{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T17:11:26Z","timestamp":1770743486879,"version":"3.49.0"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031533013","type":"print"},{"value":"9783031533020","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\/978-3-031-53302-0_34","type":"book-chapter","created":{"date-parts":[[2024,1,28]],"date-time":"2024-01-28T09:02:09Z","timestamp":1706432529000},"page":"372-379","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["DiveXplore at\u00a0the\u00a0Video Browser Showdown 2024"],"prefix":"10.1007","author":[{"given":"Klaus","family":"Schoeffmann","sequence":"first","affiliation":[]},{"given":"Sahar","family":"Nasirihaghighi","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,1,29]]},"reference":[{"key":"34_CR1","doi-asserted-by":"crossref","unstructured":"Baek, J., et al.: What is wrong with scene text recognition model comparisons? Dataset and model analysis. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4715\u20134723 (2019)","DOI":"10.1109\/ICCV.2019.00481"},{"key":"34_CR2","doi-asserted-by":"crossref","unstructured":"Baek, Y., Lee, B., Han, D., Yun, S., Lee, H.: Character region awareness for text detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9365\u20139374 (2019)","DOI":"10.1109\/CVPR.2019.00959"},{"key":"34_CR3","doi-asserted-by":"crossref","unstructured":"Berns, F., Rossetto, L., Schoeffmann, K., Beecks, C., Awad, G.: V3C1 dataset: an evaluation of content characteristics. In: Proceedings of the 2019 on International Conference on Multimedia Retrieval, pp. 334\u2013338. ACM (2019)","DOI":"10.1145\/3323873.3325051"},{"key":"34_CR4","doi-asserted-by":"publisher","unstructured":"Cherti, M., et al.: Reproducible scaling laws for contrastive language-image learning (2022). https:\/\/doi.org\/10.48550\/ARXIV.2212.07143. https:\/\/arxiv.org\/abs\/2212.07143","DOI":"10.48550\/ARXIV.2212.07143"},{"issue":"3","key":"34_CR5","doi-asserted-by":"publisher","first-page":"535","DOI":"10.1109\/TBDATA.2019.2921572","volume":"7","author":"J Johnson","year":"2019","unstructured":"Johnson, J., Douze, M., J\u00e9gou, H.: Billion-scale similarity search with GPUs. IEEE Trans. Big Data 7(3), 535\u2013547 (2019)","journal-title":"IEEE Trans. Big Data"},{"key":"34_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"589","DOI":"10.1007\/978-3-030-37734-2_48","volume-title":"MultiMedia Modeling","author":"S Kletz","year":"2020","unstructured":"Kletz, S., Schoeffmann, K., Leibetseder, A., Benois-Pineau, J., Husslein, H.: Instrument recognition in laparoscopy for technical skill assessment. In: Ro, Y.M., et al. (eds.) MMM 2020, Part II. LNCS, vol. 11962, pp. 589\u2013600. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-37734-2_48"},{"key":"34_CR7","doi-asserted-by":"publisher","unstructured":"Leibetseder, A., Schoeffmann, K.: diveXplore 6.0: ITEC\u2019s interactive video exploration system at VBS 2022. In: \u00de\u00f3r J\u00f3nsson, B., et al. (eds.) MMM 2022. LNCS, vol. 13142, pp. 569\u2013574. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-030-98355-0_56","DOI":"10.1007\/978-3-030-98355-0_56"},{"key":"34_CR8","doi-asserted-by":"crossref","unstructured":"Loko\u010d, J., et al.: Interactive video retrieval in the age of effective joint embedding deep models: lessons from the 11th vbs. Multimedia Systems, pp. 1\u201324 (2023)","DOI":"10.1007\/s00530-023-01143-5"},{"key":"34_CR9","doi-asserted-by":"publisher","unstructured":"Loko\u010d, J., et al.: Interactive search or sequential browsing? A detailed analysis of the video browser showdown 2018. ACM Trans. Multimedia Comput. Commun. Appl. 15(1), 29:1\u201329:18 (2019). https:\/\/doi.org\/10.1145\/3295663. http:\/\/doi.acm.org\/10.1145\/3295663","DOI":"10.1145\/3295663"},{"issue":"2","key":"34_CR10","doi-asserted-by":"publisher","first-page":"502","DOI":"10.1109\/TPAMI.2019.2901464","volume":"42","author":"M Monfort","year":"2020","unstructured":"Monfort, M., et al.: Moments in time dataset: one million videos for event understanding. IEEE Trans. Pattern Anal. Mach. Intell. 42(2), 502\u2013508 (2020). https:\/\/doi.org\/10.1109\/TPAMI.2019.2901464","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"34_CR11","doi-asserted-by":"crossref","unstructured":"Nasirihaghighi, S., Ghamsarian, N., Stefanics, D., Schoeffmann, K., Husslein, H.: Action recognition in video recordings from gynecologic laparoscopy. In: 2023 IEEE 36th International Symposium on Computer-Based Medical Systems (CBMS), pp. 29\u201334. IEEE (2023)","DOI":"10.1109\/CBMS58004.2023.00187"},{"key":"34_CR12","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":"34_CR13","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1109\/TMM.2020.2980944","volume":"23","author":"L Rossetto","year":"2021","unstructured":"Rossetto, L., et al.: Interactive video retrieval in the age of deep learning - detailed evaluation of VBS 2019. IEEE Trans. Multimedia 23, 243\u2013256 (2021). https:\/\/doi.org\/10.1109\/TMM.2020.2980944","journal-title":"IEEE Trans. Multimedia"},{"key":"34_CR14","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, Part II 27. LNCS, vol. 12573, pp. 385\u2013390. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-67835-7_33"},{"key":"34_CR15","unstructured":"Rossetto, L., Schoeffmann, K., Bernstein, A.: Insights on the V3C2 dataset. arXiv preprint arXiv:2105.01475 (2021)"},{"key":"34_CR16","doi-asserted-by":"crossref","unstructured":"Schoeffmann, K.: diveXB: an interactive video retrieval system for beginners. In: Proceedings of the 20th International Conference on Content-based Multimedia Indexing, CBMI 2023, pp. 1\u20136. IEEE (2023)","DOI":"10.1145\/3617233.3617258"},{"key":"34_CR17","doi-asserted-by":"publisher","first-page":"11187","DOI":"10.1007\/s11042-014-2224-7","volume":"74","author":"K Schoeffmann","year":"2015","unstructured":"Schoeffmann, K., Del Fabro, M., Szkaliczki, T., B\u00f6sz\u00f6rmenyi, L., Keckstein, J.: Keyframe extraction in endoscopic video. Multimedia Tools Appl. 74, 11187\u201311206 (2015)","journal-title":"Multimedia Tools Appl."},{"key":"34_CR18","doi-asserted-by":"publisher","unstructured":"Schoeffmann, K., Stefanics, D., Leibetseder, A.: diveXplore at the video browser showdown 2023. In: Dang-Nguyen, D.T., et al. (eds.) MultiMedia Modeling, MMM 2023. LNCS, vol. 13833. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-27077-2_59","DOI":"10.1007\/978-3-031-27077-2_59"},{"key":"34_CR19","unstructured":"Schuhmann, C., et al.: LAION-400M: open dataset of clip-filtered 400 million image-text pairs. arXiv preprint arXiv:2111.02114 (2021)"},{"key":"34_CR20","unstructured":"Sou\u010dek, T., Loko\u010d, J.: TransNet V2: an effective deep network architecture for fast shot transition detection. arXiv preprint arXiv:2008.04838 (2020)"},{"key":"34_CR21","unstructured":"Tan, M., Le, Q.: EfficientNet: rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning, pp. 6105\u20136114. PMLR (2019)"},{"key":"34_CR22","doi-asserted-by":"publisher","unstructured":"Truong, Q.T., et al.: Marine video kit: a new marine video dataset for content-based analysis and retrieval. In: Dang-Nguyen, D.T., et al. (eds.) MultiMedia Modeling, MMM 2023. LNCS, vol. 13833. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-27077-2_42","DOI":"10.1007\/978-3-031-27077-2_42"},{"key":"34_CR23","doi-asserted-by":"crossref","unstructured":"Wang, C.Y., Bochkovskiy, A., Liao, H.Y.M.: YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. arXiv preprint arXiv:2207.02696 (2022)","DOI":"10.1109\/CVPR52729.2023.00721"},{"issue":"6","key":"34_CR24","doi-asserted-by":"publisher","first-page":"1452","DOI":"10.1109\/TPAMI.2017.2723009","volume":"40","author":"B Zhou","year":"2018","unstructured":"Zhou, B., Lapedriza, A., Khosla, A., Oliva, A., Torralba, A.: Places: a 10 million image database for scene recognition. IEEE Trans. Pattern Anal. Mach. Intell. 40(6), 1452\u20131464 (2018). https:\/\/doi.org\/10.1109\/TPAMI.2017.2723009","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-53302-0_34","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T12:01:05Z","timestamp":1709812865000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-53302-0_34"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031533013","9783031533020"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-53302-0_34","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":"29 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)"}}]}}