{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T14:08:29Z","timestamp":1742998109814,"version":"3.40.3"},"publisher-location":"Cham","reference-count":22,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031270765"},{"type":"electronic","value":"9783031270772"}],"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_55","type":"book-chapter","created":{"date-parts":[[2023,3,28]],"date-time":"2023-03-28T05:03:10Z","timestamp":1679979790000},"page":"658-664","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["VERGE in\u00a0VBS 2023"],"prefix":"10.1007","author":[{"given":"Nick","family":"Pantelidis","sequence":"first","affiliation":[]},{"given":"Stelios","family":"Andreadis","sequence":"additional","affiliation":[]},{"given":"Maria","family":"Pegia","sequence":"additional","affiliation":[]},{"given":"Anastasia","family":"Moumtzidou","sequence":"additional","affiliation":[]},{"given":"Damianos","family":"Galanopoulos","sequence":"additional","affiliation":[]},{"given":"Konstantinos","family":"Apostolidis","sequence":"additional","affiliation":[]},{"given":"Despoina","family":"Touska","sequence":"additional","affiliation":[]},{"given":"Konstantinos","family":"Gkountakos","sequence":"additional","affiliation":[]},{"given":"Ilias","family":"Gialampoukidis","sequence":"additional","affiliation":[]},{"given":"Stefanos","family":"Vrochidis","sequence":"additional","affiliation":[]},{"given":"Vasileios","family":"Mezaris","sequence":"additional","affiliation":[]},{"given":"Ioannis","family":"Kompatsiaris","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,3,29]]},"reference":[{"key":"55_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":"55_CR2","doi-asserted-by":"crossref","unstructured":"Caba Heilbron, F., et al.: ActivityNet: a large-scale video benchmark for human activity understanding. In: Proceedings of IEEE CVPR 2015, pp. 961\u2013970 (2015)","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"55_CR3","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo Vadis, action recognition? a new model and the kinetics dataset. In: proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6299\u20136308 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"55_CR4","unstructured":"Faghri, F., Fleet, D.J., et al.: VSE++: improving visual-semantic embeddings with hard negatives. In: Proceedings of BMVC 2018 (2018)"},{"key":"55_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 ACM ICMR 2020 (2020)","DOI":"10.1145\/3372278.3390737"},{"key":"55_CR6","doi-asserted-by":"publisher","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, vol. 13804, pp. 627\u2013643. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-25069-9_40","DOI":"10.1007\/978-3-031-25069-9_40"},{"key":"55_CR7","unstructured":"Guangnan, Y., Yitong, L., et al.: Eventnet: a large scale structured concept library for complex event detection in video. In: Proceedings of ACM MM 2015 (2015)"},{"key":"55_CR8","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"},{"issue":"1","key":"55_CR9","doi-asserted-by":"crossref","first-page":"1","DOI":"10.69711\/Sharda.IJMIR.v11i1.2201","volume":"11","author":"S Heller","year":"2022","unstructured":"Heller, S., Gsteiger, V., Bailer, W., 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. IJMIR 11(1), 1\u201318 (2022)","journal-title":"IJMIR"},{"issue":"1","key":"55_CR10","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1109\/TPAMI.2010.57","volume":"33","author":"H Jegou","year":"2010","unstructured":"Jegou, H., et al.: 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":"55_CR11","doi-asserted-by":"crossref","unstructured":"Li, Y., Song, Y., Cao, L., Tetreault, J., et al.: TGIF: a new dataset and benchmark on animated gif description. In: Proceedings of IEEE CVPR 2016 (2016)","DOI":"10.1109\/CVPR.2016.502"},{"key":"55_CR12","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":"55_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1007\/978-3-030-01216-8_12","volume-title":"Computer Vision \u2013 ECCV 2018","author":"D Mahajan","year":"2018","unstructured":"Mahajan, D., et al.: Exploring the limits of weakly supervised pretraining. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11206, pp. 185\u2013201. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01216-8_12"},{"key":"55_CR14","unstructured":"Markatopoulou, F., Moumtzidou, A., Galanopoulos, D., et al.: ITI-CERTH participation in TRECVID 2017. In: Proceedings of TRECVID 2017 Workshop, USA (2017)"},{"key":"55_CR15","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":"55_CR16","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: Proceedings of the 38th International Conference on Machine Learning (ICML) (2021)"},{"key":"55_CR17","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":"55_CR18","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":"55_CR19","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":"55_CR20","unstructured":"Tan, M., Le, Q.V.: Efficientnet: rethinking model scaling for convolutional neural networks. arXiv preprint arXiv:1905.11946 (2019)"},{"key":"55_CR21","doi-asserted-by":"crossref","unstructured":"Wang, X., et al.: Vatex: a large-scale, high-quality multilingual dataset for video-and-language research. In: Proceedings of IEEE\/CVF ICCV 2019, pp. 4581\u20134591 (2019)","DOI":"10.1109\/ICCV.2019.00468"},{"key":"55_CR22","doi-asserted-by":"crossref","unstructured":"Xu, J., Mei, T., et al.: MSR-VTT: a large video description dataset for bridging video and language. In: Proceedings of IEEE CVPR 2016, pp. 5288\u20135296 (2016)","DOI":"10.1109\/CVPR.2016.571"}],"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_55","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,17]],"date-time":"2024-10-17T04:35:24Z","timestamp":1729139724000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-27077-2_55"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031270765","9783031270772"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-27077-2_55","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"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)"}}]}}