{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T03:32:19Z","timestamp":1772595139888,"version":"3.50.1"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031533105","type":"print"},{"value":"9783031533112","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-53311-2_35","type":"book-chapter","created":{"date-parts":[[2024,1,27]],"date-time":"2024-01-27T21:37:36Z","timestamp":1706391456000},"page":"477-488","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["A Language-Based Solution to\u00a0Enable Metaverse Retrieval"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4482-0479","authenticated-orcid":false,"given":"Ali","family":"Abdari","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6325-9066","authenticated-orcid":false,"given":"Alex","family":"Falcon","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4269-4501","authenticated-orcid":false,"given":"Giuseppe","family":"Serra","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,1,28]]},"reference":[{"key":"35_CR1","first-page":"70","volume":"700","author":"H Abdul-Rashid","year":"2018","unstructured":"Abdul-Rashid, H., et al.: Shrec\u201918 track: 2D image-based 3D scene retrieval. Training 700, 70 (2018)","journal-title":"Training"},{"key":"35_CR2","unstructured":"Abdul-Rashid, H., et al.: Shrec\u201919 track: extended 2D scene image-based 3D scene retrieval. Training (per class) 700, 70 (2019)"},{"key":"35_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2021.107137","volume":"154","author":"GP Agnusdei","year":"2021","unstructured":"Agnusdei, G.P., Elia, V., Gnoni, M.G.: A classification proposal of digital twin applications in the safety domain. Comput. Ind. Eng. 154, 107137 (2021)","journal-title":"Comput. Ind. Eng."},{"key":"35_CR4","doi-asserted-by":"publisher","first-page":"8915","DOI":"10.3390\/app13158915","volume":"13","author":"LGG Almeida","year":"2023","unstructured":"Almeida, L.G.G., de Vasconcelos, N.V., Winkler, I., Catapan, M.F.: Innovating industrial training with immersive metaverses: a method for developing cross-platform virtual reality environments. Appl. Sci. 13, 8915 (2023)","journal-title":"Appl. Sci."},{"issue":"4","key":"35_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3499027","volume":"18","author":"Y Cheng","year":"2022","unstructured":"Cheng, Y., Zhu, X., Qian, J., Wen, F., Liu, P.: Cross-modal graph matching network for image-text retrieval. ACM Trans. Multimedia Comput. Commun. Appl. 18(4), 1\u201323 (2022)","journal-title":"ACM Trans. Multimedia Comput. Commun. Appl."},{"issue":"1","key":"35_CR6","doi-asserted-by":"publisher","first-page":"1519","DOI":"10.1016\/j.ijinfomgt.2016.04.017","volume":"37","author":"HS Choi","year":"2017","unstructured":"Choi, H.S., Kim, S.H.: A content service deployment plan for metaverse museum exhibitions-centering on the combination of beacons and HMDs. Int. J. Inf. Manag. 37(1), 1519\u20131527 (2017)","journal-title":"Int. J. Inf. Manag."},{"issue":"2","key":"35_CR7","doi-asserted-by":"publisher","first-page":"52","DOI":"10.22381\/jsme10220224","volume":"10","author":"A Dawson","year":"2022","unstructured":"Dawson, A., et al.: Data-driven consumer engagement, virtual immersive shopping experiences, and blockchain-based digital assets in the retail metaverse. J. Self-Gov. Manag. Econ. 10(2), 52\u201366 (2022)","journal-title":"J. Self-Gov. Manag. Econ."},{"key":"35_CR8","unstructured":"Devlin, J., Chang, M.W., Lee, K.: Google, KT, language, AI: bert: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of NAACL-HLT, pp. 4171\u20134186 (2019)"},{"key":"35_CR9","doi-asserted-by":"crossref","unstructured":"Fu, H., et al.: 3D-front: 3D furnished rooms with layouts and semantics. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10933\u201310942 (2021)","DOI":"10.1109\/ICCV48922.2021.01075"},{"key":"35_CR10","doi-asserted-by":"crossref","unstructured":"Ge, Y., et al.: Bridging video-text retrieval with multiple choice questions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16167\u201316176 (2022)","DOI":"10.1109\/CVPR52688.2022.01569"},{"key":"35_CR11","unstructured":"J., C.: Daily active users (dau) of roblox games worldwide from 4th quarter 2018 to 2nd quarter 2023. Technical report, Statista (2023). https:\/\/www.statista.com\/statistics\/1192573\/daily-active-users-global-roblox\/"},{"key":"35_CR12","doi-asserted-by":"crossref","unstructured":"Jin, C., Wu, F., Wang, J., Liu, Y., Guan, Z., Han, Z.: Metamgc: a music generation framework for concerts in metaverse. J. Audio Speech Music Proc. 31 (2022)","DOI":"10.1186\/s13636-022-00261-8"},{"key":"35_CR13","doi-asserted-by":"publisher","first-page":"20325","DOI":"10.1109\/ACCESS.2019.2897018","volume":"7","author":"H Laaki","year":"2019","unstructured":"Laaki, H., Miche, Y., Tammi, K.: Prototyping a digital twin for real time remote control over mobile networks: Application of remote surgery. IEEE Access 7, 20325\u201320336 (2019)","journal-title":"IEEE Access"},{"issue":"2","key":"35_CR14","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1080\/14626268.2022.2063903","volume":"33","author":"HK Lee","year":"2022","unstructured":"Lee, H.K., Park, S., Lee, Y.: A proposal of virtual museum metaverse content for the mz generation. Dig. Creat. 33(2), 79\u201395 (2022)","journal-title":"Dig. Creat."},{"key":"35_CR15","unstructured":"Lee, L.H., et al.: All one needs to know about metaverse: a complete survey on technological singularity, virtual ecosystem, and research agenda. arXiv preprint arXiv:2110.05352 (2021)"},{"key":"35_CR16","doi-asserted-by":"publisher","first-page":"49088","DOI":"10.1109\/ACCESS.2019.2909828","volume":"7","author":"Y Liu","year":"2019","unstructured":"Liu, Y., et al.: A novel cloud-based framework for the elderly healthcare services using digital twin. IEEE Access 7, 49088\u201349101 (2019)","journal-title":"IEEE Access"},{"key":"35_CR17","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., et al.: Clip4clip: an empirical study of clip for end to end video clip retrieval and captioning. Neurocomputing 508, 293\u2013304 (2022)","journal-title":"Neurocomputing"},{"key":"35_CR18","unstructured":"Metaversed: The metaverse reaches 400m monthly active users. Technical report, Metaversed Consulting (2023). https:\/\/www.metaversed.consulting\/blog\/the-metaverse-reaches-400m-active-users"},{"key":"35_CR19","doi-asserted-by":"crossref","unstructured":"Miech, A., Alayrac, J.B., Smaira, L., Laptev, I., Sivic, J., Zisserman, A.: End-to-end learning of visual representations from uncurated instructional videos. In: Proceedings of IEEE\/CVF CVPR, pp. 9879\u20139889 (2020)","DOI":"10.1109\/CVPR42600.2020.00990"},{"key":"35_CR20","doi-asserted-by":"crossref","unstructured":"Nguyen, T., Gopalan, N., Patel, R., Corsaro, M., Pavlick, E., Tellex, S.: Robot object retrieval with contextual natural language queries. arXiv preprint arXiv:2006.13253 (2020)","DOI":"10.15607\/RSS.2020.XVI.080"},{"key":"35_CR21","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"35_CR22","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"},{"issue":"6","key":"35_CR23","doi-asserted-by":"publisher","first-page":"2066","DOI":"10.3390\/s21062066","volume":"21","author":"A Siyaev","year":"2021","unstructured":"Siyaev, A., Jo, G.S.: Towards aircraft maintenance metaverse using speech interactions with virtual objects in mixed reality. Sensors 21(6), 2066 (2021)","journal-title":"Sensors"},{"key":"35_CR24","doi-asserted-by":"crossref","unstructured":"Song, W., Gong, Y., Wang, Y.: VTONShoes: Virtual try-on of shoes in augmented reality on a mobile device. In: IEEE ISMAR, pp. 234\u2013242 (2022)","DOI":"10.1109\/ISMAR55827.2022.00038"},{"key":"35_CR25","doi-asserted-by":"crossref","unstructured":"Wang, H., Bai, X., Yang, M., Zhu, S., Wang, J., Liu, W.: Scene text retrieval via joint text detection and similarity learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4558\u20134567 (2021)","DOI":"10.1109\/CVPR46437.2021.00453"},{"key":"35_CR26","doi-asserted-by":"publisher","first-page":"76222","DOI":"10.1109\/ACCESS.2023.3297873","volume":"11","author":"J Wang","year":"2023","unstructured":"Wang, J., Chen, S., Liu, Y., Lau, R.: Intelligent metaverse scene content construction. IEEE Access 11, 76222\u201376241 (2023). https:\/\/doi.org\/10.1109\/ACCESS.2023.3297873","journal-title":"IEEE Access"},{"key":"35_CR27","doi-asserted-by":"crossref","unstructured":"Wang, X., Wang, Y., Shi, Y., Zhang, W., Zheng, Q.: AvatarMeeting: an augmented reality remote interaction system with personalized avatars. In: Proceedings of the 28th ACMMM, pp. 4533\u20134535 (2020)","DOI":"10.1145\/3394171.3414449"},{"key":"35_CR28","doi-asserted-by":"crossref","unstructured":"Wen, L., Wang, Y., Zhang, D., Chen, G.: Visual matching is enough for scene text retrieval. In: Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining, pp. 447\u2013455 (2023)","DOI":"10.1145\/3539597.3570428"},{"key":"35_CR29","doi-asserted-by":"crossref","unstructured":"Wu, Y., Chen, K., Zhang, T., Hui, Y., Berg-Kirkpatrick, T., Dubnov, S.: Large-scale contrastive language-audio pretraining with feature fusion and keyword-to-caption augmentation. In: ICASSP 2023\u20132023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1\u20135. IEEE (2023)","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"35_CR30","doi-asserted-by":"crossref","unstructured":"Xin, Y., Yang, D., Zou, Y.: Improving text-audio retrieval by text-aware attention pooling and prior matrix revised loss. In: ICASSP 2023\u20132023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1\u20135. IEEE (2023)","DOI":"10.1109\/ICASSP49357.2023.10096972"},{"key":"35_CR31","doi-asserted-by":"crossref","unstructured":"Yang, H., et al.: Scene synthesis via uncertainty-driven attribute synchronization. In: Proceedings of the IEEE\/CVF ICCV, pp. 5630\u20135640 (2021)","DOI":"10.1109\/ICCV48922.2021.00558"},{"key":"35_CR32","doi-asserted-by":"crossref","unstructured":"Yuan, J., Abdul-Rashid, H., Li, B., Lu, Y.: Sketch\/image-based 3d scene retrieval: Benchmark, algorithm, evaluation. In: 2019 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR), pp. 264\u2013269. IEEE (2019)","DOI":"10.1109\/MIPR.2019.00054"},{"issue":"16","key":"35_CR33","doi-asserted-by":"publisher","first-page":"14128","DOI":"10.1109\/JIOT.2023.3262940","volume":"10","author":"Y Zhou","year":"2023","unstructured":"Zhou, Y., Huang, H., Yuan, S., Zou, H., Xie, L., Yang, J.: Metafi++: Wifi-enabled transformer-based human pose estimation for metaverse avatar simulation. IEEE Internet Things J. 10(16), 14128\u201314136 (2023). https:\/\/doi.org\/10.1109\/JIOT.2023.3262940","journal-title":"IEEE Internet Things J."}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-53311-2_35","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T15:31:46Z","timestamp":1710257506000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-53311-2_35"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031533105","9783031533112"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-53311-2_35","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"28 January 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Amsterdam","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"The Netherlands","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":"29 January 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 February 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"ConfTool Pro","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"297","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"112","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"38% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.2","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.2","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}