{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,15]],"date-time":"2025-05-15T16:07:25Z","timestamp":1747325245605,"version":"3.40.3"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031278174"},{"type":"electronic","value":"9783031278181"}],"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\/978-3-031-27818-1_5","type":"book-chapter","created":{"date-parts":[[2023,3,30]],"date-time":"2023-03-30T10:20:17Z","timestamp":1680171617000},"page":"54-65","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Less Is More: Similarity Models for\u00a0Content-Based Video Retrieval"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5985-3310","authenticated-orcid":false,"given":"Patrik","family":"Vesel\u00fd","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8082-4509","authenticated-orcid":false,"given":"Ladislav","family":"Pe\u0161ka","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,3,31]]},"reference":[{"key":"5_CR1","doi-asserted-by":"crossref","unstructured":"Berns, F., Rossetto, L., Schoeffmann, K., Beecks, C., Awad, G.: V3C1 dataset: an evaluation of content characteristics. In: ICMR 2019, pp. 334\u2013338. ACM (2019)","DOI":"10.1145\/3323873.3325051"},{"key":"5_CR2","unstructured":"Chen, M., et al.: Generative pretraining from pixels. In: ICML 2020. PMLR (2020)"},{"key":"5_CR3","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: CVPR 2009, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"5_CR4","unstructured":"Dosovitskiy, A., et al.: An image is worth $$16\\times 16$$ words: transformers for image recognition at scale. arXiv (2020)"},{"key":"5_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"630","DOI":"10.1007\/978-3-319-46493-0_38","volume-title":"Computer Vision \u2013 ECCV 2016","author":"K He","year":"2016","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Identity mappings in deep residual networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 630\u2013645. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_38"},{"issue":"11","key":"5_CR6","doi-asserted-by":"publisher","first-page":"1173","DOI":"10.1038\/s41562-020-00951-3","volume":"4","author":"MN Hebart","year":"2020","unstructured":"Hebart, M.N., Zheng, C.Y., Pereira, F., Baker, C.I.: Revealing the multidimensional mental representations of natural objects underlying human similarity judgements. Nat. Hum. Behav. 4(11), 1173\u20131185 (2020)","journal-title":"Nat. Hum. Behav."},{"issue":"1","key":"5_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s13735-021-00225-2","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. Int. J. Multimed. Inf. Retr. 11(1), 1\u201318 (2022). https:\/\/doi.org\/10.1007\/s13735-021-00225-2","journal-title":"Int. J. Multimed. Inf. Retr."},{"key":"5_CR8","doi-asserted-by":"publisher","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","DOI":"10.1007\/978-3-030-98355-0_43"},{"key":"5_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"624","DOI":"10.1007\/978-3-319-06028-6_67","volume-title":"Advances in Information Retrieval","author":"K Hofmann","year":"2014","unstructured":"Hofmann, K., Schuth, A., Bellog\u00edn, A., de Rijke, M.: Effects of position bias on click-based recommender evaluation. In: de Rijke, M., et al. (eds.) ECIR 2014. LNCS, vol. 8416, pp. 624\u2013630. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-06028-6_67"},{"issue":"3","key":"5_CR10","doi-asserted-by":"publisher","first-page":"665","DOI":"10.1016\/S0031-3203(02)00083-3","volume":"36","author":"P Huang","year":"2003","unstructured":"Huang, P., Dai, S.: Image retrieval by texture similarity. Pattern Recogn. 36(3), 665\u2013679 (2003)","journal-title":"Pattern Recogn."},{"key":"5_CR11","doi-asserted-by":"crossref","unstructured":"J\u00e9gou, H., Douze, M., Schmid, C., P\u00e9rez, P.: Aggregating local descriptors into a compact image representation. In: CVPR 2010, pp. 3304\u20133311. IEEE (2010)","DOI":"10.1109\/CVPR.2010.5540039"},{"key":"5_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"790","DOI":"10.1007\/978-3-030-37734-2_71","volume-title":"MultiMedia Modeling","author":"M Kratochv\u00edl","year":"2020","unstructured":"Kratochv\u00edl, M., Vesel\u00fd, P., Mejzl\u00edk, F., Loko\u010d, J.: SOM-hunter: video browsing with relevance-to-SOM feedback loop. In: Ro, Y.M., et al. (eds.) MMM 2020. LNCS, vol. 11962, pp. 790\u2013795. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-37734-2_71"},{"key":"5_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"118","DOI":"10.1007\/978-3-031-17849-8_10","volume-title":"Similarity Search and Applications","author":"M K\u0159enkov\u00e1","year":"2022","unstructured":"K\u0159enkov\u00e1, M., Mic, V., Zezula, P.: Similarity search with the distance density model. In: Skopal, T., Falchi, F., Loko\u010d, J., Sapino, M.L., Bartolini, I., Patella, M. (eds.) SISAP 2022. LNCS, vol. 13590, pp. 118\u2013132. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-17849-8_10"},{"key":"5_CR14","doi-asserted-by":"crossref","unstructured":"Li, X., Xu, C., Yang, G., Chen, Z., Dong, J.: W2VV++ fully deep learning for ad-hoc video search. In: ACM MM 2019, pp. 1786\u20131794 (2019)","DOI":"10.1145\/3343031.3350906"},{"key":"5_CR15","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: TGIF: a new dataset and benchmark on animated GIF description. In: CVPR 2016, pp. 4641\u20134650 (2016)","DOI":"10.1109\/CVPR.2016.502"},{"key":"5_CR16","doi-asserted-by":"publisher","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","DOI":"10.1007\/978-3-030-98355-0_46"},{"issue":"2","key":"5_CR17","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"DG Lowe","year":"2004","unstructured":"Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60(2), 91\u2013110 (2004). https:\/\/doi.org\/10.1023\/B:VISI.0000029664.99615.94","journal-title":"Int. J. Comput. Vis."},{"issue":"2","key":"5_CR18","doi-asserted-by":"publisher","first-page":"461","DOI":"10.1016\/j.ipm.2006.07.014","volume":"43","author":"TC Lu","year":"2007","unstructured":"Lu, T.C., Chang, C.C.: Color image retrieval technique based on color features and image bitmap. Inf. Process. Manag. 43(2), 461\u2013472 (2007)","journal-title":"Inf. Process. Manag."},{"key":"5_CR19","doi-asserted-by":"publisher","first-page":"338","DOI":"10.1111\/j.1478-4408.1976.tb03301.x","volume":"92","author":"K McLaren","year":"2008","unstructured":"McLaren, K.: The development of the CIE 1976 (L*a*b*) uniform colour-space and colour-difference formula. J. Soc. Dyers Colour. 92, 338\u2013341 (2008)","journal-title":"J. Soc. Dyers Colour."},{"issue":"8","key":"5_CR20","doi-asserted-by":"publisher","first-page":"2648","DOI":"10.1111\/cogs.12670","volume":"42","author":"JC Peterson","year":"2018","unstructured":"Peterson, J.C., Abbott, J.T., Griffiths, T.L.: Evaluating (and improving) the correspondence between deep neural networks and human representations. Cogn. Sci. 42(8), 2648\u20132669 (2018)","journal-title":"Cogn. Sci."},{"key":"5_CR21","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML 2019, pp. 8748\u20138763. PMLR (2021)"},{"key":"5_CR22","doi-asserted-by":"crossref","unstructured":"Roads, B.D., Love, B.C.: Enriching ImageNet with human similarity judgments and psychological embeddings. In: CVPR 2021, pp. 3547\u20133557. IEEE\/CVF (2021)","DOI":"10.1109\/CVPR46437.2021.00355"},{"key":"5_CR23","doi-asserted-by":"crossref","unstructured":"Skopal, T.: On visualizations in the role of universal data representation. In: ICMR 2020, pp. 362\u2013367. ACM (2020)","DOI":"10.1145\/3372278.3390743"},{"key":"5_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"270","DOI":"10.1007\/978-3-030-01424-7_27","volume-title":"Artificial Neural Networks and Machine Learning \u2013 ICANN 2018","author":"C Tan","year":"2018","unstructured":"Tan, C., Sun, F., Kong, T., Zhang, W., Yang, C., Liu, C.: A survey on deep transfer learning. In: K\u016frkov\u00e1, V., Manolopoulos, Y., Hammer, B., Iliadis, L., Maglogiannis, I. (eds.) ICANN 2018. LNCS, vol. 11141, pp. 270\u2013279. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01424-7_27"},{"key":"5_CR25","unstructured":"Tan, M., Le, Q.: EfficientNet: rethinking model scaling for convolutional neural networks. In: ICML 2019, pp. 6105\u20136114. PMLR (2019)"},{"key":"5_CR26","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"5_CR27","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: 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\/978-3-031-27818-1_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,30]],"date-time":"2023-03-30T10:22:28Z","timestamp":1680171748000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-27818-1_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031278174","9783031278181"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-27818-1_5","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":"31 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)"}}]}}