{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,7]],"date-time":"2026-02-07T11:51:06Z","timestamp":1770465066161,"version":"3.49.0"},"publisher-location":"Cham","reference-count":30,"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_32","type":"book-chapter","created":{"date-parts":[[2024,1,28]],"date-time":"2024-01-28T09:02:09Z","timestamp":1706432529000},"page":"356-363","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["VERGE in\u00a0VBS 2024"],"prefix":"10.1007","author":[{"given":"Nick","family":"Pantelidis","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maria","family":"Pegia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Damianos","family":"Galanopoulos","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Konstantinos","family":"Apostolidis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Klearchos","family":"Stavrothanasopoulos","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anastasia","family":"Moumtzidou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Konstantinos","family":"Gkountakos","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ilias","family":"Gialampoukidis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stefanos","family":"Vrochidis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vasileios","family":"Mezaris","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ioannis","family":"Kompatsiaris","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bj\u00f6rn \u00de\u00f3r","family":"J\u00f3nsson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,1,29]]},"reference":[{"key":"32_CR1","unstructured":"Bochkovskiy, A., Wang, C.Y., Liao, H.Y.M.: YOLOv4: optimal speed and accuracy of object detection. arXiv Preprint arXiv:2004.10934 (2020)"},{"key":"32_CR2","doi-asserted-by":"crossref","unstructured":"Caba Heilbron, F., Escorcia, V., Ghanem, B., Carlos Niebles, J.: ActivityNet: a large-scale video benchmark for human activity understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 961\u2013970 (2015)","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"32_CR3","unstructured":"Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. CoRR abs\/1810.04805 (2018). http:\/\/arxiv.org\/abs\/1810.04805"},{"key":"32_CR4","unstructured":"Faghri, F., Fleet, D.J., Kiros, J.R., Fidler, S.: VSE++: improving visual-semantic embeddings with hard negatives. In: Proceedings of the British Machine Vision Conference (BMVC) (2018)"},{"key":"32_CR5","doi-asserted-by":"crossref","unstructured":"Galanopoulos, D., Mezaris, V.: Attention mechanisms, signal encodings and fusion strategies for improved ad-hoc video search with dual encoding networks. In: Proceedings of the ACM International Conference on Multimedia Retrieval (ICMR 2020). ACM (2020)","DOI":"10.1145\/3372278.3390737"},{"key":"32_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"627","DOI":"10.1007\/978-3-031-25069-9_40","volume-title":"Computer Vision","author":"D Galanopoulos","year":"2023","unstructured":"Galanopoulos, D., Mezaris, V.: Are all combinations equal? Combining textual and visual features with multiple space learning for text-based video retrieval. In: Karlinsky, L., Michaeli, T., Nishino, K. (eds.) ECCV 2022. LNCS, pp. 627\u2013643. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-25069-9_40"},{"key":"32_CR7","doi-asserted-by":"publisher","first-page":"108797","DOI":"10.1109\/ACCESS.2022.3213652","volume":"10","author":"N Gkalelis","year":"2022","unstructured":"Gkalelis, N., Daskalakis, D., Mezaris, V.: ViGAT: bottom-up event recognition and explanation in video using factorized graph attention network. IEEE Access 10, 108797\u2013108816 (2022). https:\/\/doi.org\/10.1109\/ACCESS.2022.3213652","journal-title":"IEEE Access"},{"key":"32_CR8","doi-asserted-by":"crossref","unstructured":"Gkountakos, K., Touska, D., Ioannidis, K., Tsikrika, T., Vrochidis, S., Kompatsiaris, I.: Spatio-temporal activity detection and recognition in untrimmed surveillance videos. In: Proceedings of the 2021 International Conference on Multimedia Retrieval, pp. 451\u2013455 (2021)","DOI":"10.1145\/3460426.3463591"},{"key":"32_CR9","doi-asserted-by":"crossref","unstructured":"Hara, K., et al.: Can spatiotemporal 3D CNNs retrace the history of 2D CNNs and ImageNet? In: Proceedings of IEEE CVPR 2018 (2018)","DOI":"10.1109\/CVPR.2018.00685"},{"key":"32_CR10","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"32_CR11","doi-asserted-by":"publisher","unstructured":"Ilharco, G., et al.: OpenCLIP (2021). https:\/\/doi.org\/10.5281\/zenodo.5143773, if you use this software, please cite it as below","DOI":"10.5281\/zenodo.5143773"},{"issue":"1","key":"32_CR12","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1109\/TPAMI.2010.57","volume":"33","author":"H Jegou","year":"2010","unstructured":"Jegou, H., Douze, M., Schmid, C.: Product quantization for nearest neighbor search. IEEE Trans. Pattern Anal. Mach. Intell. 33(1), 117\u2013128 (2010)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"32_CR13","unstructured":"Kolesnikov, A., et al.: An image is worth $$16 \\times 16$$ words: transformers for image recognition at scale (2021)"},{"issue":"7","key":"32_CR14","doi-asserted-by":"publisher","first-page":"1956","DOI":"10.1007\/s11263-020-01316-z","volume":"128","author":"A Kuznetsova","year":"2020","unstructured":"Kuznetsova, A., et al.: The open images dataset v4: unified image classification, object detection, and visual relationship detection at scale. Int. J. Comput. Vis. 128(7), 1956\u20131981 (2020)","journal-title":"Int. J. Comput. Vis."},{"key":"32_CR15","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: TGIF: a new dataset and benchmark on animated GIF description. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4641\u20134650 (2016)","DOI":"10.1109\/CVPR.2016.502"},{"key":"32_CR16","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":"32_CR17","doi-asserted-by":"publisher","first-page":"3481","DOI":"10.1007\/s00530-023-01143-5","volume":"29","author":"J Loko\u010d","year":"2023","unstructured":"Loko\u010d, J., et al.: Interactive video retrieval in the age of effective joint embedding deep models: lessons from the 11th VBS. Multimed. Syst. 29, 3481\u20133504 (2023)","journal-title":"Multimed. Syst."},{"key":"32_CR18","doi-asserted-by":"crossref","unstructured":"Mahajan, D., et al.: Exploring the limits of weakly supervised pretraining. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 181\u2013196 (2018)","DOI":"10.1007\/978-3-030-01216-8_12"},{"key":"32_CR19","unstructured":"Markatopoulou, F., Moumtzidou, A., Galanopoulos, D., et al.: ITI-CERTH participation in TRECVID 2017. In: Proceedings of TRECVID 2017 Workshop, USA (2017)"},{"key":"32_CR20","unstructured":"Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. In: 1st International Conference on Learning Representations, Workshop Track Proceedings, ICLR 2013 (2013)"},{"key":"32_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1007\/978-3-319-51811-4_9","volume-title":"MultiMedia Modeling","author":"N Pittaras","year":"2017","unstructured":"Pittaras, N., Markatopoulou, F., Mezaris, V., Patras, I.: Comparison of fine-tuning and extension strategies for deep convolutional neural networks. In: Amsaleg, L., Gu\u00f0mundsson, G.\u00de, Gurrin, C., J\u00f3nsson, B.\u00de, Satoh, S. (eds.) MMM 2017. LNCS, vol. 10132, pp. 102\u2013114. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-51811-4_9"},{"key":"32_CR22","doi-asserted-by":"crossref","unstructured":"Reimers, N., Gurevych, I.: Sentence-BERT: sentence embeddings using Siamese BERT-networks. arXiv preprint arXiv:1908.10084 (2019)","DOI":"10.18653\/v1\/D19-1410"},{"key":"32_CR23","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":"32_CR24","unstructured":"Shao, S., Zhao, Z., Li, B., Xiao, T., Yu, G., et al.: CrowdHuman: a benchmark for detecting human in a crowd. arXiv Preprint arXiv:1805.00123 (2018)"},{"key":"32_CR25","unstructured":"Tan, M., Le, Q.: Efficientnetv2: smaller models and faster training. In: International Conference on Machine Learning, pp. 10096\u201310106. PMLR (2021)"},{"key":"32_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"539","DOI":"10.1007\/978-3-031-27077-2_42","volume-title":"MultiMedia Modeling","author":"QT Truong","year":"2023","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.) MMM 2023. LNCS, vol. 13833, pp. 539\u2013550. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-27077-2_42"},{"key":"32_CR27","doi-asserted-by":"crossref","unstructured":"Wang, X., Wu, J., Chen, J., Li, L., Wang, Y.F., Wang, W.Y.: VATEX: a large-scale, high-quality multilingual dataset for video-and-language research. In: Proceedings of the 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 4581\u20134591 (2019)","DOI":"10.1109\/ICCV.2019.00468"},{"key":"32_CR28","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5288\u20135296 (2016)","DOI":"10.1109\/CVPR.2016.571"},{"key":"32_CR29","doi-asserted-by":"crossref","unstructured":"Zagoruyko, S., Komodakis, N.: Wide residual networks. arXiv preprint arXiv:1605.07146 (2016)","DOI":"10.5244\/C.30.87"},{"issue":"6","key":"32_CR30","doi-asserted-by":"publisher","first-page":"1452","DOI":"10.1109\/TPAMI.2017.2723009","volume":"40","author":"B Zhou","year":"2017","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 (2017)","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_32","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T12:00:40Z","timestamp":1709812840000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-53302-0_32"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031533013","9783031533020"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-53302-0_32","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)"}}]}}