{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,19]],"date-time":"2026-10-19T21:29:46Z","timestamp":1792445386047,"version":"4.5.0"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032101914","type":"print"},{"value":"9783032101921","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\/978-3-032-10192-1_2","type":"book-chapter","created":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T00:46:53Z","timestamp":1767314813000},"page":"13-25","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Hierarchical Vision-Language Retrieval of Educational Metaverse Content in Agriculture"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4482-0479","authenticated-orcid":false,"given":"Ali","family":"Abdari","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6325-9066","authenticated-orcid":false,"given":"Alex","family":"Falcon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4269-4501","authenticated-orcid":false,"given":"Giuseppe","family":"Serra","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,1,2]]},"reference":[{"key":"2_CR1","doi-asserted-by":"crossref","unstructured":"Abdari, A., Falcon, A., Serra, G.: Farmare: a furniture-aware multi-task methodology for recommending apartments based on the user interests. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4293\u20134303 (2023)","DOI":"10.1109\/ICCVW60793.2023.00464"},{"key":"2_CR2","doi-asserted-by":"crossref","unstructured":"Abdari, A., Falcon, A., Serra, G.: Metaverse retrieval: finding the best metaverse environment via language. In: Proceedings of the 1st International Workshop on Deep Multimodal Learning for Information Retrieval, pp.\u00a01\u20139 (2023)","DOI":"10.1145\/3606040.3617445"},{"key":"2_CR3","doi-asserted-by":"crossref","unstructured":"Abdari, A., Falcon, A., Serra, G.: Adoctera: adaptive optimization constraints for improved text-guided retrieval of apartments. In: Proceedings of the 2024 International Conference on Multimedia Retrieval, pp. 1043\u20131050 (2024)","DOI":"10.1145\/3652583.3658039"},{"key":"2_CR4","doi-asserted-by":"crossref","unstructured":"Abdari, A., Falcon, A., Serra, G.: A language-based solution to enable metaverse retrieval. In: International Conference on Multimedia Modeling, pp. 477\u2013488. Springer (2024)","DOI":"10.1007\/978-3-031-53311-2_35"},{"key":"2_CR5","unstructured":"Abdari, A., Falcon, A., Serra, G.: Agrimus: developing museums in the metaverse for agricultural education (2025)"},{"key":"2_CR6","doi-asserted-by":"crossref","unstructured":"Abdari, A., Falcon, A., Serra, G., Huang, Q.: Reproducibility companion paper: Adoctera\u2014adaptive optimization constraints for improved text-guided retrieval of apartments. In: Proceedings of the 2025 International Conference on Multimedia Retrieval, pp. 1958\u20131960 (2025)","DOI":"10.1145\/3731715.3734535"},{"key":"2_CR7","doi-asserted-by":"crossref","unstructured":"Arnab, A., Dehghani, M., Heigold, G., Sun, C., Lu\u010di\u0107, M., Schmid, C.: Vivit: a video vision transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6836\u20136846 (2021)","DOI":"10.1109\/ICCV48922.2021.00676"},{"issue":"3\u20134","key":"2_CR8","doi-asserted-by":"publisher","DOI":"10.1002\/cav.2154","volume":"34","author":"M Barszcz","year":"2023","unstructured":"Barszcz, M., Dziedzic, K., Skublewska-Paszkowska, M., Powroznik, P.: 3D scanning digital models for virtual museums. Comput. Anim. Virtual Worlds 34(3\u20134), e2154 (2023)","journal-title":"Comput. Anim. Virtual Worlds"},{"key":"2_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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3193\u20133203 (2021)","DOI":"10.1109\/CVPR46437.2021.00321"},{"key":"2_CR10","doi-asserted-by":"crossref","unstructured":"Falcon, A., Abdari, A., Serra, G.: Hierartex: hierarchical representations and art experts supporting the retrieval of museums in the metaverse. In: International Conference on Multimedia Modeling, pp. 60\u201373. Springer (2024)","DOI":"10.1007\/978-981-96-2061-6_5"},{"key":"2_CR11","unstructured":"Falcon, A., Portelli, B., Abdari, A., Serra, G., et\u00a0al.: Paving the way for personalized museums tours in the metaverse. In: IRCDL, pp. 178\u2013188 (2024)"},{"key":"2_CR12","unstructured":"FarmVR: Farmvr\u2014virtual reality farming experiences. https:\/\/farmvr.com\/"},{"key":"2_CR13","doi-asserted-by":"crossref","unstructured":"Jin, B., Zheng, Y., Li, P., Li, W., Zheng, Y., Hu, S., Liu, X., Zhu, J., Yan, Z., Sun, H., et\u00a0al.: Tod3cap: towards 3D dense captioning in outdoor scenes. In: European Conference on Computer Vision, pp. 367\u2013384. Springer (2024)","DOI":"10.1007\/978-3-031-72649-1_21"},{"key":"2_CR14","doi-asserted-by":"publisher","first-page":"984","DOI":"10.1016\/j.culher.2016.06.007","volume":"22","author":"C Kiourt","year":"2016","unstructured":"Kiourt, C., Koutsoudis, A., Pavlidis, G.: Dynamus: a fully dynamic 3D virtual museum framework. J. Cult. Herit. 22, 984\u2013991 (2016)","journal-title":"J. Cult. Herit."},{"key":"2_CR15","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: Blip: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: International Conference on Machine Learning, pp. 12888\u201312900. PMLR (2022)"},{"key":"2_CR16","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1016\/j.neucom.2022.07.028","volume":"508","author":"H Luo","year":"2022","unstructured":"Luo, H., Ji, L., Zhong, M., Chen, Y., Lei, W., Duan, N., Li, T.: Clip4clip: an empirical study of clip for end to end video clip retrieval and captioning. Neurocomputing 508, 293\u2013304 (2022)","journal-title":"Neurocomputing"},{"issue":"10","key":"2_CR17","doi-asserted-by":"publisher","first-page":"6762","DOI":"10.3390\/heritage6100353","volume":"6","author":"M Merella","year":"2023","unstructured":"Merella, M., Farina, S., Scaglia, P., Caneve, G., Bernardini, G., Pieri, A., Collareta, A., Bianucci, G.: Structured-light 3D scanning as a tool for creating a digital collection of modern and fossil cetacean skeletons (Natural History Museum, University of Pisa). Heritage 6(10), 6762\u20136776 (2023)","journal-title":"Heritage"},{"key":"2_CR18","unstructured":"Qi, Z., Zhang, Z., Fang, Y., Wang, J., Zhao, H.: Gpt4scene: understand 3D scenes from videos with vision-language models (2025). arXiv preprint arXiv:2501.01428"},{"key":"2_CR19","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"2_CR20","doi-asserted-by":"crossref","unstructured":"Schroff, F., Kalenichenko, D., Philbin, J.: Facenet: a unified embedding for face recognition and clustering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 815\u2013823 (2015)","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"2_CR21","first-page":"10078","volume":"35","author":"Z Tong","year":"2022","unstructured":"Tong, Z., Song, Y., Wang, J., Wang, L.: Videomae: masked autoencoders are data-efficient learners for self-supervised video pre-training. Adv. Neural. Inf. Process. Syst. 35, 10078\u201310093 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2_CR22","doi-asserted-by":"crossref","unstructured":"Vasu, P.K.A., Pouransari, H., Faghri, F., Vemulapalli, R., Tuzel, O.: Mobileclip: fast image-text models through multi-modal reinforced training. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15963\u201315974 (2024)","DOI":"10.1109\/CVPR52733.2024.01511"},{"key":"2_CR23","unstructured":"youtube. https:\/\/www.lordsuni.edu.in\/blog\/youtube-and-education, https:\/\/farmvr.com\/"},{"key":"2_CR24","doi-asserted-by":"crossref","unstructured":"Yu, F., Wang, Z., Li, D., Zhu, P., Liang, X., Wang, X., Okumura, M.: Towards cross-modal point cloud retrieval for indoor scenes. In: International Conference on Multimedia Modeling, pp. 89\u2013102. Springer (2024)","DOI":"10.1007\/978-3-031-53302-0_7"},{"key":"2_CR25","doi-asserted-by":"crossref","unstructured":"Zhu, Z., Zhang, Z., Ma, X., Niu, X., Chen, Y., Jia, B., Deng, Z., Huang, S., Li, Q.: Unifying 3D vision-language understanding via promptable queries. In: European Conference on Computer Vision, pp. 188\u2013206. Springer (2024)","DOI":"10.1007\/978-3-031-72784-9_11"},{"issue":"3","key":"2_CR26","doi-asserted-by":"publisher","first-page":"363","DOI":"10.3390\/electronics10030363","volume":"10","author":"E Zidianakis","year":"2021","unstructured":"Zidianakis, E., Partarakis, N., Ntoa, S., Dimopoulos, A., Kopidaki, S., Ntagianta, A., Ntafotis, E., Xhako, A., Pervolarakis, Z., Kontaki, E., et al.: The invisible museum: a user-centric platform for creating virtual 3D exhibitions with VR support. Electronics 10(3), 363 (2021)","journal-title":"Electronics"}],"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\/978-3-032-10192-1_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T00:46:56Z","timestamp":1767314816000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-10192-1_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032101914","9783032101921"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-10192-1_2","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"}}]}}