},{"key":"13_CR15","doi-asserted-by":"crossref","unstructured":"Sautier, C., Puy, G., Gidaris, S., Boulch, A., Bursuc, A., Marlet, R.: Image-to-lidar self-supervised distillation for autonomous driving data. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9891\u20139901 (2022)","DOI":"10.1109\/CVPR52688.2022.00966"},{"key":"13_CR16","unstructured":"Sbrolli, C., Matteucci, M.: No captions, no problem: captionless 3d-clip alignment with hard negatives via clip knowledge and llms. In: 35th British Machine Vision Conference 2024, BMVC 2024, Glasgow, UK, 25\u201328 November 2024. BMVA (2024). https:\/\/papers.bmvc2024.org\/0032.pdf"},{"key":"13_CR17","doi-asserted-by":"crossref","unstructured":"Xie, S., Gu, J., Guo, D., Qi, C.R., Guibas, L., Litany, O.: Pointcontrast: unsupervised pre-training for 3d point cloud understanding. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 574\u2013591 (2020)","DOI":"10.1007\/978-3-030-58580-8_34"},{"key":"13_CR18","unstructured":"Xue, L., et al.: Ulip: learning unified representation of language, image and point cloud for 3d understanding. arXiv preprint arXiv:2212.05171 (2022)"},{"key":"13_CR19","doi-asserted-by":"crossref","unstructured":"Xue, L., et al.: Ulip-2: towards scalable multimodal pre-training for 3d understanding (2023)","DOI":"10.1109\/CVPR52733.2024.02558"},{"key":"13_CR20","doi-asserted-by":"crossref","unstructured":"Yang, C.K., Chen, M.H., Chuang, Y.Y., Lin, Y.Y.: 2d-3d interlaced transformer for point cloud segmentation with scene-level supervision (2024)","DOI":"10.1109\/ICCV51070.2023.00096"},{"key":"13_CR21","unstructured":"\u00c9loi Zablocki, Bordes, P., Piwowarski, B., Soulier, L., Gallinari, P.: Context-aware zero-shot learning for object recognition. In: Proceedings of the International Conference on Machine Learning (ICML), pp. 7292\u20137303 (2019)"},{"key":"13_CR22","doi-asserted-by":"crossref","unstructured":"Zhang, R., et al.: Pointclip: point cloud understanding by clip. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8552\u20138562 (2022)","DOI":"10.1109\/CVPR52688.2022.00836"},{"key":"13_CR23","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Girdhar, R., Joulin, A., Misra, I.: Self-supervised pretraining of 3d features on any point-cloud. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 10252\u201310263 (2021)","DOI":"10.1109\/ICCV48922.2021.01009"},{"key":"13_CR24","doi-asserted-by":"crossref","unstructured":"Zhou, C., Loy, C.C., Dai, B.: Extract free dense labels from clip. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 696\u2013712 (2022)","DOI":"10.1007\/978-3-031-19815-1_40"}],"container-title":["Lecture Notes in Computer Science","Image Analysis and Processing \u2013 ICIAP 2025"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-10185-3_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T00:51:22Z","timestamp":1767315082000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-10185-3_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032101846","9783032101853"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-10185-3_13","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":"2 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIAP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Image Analysis and Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Rome","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":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iciap2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.iciap.org\/home","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}