{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,18]],"date-time":"2025-05-18T18:21:16Z","timestamp":1747592476032,"version":"3.40.3"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031064326"},{"type":"electronic","value":"9783031064333"}],"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\/978-3-031-06433-3_16","type":"book-chapter","created":{"date-parts":[[2022,5,14]],"date-time":"2022-05-14T18:03:24Z","timestamp":1652551404000},"page":"182-194","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Learning Video Retrieval Models with\u00a0Relevance-Aware Online Mining"],"prefix":"10.1007","author":[{"given":"Alex","family":"Falcon","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Giuseppe","family":"Serra","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Oswald","family":"Lanz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,5,15]]},"reference":[{"key":"16_CR1","doi-asserted-by":"crossref","unstructured":"Arandjelovic, R., Gronat, P., Torii, A., Pajdla, T., Sivic, J.: Netvlad: CNN architecture for weakly supervised place recognition. In: Proceedings of the IEEE CVPR, pp. 5297\u20135307 (2016)","DOI":"10.1109\/CVPR.2016.572"},{"key":"16_CR2","unstructured":"Baeza-Yates, R., Ribeiro-Neto, B., et al.: Modern Information Retrieval, vol. 463. ACM Press, New York (1999)"},{"key":"16_CR3","doi-asserted-by":"crossref","unstructured":"Chen, S., Zhao, Y., Jin, Q., Wu, Q.: Fine-grained video-text retrieval with hierarchical graph reasoning. In: Proceedings of the IEEE\/CVF CVPR, June 2020","DOI":"10.1109\/CVPR42600.2020.01065"},{"key":"16_CR4","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning, pp. 1597\u20131607. PMLR (2020)"},{"key":"16_CR5","doi-asserted-by":"crossref","unstructured":"Chen, W., Chen, X., Zhang, J., Huang, K.: Beyond triplet loss: a deep quadruplet network for person re-identification. In: Proceedings of the IEEE CVPR, pp. 403\u2013412 (2017)","DOI":"10.1109\/CVPR.2017.145"},{"key":"16_CR6","doi-asserted-by":"crossref","unstructured":"Croitoru, I., Bogolin, S.V., Leordeanu, M., Jin, H., Zisserman, A., Albanie, S., Liu, Y.: Teachtext: Crossmodal generalized distillation for text-video retrieval. In: Proceedings of the IEEE\/CVF ICCV. pp. 11583\u201311593 (2021)","DOI":"10.1109\/ICCV48922.2021.01138"},{"key":"16_CR7","unstructured":"Damen, D., Doughty, H., Farinella, G.M., Furnari, A., Kazakos, E., Ma, J., Moltisanti, D., Munro, J., Perrett, T., Price, W., et al.: Rescaling egocentric vision. IJCV (2021)"},{"key":"16_CR8","volume-title":"Epic-kitchens-100- 2021 challenges report","author":"D Damen","year":"2021","unstructured":"Damen, D., Fragomeni, A., Munro, J., Perrett, T., Whettam, D., Wray, M., Furnari, A., Farinella, G.M., Moltisanti, D.: Epic-kitchens-100- 2021 challenges report. University of Bristol, Tech. rep. (2021)"},{"key":"16_CR9","doi-asserted-by":"crossref","unstructured":"Dong, J., Li, X., Xu, C., Yang, X., Yang, G., Wang, X., Wang, M.: Dual encoding for video retrieval by text. IEEE Transactions on Pattern Analysis and Machine Intelligence (2021)","DOI":"10.1109\/TPAMI.2021.3059295"},{"key":"16_CR10","doi-asserted-by":"crossref","unstructured":"Dzabraev, M., Kalashnikov, M., Komkov, S., Petiushko, A.: MDMMT: multidomain multimodal transformer for video retrieval. In: Proceedings of the IEEE\/CVF CVPR, pp. 3354\u20133363 (2021)","DOI":"10.1109\/CVPRW53098.2021.00374"},{"key":"16_CR11","doi-asserted-by":"crossref","unstructured":"Gabeur, V., Sun, C., Alahari, K., Schmid, C.: Multi-modal transformer for video retrieval. In: Proceedings of the IEEE ECCV. Springer (2020)","DOI":"10.1007\/978-3-030-58548-8_13"},{"key":"16_CR12","doi-asserted-by":"crossref","unstructured":"Gordo, A., Larlus, D.: Beyond instance-level image retrieval: leveraging captions to learn a global visual representation for semantic retrieval. In: Proceedings of the IEEE CVPR, pp. 6589\u20136598 (2017)","DOI":"10.1109\/CVPR.2017.560"},{"key":"16_CR13","unstructured":"Gutmann, M., Hyv\u00e4rinen, A.: Noise-contrastive estimation: a new estimation principle for unnormalized statistical models. In: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics. pp. 297\u2013304. JMLR Workshop and Conference Proceedings (2010)"},{"key":"16_CR14","doi-asserted-by":"crossref","unstructured":"Hadsell, R., Chopra, S., LeCun, Y.: Dimensionality reduction by learning an invariant mapping. In: 2006 IEEE Computer Society CVPR (CVPR 2006). vol. 2, pp. 1735\u20131742. IEEE (2006)","DOI":"10.1109\/CVPR.2006.100"},{"key":"16_CR15","doi-asserted-by":"crossref","unstructured":"Harwood, B., Kumar BG, V., Carneiro, G., Reid, I., Drummond, T.: Smart mining for deep metric learning. In: Proceedings of the IEEE ICCV, pp. 2821\u20132829 (2017)","DOI":"10.1109\/ICCV.2017.307"},{"key":"16_CR16","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE\/CVF CVPR, pp. 9729\u20139738 (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"16_CR17","unstructured":"Hermans, A., Beyer, L., Leibe, B.: In defense of the triplet loss for person re-identification. arXiv preprint arXiv:1703.07737 (2017)"},{"issue":"4","key":"16_CR18","doi-asserted-by":"publisher","first-page":"422","DOI":"10.1145\/582415.582418","volume":"20","author":"K J\u00e4rvelin","year":"2002","unstructured":"J\u00e4rvelin, K., Kek\u00e4l\u00e4inen, J.: Cumulated gain-based evaluation of IR techniques. ACM Trans. Inf. Syst. 20(4), 422\u2013446 (2002)","journal-title":"ACM Trans. Inf. Syst."},{"key":"16_CR19","doi-asserted-by":"crossref","unstructured":"Jiang, Q.Y., He, Y., Li, G., Lin, J., Li, L., Li, W.J.: SVD: a large-scale short video dataset for near-duplicate video retrieval. In: Proceedings of the IEEE\/CVF ICCV, pp. 5281\u20135289 (2019)","DOI":"10.1109\/ICCV.2019.00538"},{"key":"16_CR20","doi-asserted-by":"crossref","unstructured":"Kazakos, E., Nagrani, A., Zisserman, A., Damen, D.: Epic-fusion: audio-visual temporal binding for egocentric action recognition. In: Proceedings of the IEEE\/CVF ICCV, pp. 5492\u20135501 (2019)","DOI":"10.1109\/ICCV.2019.00559"},{"key":"16_CR21","doi-asserted-by":"crossref","unstructured":"Lesk, M.: Automatic sense disambiguation using machine readable dictionaries: how to tell a pine cone from an ice cream cone. In: Proceedings of the 5th Annual International Conference on Systems Documentation, pp. 24\u201326 (1986)","DOI":"10.1145\/318723.318728"},{"key":"16_CR22","unstructured":"Liu, Y., Albanie, S., Nagrani, A., Zisserman, A.: Use what you have: video retrieval using representations from collaborative experts. In: BMVC (2019)"},{"key":"16_CR23","unstructured":"Miech, A., Laptev, I., Sivic, J.: Learning a text-video embedding from incomplete and heterogeneous data. arXiv preprint arXiv:1804.02516 (2018)"},{"issue":"11","key":"16_CR24","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1145\/219717.219748","volume":"38","author":"GA Miller","year":"1995","unstructured":"Miller, G.A.: WordNet: a lexical database for English. Commun. ACM 38(11), 39\u201341 (1995)","journal-title":"Commun. ACM"},{"key":"16_CR25","doi-asserted-by":"crossref","unstructured":"Mithun, N.C., Li, J., Metze, F., Roy-Chowdhury, A.K.: Learning joint embedding with multimodal cues for cross-modal video-text retrieval. In: Proceedings of the 2018 ACM on International Conference on Multimedia Retrieval, pp. 19\u201327 (2018)","DOI":"10.1145\/3206025.3206064"},{"key":"16_CR26","doi-asserted-by":"crossref","unstructured":"Pan, T., Song, Y., Yang, T., Jiang, W., Liu, W.: Videomoco: Contrastive video representation learning with temporally adversarial examples. In: Proceedings of the IEEE\/CVF CVPR. pp. 11205\u201311214 (2021)","DOI":"10.1109\/CVPR46437.2021.01105"},{"key":"16_CR27","doi-asserted-by":"crossref","unstructured":"Qian, R., et al.: Spatiotemporal contrastive video representation learning. In: Proceedings of the IEEE\/CVF CVPR, pp. 6964\u20136974 (2021)","DOI":"10.1109\/CVPR46437.2021.00689"},{"key":"16_CR28","doi-asserted-by":"crossref","unstructured":"Schroff, F., Kalenichenko, D., Philbin, J.: FaceNet: a unified embedding for face recognition and clustering. In: Proceedings of the IEEE CVPR, pp. 815\u2013823 (2015)","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"16_CR29","unstructured":"Sohn, K.: Improved deep metric learning with multi-class n-pair loss objective. In: Michael, I., Jordan, Y.L., Solla, S.A. (eds.) Advances in Neural Information Processing Systems, pp. 1857\u20131865. MIT Press, London (2016)"},{"key":"16_CR30","doi-asserted-by":"crossref","unstructured":"Suh, Y., Han, B., Kim, W., Lee, K.M.: Stochastic class-based hard example mining for deep metric learning. In: Proceedings of the IEEE\/CVF CVPR, pp. 7251\u20137259 (2019)","DOI":"10.1109\/CVPR.2019.00742"},{"key":"16_CR31","doi-asserted-by":"crossref","unstructured":"Wang, X., Zhu, L., Yang, Y.: T2VLAD: global-local sequence alignment for text-video retrieval. In: Proceedings of the IEEE\/CVF CVPR, pp. 5079\u20135088 (2021)","DOI":"10.1109\/CVPR46437.2021.00504"},{"key":"16_CR32","doi-asserted-by":"crossref","unstructured":"Wray, M., Doughty, H., Damen, D.: On semantic similarity in video retrieval. In: Proceedings of the IEEE\/CVF CVPR, pp. 3650\u20133660 (2021)","DOI":"10.1109\/CVPR46437.2021.00365"},{"key":"16_CR33","doi-asserted-by":"crossref","unstructured":"Wray, M., Larlus, D., Csurka, G., Damen, D.: Fine-grained action retrieval through multiple parts-of-speech embeddings. In: Proceedings of the IEEE ICCV, pp. 450\u2013459 (2019)","DOI":"10.1109\/ICCV.2019.00054"},{"key":"16_CR34","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 CVPR, pp. 5288\u20135296 (2016)","DOI":"10.1109\/CVPR.2016.571"},{"key":"16_CR35","doi-asserted-by":"crossref","unstructured":"Xuan, H., Stylianou, A., Liu, X., Pless, R.: Hard negative examples are hard, but useful. In: Proceedings of the IEEE ECCV, pp. 126\u2013142 (2020)","DOI":"10.1007\/978-3-030-58568-6_8"},{"key":"16_CR36","doi-asserted-by":"crossref","unstructured":"Xuan, H., Stylianou, A., Pless, R.: Improved embeddings with easy positive triplet mining. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 2474\u20132482 (2020)","DOI":"10.1109\/WACV45572.2020.9093432"}],"container-title":["Lecture Notes in Computer Science","Image Analysis and Processing \u2013 ICIAP 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-06433-3_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,24]],"date-time":"2024-09-24T20:31:39Z","timestamp":1727209899000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-06433-3_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031064326","9783031064333"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-06433-3_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"15 May 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIAP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Image Analysis and Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lecce","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","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":"23 May 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 May 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iciap2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.iciap2021.org\/","order":11,"name":"conference_url","label":"Conference URL","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":"Microsoft","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"307","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":"168","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":"55% - 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)"}}]}}