{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,7]],"date-time":"2026-02-07T10:59:37Z","timestamp":1770461977223,"version":"3.49.0"},"publisher-location":"Cham","reference-count":19,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030983543","type":"print"},{"value":"9783030983550","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-030-98355-0_45","type":"book-chapter","created":{"date-parts":[[2022,3,14]],"date-time":"2022-03-14T12:06:56Z","timestamp":1647259616000},"page":"499-504","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["Multi-modal Video Retrieval in\u00a0Virtual Reality with\u00a0vitrivr-VR"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3396-1516","authenticated-orcid":false,"given":"Florian","family":"Spiess","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3016-1396","authenticated-orcid":false,"given":"Ralph","family":"Gasser","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5386-330X","authenticated-orcid":false,"given":"Silvan","family":"Heller","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7063-8585","authenticated-orcid":false,"given":"Mahnaz","family":"Parian-Scherb","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5389-9465","authenticated-orcid":false,"given":"Luca","family":"Rossetto","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8046-0362","authenticated-orcid":false,"given":"Loris","family":"Sauter","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9865-6371","authenticated-orcid":false,"given":"Heiko","family":"Schuldt","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,3,15]]},"reference":[{"key":"45_CR1","doi-asserted-by":"crossref","unstructured":"Cer, D., et al.: Universal sentence encoder. CoRR (2018)","DOI":"10.18653\/v1\/D18-2029"},{"key":"45_CR2","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L., Li, K., Li, F.: ImageNet: a large-scale hierarchical image database. In: Conference on Computer Vision and Pattern Recognition (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"45_CR3","unstructured":"Faghri, F., Fleet, D.J., Kiros, J.R., Fidler, S.: VSE++: improving visual-semantic embeddings with hard negatives. In: British Machine Vision Conference 2018 (2018)"},{"key":"45_CR4","doi-asserted-by":"crossref","unstructured":"Gasser, R., Rossetto, L., Heller, S., Schuldt, H.: Cottontail DB: an open source database system for multimedia retrieval and analysis. In: International Conference on Multimedia (2020)","DOI":"10.1145\/3394171.3414538"},{"key":"45_CR5","doi-asserted-by":"crossref","unstructured":"Heller, S., et al.: Multi-modal interactive video retrieval with temporal queries. In: International Conference on Multimedia Modeling (2022)","DOI":"10.1007\/978-3-030-98355-0_44"},{"key":"45_CR6","doi-asserted-by":"crossref","unstructured":"Heller, S., Sauter, L., Schuldt, H., Rossetto, L.: Multi-stage queries and temporal scoring in vitrivr. In: International Conference on Multimedia & Expo Workshops (2020)","DOI":"10.1109\/ICMEW46912.2020.9105954"},{"key":"45_CR7","doi-asserted-by":"crossref","unstructured":"Li, X., Xu, C., Yang, G., Chen, Z., Dong, J.: W2VV++: fully deep learning for ad-hoc video search. In: International Conference on Multimedia (2019)","DOI":"10.1145\/3343031.3350906"},{"key":"45_CR8","doi-asserted-by":"crossref","unstructured":"Li, Y., Song, Y., Cao, L., Tetreault, J.R., Goldberg, L., Jaimes, A., Luo, J.: TGIF: A new dataset and benchmark on animated GIF description. In: Conference on Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.502"},{"key":"45_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"45_CR10","doi-asserted-by":"crossref","unstructured":"Loko\u010d, J., et al.: Is the reign of interactive search eternal? Findings from the video browser showdown 2020. In: ACM TOMM (2021)","DOI":"10.1145\/3445031"},{"key":"45_CR11","doi-asserted-by":"crossref","unstructured":"Rossetto, L., Giangreco, I., Schuldt, H.: Cineast: a multi-feature sketch-based video retrieval engine. In: IEEE International Symposium on Multimedia (2014)","DOI":"10.1109\/ISM.2014.38"},{"key":"45_CR12","doi-asserted-by":"crossref","unstructured":"Rossetto, L., Schuldt, H., Awad, G., Butt, A.A.: V3C - a research video collection. In: International Conference on Multimedia Modeling (2019)","DOI":"10.1007\/978-3-030-05710-7_29"},{"key":"45_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"742","DOI":"10.1007\/978-3-030-58536-5_44","volume-title":"Computer Vision \u2013 ECCV 2020","author":"O Sidorov","year":"2020","unstructured":"Sidorov, O., Hu, R., Rohrbach, M., Singh, A.: TextCaps: a dataset for image captioning with reading comprehension. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12347, pp. 742\u2013758. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58536-5_44"},{"key":"45_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"441","DOI":"10.1007\/978-3-030-67835-7_42","volume-title":"MultiMedia Modeling","author":"F Spiess","year":"2021","unstructured":"Spiess, F., Gasser, R., Heller, S., Rossetto, L., Sauter, L., Schuldt, H.: Competitive interactive video retrieval in virtual reality with vitrivr-VR. In: Loko\u010d, J., et al. (eds.) MMM 2021. LNCS, vol. 12573, pp. 441\u2013447. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-67835-7_42"},{"key":"45_CR15","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.A.: Inception-v4, inception-resnet and the impact of residual connections on learning. In: AAAI Conference on Artificial Intelligence (2017)","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"45_CR16","doi-asserted-by":"crossref","unstructured":"Tran, L., et al.: A VR interface for browsing visual spaces at VBS2021. In: International Conference on Multimedia Modeling (2021)","DOI":"10.1007\/978-3-030-67835-7_50"},{"key":"45_CR17","doi-asserted-by":"crossref","unstructured":"Wang, X., Wu, J., Chen, J., Li, L., Wang, Y., Wang, W.Y.: Vatex: a large-scale, high-quality multilingual dataset for video-and-language research. In: International Conference on Computer Vision (2019)","DOI":"10.1109\/ICCV.2019.00468"},{"key":"45_CR18","doi-asserted-by":"crossref","unstructured":"Xu, J., Mei, T., Yao, T., Rui, Y.: MSR-VTT: a large video description dataset for bridging video and language. In: Conference on Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.571"},{"key":"45_CR19","doi-asserted-by":"crossref","unstructured":"Young, P., Lai, A., Hodosh, M., Hockenmaier, J.: From image descriptions to visual denotations: new similarity metrics for semantic inference over event descriptions. Trans. Assoc. Comput. Linguistics 2, 67\u201378 (2014)","DOI":"10.1162\/tacl_a_00166"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-98355-0_45","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,29]],"date-time":"2023-01-29T02:18:19Z","timestamp":1674958699000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-98355-0_45"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783030983543","9783030983550"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-98355-0_45","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"15 March 2022","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":"Phu Quoc","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 June 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 June 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2022","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":"212","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":"84","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":"40% - 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","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":"4","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)"}}]}}