{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T20:11:38Z","timestamp":1780344698949,"version":"3.54.1"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783031270765","type":"print"},{"value":"9783031270772","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-27077-2_53","type":"book-chapter","created":{"date-parts":[[2023,3,28]],"date-time":"2023-03-28T05:03:10Z","timestamp":1679979790000},"page":"646-651","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Exploring Effective Interactive Text-Based Video Search in\u00a0vitrivr"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8046-0362","authenticated-orcid":false,"given":"Loris","family":"Sauter","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3016-1396","authenticated-orcid":false,"given":"Ralph","family":"Gasser","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5386-330X","authenticated-orcid":false,"given":"Silvan","family":"Heller","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5389-9465","authenticated-orcid":false,"given":"Luca","family":"Rossetto","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Colin","family":"Saladin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3396-1516","authenticated-orcid":false,"given":"Florian","family":"Spiess","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9865-6371","authenticated-orcid":false,"given":"Heiko","family":"Schuldt","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,3,29]]},"reference":[{"key":"53_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"543","DOI":"10.1007\/978-3-030-98355-0_52","volume-title":"MultiMedia Modeling","author":"G Amato","year":"2022","unstructured":"Amato, G., et al.: VISIONE at\u00a0video browser showdown 2022. In: \u00de\u00f3r J\u00f3nsson, B., et al. (eds.) MMM 2022. LNCS, vol. 13142, pp. 543\u2013548. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-030-98355-0_52"},{"key":"53_CR2","doi-asserted-by":"publisher","unstructured":"Bain, M., Nagrani, A., Varol, G., Zisserman, A.: Frozen in time: a joint video and image encoder for end-to-end retrieval. In: International Conference on Computer Vision, ICCV (2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.00175","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"53_CR3","doi-asserted-by":"publisher","unstructured":"Berns, F., Rossetto, L., Schoeffmann, K., Beecks, C., Awad, G.: V3C1 dataset: an evaluation of content characteristics. In: International Conference on Multimedia Retrieval. ACM (2019). https:\/\/doi.org\/10.1145\/3323873.3325051","DOI":"10.1145\/3323873.3325051"},{"key":"53_CR4","doi-asserted-by":"publisher","unstructured":"Cho, J., Yoon, S., Kale, A., Dernoncourt, F., Bui, T., Bansal, M.: Fine-grained image captioning with CLIP reward. In: Findings of the Association for Computational Linguistics (2022). https:\/\/doi.org\/10.18653\/v1\/2022.findings-naacl.39","DOI":"10.18653\/v1\/2022.findings-naacl.39"},{"key":"53_CR5","doi-asserted-by":"publisher","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. ACM (2020). https:\/\/doi.org\/10.1145\/3394171.3414538","DOI":"10.1145\/3394171.3414538"},{"key":"53_CR6","doi-asserted-by":"crossref","unstructured":"Gasser, R., Rossetto, L., Schuldt, H.: Multimodal multimedia retrieval with vitrivr. In: International Conference on Multimedia Retrieval (2019)","DOI":"10.1145\/3323873.3326921"},{"key":"53_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"493","DOI":"10.1007\/978-3-030-98355-0_44","volume-title":"MultiMedia Modeling","author":"S Heller","year":"2022","unstructured":"Heller, S., et al.: Multi-modal interactive video retrieval with\u00a0temporal queries. In: \u00de\u00f3r J\u00f3nsson, B., et al. (eds.) MMM 2022. LNCS, vol. 13142, pp. 493\u2013498. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-030-98355-0_44"},{"key":"53_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"435","DOI":"10.1007\/978-3-030-67835-7_41","volume-title":"MultiMedia Modeling","author":"S Heller","year":"2021","unstructured":"Heller, S., et al.: Towards explainable interactive multi-modal video retrieval with vitrivr. In: Loko\u010d, J., et al. (eds.) MMM 2021. LNCS, vol. 12573, pp. 435\u2013440. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-67835-7_41"},{"key":"53_CR9","doi-asserted-by":"publisher","unstructured":"Heller, S., et al.: Interactive video retrieval evaluation at a distance: comparing sixteen interactive video search systems in a remote setting at the 10th Video Browser Showdown. Int. J. Multimedia Inf. Retrieval, 1\u201318 (2022). https:\/\/doi.org\/10.1007\/s13735-021-00225-2","DOI":"10.1007\/s13735-021-00225-2"},{"key":"53_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"487","DOI":"10.1007\/978-3-030-98355-0_43","volume-title":"MultiMedia Modeling","author":"N Hezel","year":"2022","unstructured":"Hezel, N., Schall, K., Jung, K., Barthel, K.U.: Efficient search and\u00a0browsing of\u00a0large-scale video collections with\u00a0vibro. In: \u00de\u00f3r J\u00f3nsson, B., et al. (eds.) MMM 2022. LNCS, vol. 13142, pp. 487\u2013492. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-030-98355-0_43"},{"key":"53_CR11","doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H., Wu, C., Feichtenhofer, C., Darrell, T., Xie, S.: A convnet for the 2020s. CoRR abs\/2201.03545 (2022)","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"53_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1007\/978-3-030-98358-1_16","volume-title":"MultiMedia Modeling","author":"J Loko\u010d","year":"2022","unstructured":"Loko\u010d, J., et al.: A Task category space for\u00a0user-centric comparative multimedia search evaluations. In: \u00de\u00f3r J\u00f3nsson, B., et al. (eds.) MMM 2022. LNCS, vol. 13141, pp. 193\u2013204. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-030-98358-1_16"},{"key":"53_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"505","DOI":"10.1007\/978-3-030-98355-0_46","volume-title":"MultiMedia Modeling","author":"J Loko\u010d","year":"2022","unstructured":"Loko\u010d, J., Mejzl\u00edk, F., Sou\u010dek, T., Dokoupil, P., Pe\u0161ka, L.: Video search with\u00a0context-aware ranker and\u00a0relevance feedback. In: \u00de\u00f3r J\u00f3nsson, B., et al. (eds.) MMM 2022. LNCS, vol. 13142, pp. 505\u2013510. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-030-98355-0_46"},{"key":"53_CR14","doi-asserted-by":"publisher","unstructured":"Loko\u010d, J., et al.: Is the reign of interactive search eternal? Findings from the video browser showdown 2020. ACM Trans. Multimedia Computi. Commun. Appl. (2021). https:\/\/doi.org\/10.1145\/3445031","DOI":"10.1145\/3445031"},{"key":"53_CR15","unstructured":"Mokady, R., Hertz, A., Bermano, A.H.: Clipcap: CLIP prefix for image captioning. CoRR abs\/2111.09734 (2021)"},{"key":"53_CR16","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning (2021)"},{"key":"53_CR17","unstructured":"Rossetto, L.: Multi-modal video retrieval. Ph.D. thesis, University of Basel (2018)"},{"key":"53_CR18","doi-asserted-by":"publisher","unstructured":"Rossetto, L., Baumgartner, M., Gasser, R., Heitz, L., Wang, R., Bernstein, A.: Exploring graph-querying approaches in LifeGraph. In: Workshop on Lifelog Search Challenge (2021). https:\/\/doi.org\/10.1145\/3463948.3469068","DOI":"10.1145\/3463948.3469068"},{"key":"53_CR19","doi-asserted-by":"crossref","unstructured":"Rossetto, L., et al.: Interactive video retrieval in the age of deep learning \u2013 detailed evaluation of VBS 2019. IEEE Trans. Multimedia (2021)","DOI":"10.1109\/TMM.2020.2980944"},{"key":"53_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"385","DOI":"10.1007\/978-3-030-67835-7_33","volume-title":"MultiMedia Modeling","author":"L Rossetto","year":"2021","unstructured":"Rossetto, L., Gasser, R., Sauter, L., Bernstein, A., Schuldt, H.: A system for interactive multimedia retrieval evaluations. In: Loko\u010d, J., et al. (eds.) MMM 2021. LNCS, vol. 12573, pp. 385\u2013390. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-67835-7_33"},{"key":"53_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"336","DOI":"10.1007\/978-3-319-27674-8_30","volume-title":"MultiMedia Modeling","author":"L Rossetto","year":"2016","unstructured":"Rossetto, L., Giangreco, I., Heller, S., T\u0103nase, C., Schuldt, H.: Searching in video collections using sketches and sample images \u2013 the Cineast system. In: Tian, Q., Sebe, N., Qi, G.-J., Huet, B., Hong, R., Liu, X. (eds.) MMM 2016. LNCS, vol. 9517, pp. 336\u2013341. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-27674-8_30"},{"key":"53_CR22","doi-asserted-by":"crossref","unstructured":"Rossetto, L., Giangreco, I., Schuldt, H.: Cineast: a multi-feature sketch-based video retrieval engine. In: International Symposium on Multimedia (2014)","DOI":"10.1109\/ISM.2014.38"},{"key":"53_CR23","doi-asserted-by":"publisher","unstructured":"Rossetto, L., Giangreco, I., Tanase, C., Schuldt, H.: vitrivr: A flexible retrieval stack supporting multiple query modes for searching in multimedia collections. In: ACM Conference on Multimedia (2016). https:\/\/doi.org\/10.1145\/2964284.2973797","DOI":"10.1145\/2964284.2973797"},{"key":"53_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"616","DOI":"10.1007\/978-3-030-05716-9_55","volume-title":"MultiMedia Modeling","author":"L Rossetto","year":"2019","unstructured":"Rossetto, L., Amiri Parian, M., Gasser, R., Giangreco, I., Heller, S., Schuldt, H.: Deep learning-based concept detection in vitrivr. In: Kompatsiaris, I., Huet, B., Mezaris, V., Gurrin, C., Cheng, W.-H., Vrochidis, S. (eds.) MMM 2019. LNCS, vol. 11296, pp. 616\u2013621. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-05716-9_55"},{"key":"53_CR25","unstructured":"Rossetto, L., Schoeffmann, K., Bernstein, A.: Insights on the V3C2 dataset. CoRR abs\/2105.01475 (2021)"},{"key":"53_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"349","DOI":"10.1007\/978-3-030-05710-7_29","volume-title":"MultiMedia Modeling","author":"L Rossetto","year":"2019","unstructured":"Rossetto, L., Schuldt, H., Awad, G., Butt, A.A.: V3C \u2013 a research video collection. In: Kompatsiaris, I., Huet, B., Mezaris, V., Gurrin, C., Cheng, W.-H., Vrochidis, S. (eds.) MMM 2019. LNCS, vol. 11295, pp. 349\u2013360. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-05710-7_29"},{"key":"53_CR27","doi-asserted-by":"crossref","unstructured":"Schoeffmann, K.: Video browser showdown 2012\u20132019: a review. In: International Conference on Content-Based Multimedia Indexing (2019)","DOI":"10.1109\/CBMI.2019.8877397"},{"key":"53_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"499","DOI":"10.1007\/978-3-030-98355-0_45","volume-title":"MultiMedia Modeling","author":"F Spiess","year":"2022","unstructured":"Spiess, F., et al.: Multi-modal video retrieval in\u00a0virtual reality with\u00a0vitrivr-VR. In: \u00de\u00f3r J\u00f3nsson, B., et al. (eds.) MMM 2022. LNCS, vol. 13142, pp. 499\u2013504. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-030-98355-0_45"},{"key":"53_CR29","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":"53_CR30","doi-asserted-by":"crossref","unstructured":"Truong, Q.T., et al.: Marine video kit: a new marine video dataset for content-based analysis and retrieval. In: Dang-Nguyen, D., et al.: MMM 2023. LNCS, vol. 13833, pp. 539\u2013550. Springer. Cham (2023)","DOI":"10.1007\/978-3-031-27077-2_42"},{"key":"53_CR31","doi-asserted-by":"publisher","unstructured":"Yang, Y., et al.: Multilingual universal sentence encoder for semantic retrieval (2019). https:\/\/doi.org\/10.48550\/ARXIV.1907.04307","DOI":"10.48550\/ARXIV.1907.04307"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-27077-2_53","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T18:24:42Z","timestamp":1680373482000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-27077-2_53"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031270765","9783031270772"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-27077-2_53","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"29 March 2023","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":"Bergen","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Norway","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 January 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 January 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2023","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":"267","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":"86","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":"32% - 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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}