{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T07:36:28Z","timestamp":1742974588308,"version":"3.40.3"},"publisher-location":"Cham","reference-count":31,"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_38","type":"book-chapter","created":{"date-parts":[[2023,3,28]],"date-time":"2023-03-28T05:03:10Z","timestamp":1679979790000},"page":"489-501","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["People@Places and\u00a0ToDY: Two Datasets for\u00a0Scene Classification in\u00a0Media Production and\u00a0Archiving"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2442-4900","authenticated-orcid":false,"given":"Werner","family":"Bailer","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7113-0038","authenticated-orcid":false,"given":"Hannes","family":"Fassold","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,3,29]]},"reference":[{"key":"38_CR1","unstructured":"Abu-El-Haija, S., et al.: Youtube-8m: A large-scale video classification benchmark. arXiv preprint arXiv:1609.08675 (2016)"},{"key":"38_CR2","unstructured":"Arijon, D.: Grammar of the film language. Silman-James Press (1991)"},{"issue":"3","key":"38_CR3","doi-asserted-by":"publisher","first-page":"187","DOI":"10.3169\/mta.4.187","volume":"4","author":"G Awad","year":"2016","unstructured":"Awad, G., Snoek, C.G., Smeaton, A.F., Qu\u00e9not, G.: Trecvid semantic indexing of video: a 6-year retrospective. ITE Trans. Media Technol. Appl. 4(3), 187\u2013208 (2016)","journal-title":"ITE Trans. Media Technol. Appl."},{"issue":"10","key":"38_CR4","doi-asserted-by":"publisher","first-page":"3390","DOI":"10.3390\/app10103390","volume":"10","author":"HY Bak","year":"2020","unstructured":"Bak, H.Y., Park, S.B.: Comparative study of movie shot classification based on semantic segmentation. Appl. Sci. 10(10), 3390 (2020)","journal-title":"Appl. Sci."},{"key":"38_CR5","unstructured":"Bochkovskiy, A., Wang, C.Y., Liao, H.Y.M.: Yolov4: Optimal speed and accuracy of object detection. ArXiv abs\/2004.10934 (2020)"},{"issue":"4","key":"38_CR6","doi-asserted-by":"publisher","first-page":"656","DOI":"10.2307\/209373","volume":"21","author":"S Boggs","year":"1931","unstructured":"Boggs, S.: Seasonal variations in daylight, twilight, and darkness. Geogr. Rev. 21(4), 656\u2013659 (1931)","journal-title":"Geogr. Rev."},{"key":"38_CR7","doi-asserted-by":"crossref","unstructured":"Cheng, P., Zhou, J.: Automatic season classification of outdoor photos. In: 2011 Third International Conference on Intelligent Human-Machine Systems and Cybernetics. vol. 1, pp. 46\u201349. IEEE (2011)","DOI":"10.1109\/IHMSC.2011.18"},{"key":"38_CR8","doi-asserted-by":"crossref","unstructured":"Deng, J., Guo, J., Zhou, Y., Yu, J., Kotsia, I., Zafeiriou, S.: Retinaface: Single-stage dense face localisation in the wild. arXiv preprint arXiv:1905.00641 (2019)","DOI":"10.1109\/CVPR42600.2020.00525"},{"key":"38_CR9","unstructured":"ETSI: Ts 102 822-3-1 v1.9.1 - broadcast and on-line services: Search, select, and rightful use of content on personal storage systems (tv-anytime); part 3: Metadata; sub-part 1: Phase 1 - metadata schemas. Tech. rep. (2015)"},{"key":"38_CR10","unstructured":"Fairbanks, A.T., Fairbanks, E.F.: Human proportions for artists. Fairbanks Art and Books (2005)"},{"key":"38_CR11","unstructured":"Galvane, Q.: Automatic Cinematography and Editing in Virtual Environments. Ph.D. thesis, Universit\u00e9 Grenoble Alpes (ComUE) (2015)"},{"key":"38_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. arXiv preprint arXiv:2111.06377 (2021)","DOI":"10.1109\/CVPR52688.2022.01553"},{"issue":"6","key":"38_CR13","doi-asserted-by":"crossref","first-page":"1180","DOI":"10.1002\/asi.21327","volume":"61","author":"B Huurnink","year":"2010","unstructured":"Huurnink, B., Hollink, L., Van Den Heuvel, W., De Rijke, M.: Search behavior of media professionals at an audiovisual archive: a transaction log analysis. J. Am. Soc. Inform. Sci. Technol. 61(6), 1180\u20131197 (2010)","journal-title":"J. Am. Soc. Inform. Sci. Technol."},{"key":"38_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"541","DOI":"10.1007\/978-3-030-66096-3_37","volume-title":"Computer Vision \u2013 ECCV 2020 Workshops","author":"I Kissos","year":"2020","unstructured":"Kissos, I., Fritz, L., Goldman, M., Meir, O., Oks, E., Kliger, M.: Beyond Weak Perspective for Monocular 3D Human Pose Estimation. In: Bartoli, A., Fusiello, A. (eds.) ECCV 2020. LNCS, vol. 12536, pp. 541\u2013554. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-66096-3_37"},{"key":"38_CR15","doi-asserted-by":"crossref","unstructured":"Loper, M., Mahmood, N., Romero, J., Pons-Moll, G., Black, M.J.: SMPL: a skinned multi-person linear model. ACM Trans. Graphics (Proc. SIGGRAPH Asia) 34(6), 248:1\u2013248:16 (2015)","DOI":"10.1145\/2816795.2818013"},{"key":"38_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"614","DOI":"10.1007\/978-3-030-01249-6_37","volume-title":"Computer Vision \u2013 ECCV 2018","author":"T von Marcard","year":"2018","unstructured":"von Marcard, T., Henschel, R., Black, M.J., Rosenhahn, B., Pons-Moll, G.: Recovering accurate 3D human pose in the wild using IMUs and a moving camera. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11214, pp. 614\u2013631. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01249-6_37"},{"key":"38_CR17","doi-asserted-by":"publisher","unstructured":"Mihail, R.P., Workman, S., Bessinger, Z., Jacobs, N.: Sky segmentation in the wild: An empirical study. In: IEEE Winter Conference on Applications of Computer Vision (WACV),D pp. 1\u20136 (2016). https:\/\/doi.org\/10.1109\/WACV.2016.7477637,acceptance rate: 42.3%","DOI":"10.1109\/WACV.2016.7477637"},{"key":"38_CR18","doi-asserted-by":"crossref","unstructured":"Qassim, H., Verma, A., Feinzimer, D.: Compressed residual-vgg16 cnn model for big data places image recognition. In: 2018 IEEE 8th Annual Computing and Communication Workshop and Conference (CCWC), pp. 169\u2013175. IEEE (2018)","DOI":"10.1109\/CCWC.2018.8301729"},{"key":"38_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1007\/978-3-030-58621-8_2","volume-title":"Computer Vision \u2013 ECCV 2020","author":"A Rao","year":"2020","unstructured":"Rao, A., et al.: A unified framework for shot type classification based on subject centric lens. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12356, pp. 17\u201334. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58621-8_2"},{"key":"38_CR20","doi-asserted-by":"crossref","unstructured":"Savardi, M., Signoroni, A., Migliorati, P., Benini, S.: Shot scale analysis in movies by convolutional neural networks. In: 2018 25th IEEE International Conference on Image Processing (ICIP), pp. 2620\u20132624. IEEE (2018)","DOI":"10.1109\/ICIP.2018.8451474"},{"key":"38_CR21","doi-asserted-by":"crossref","unstructured":"Singh, A., et al.: Flava: A foundational language and vision alignment model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15638\u201315650 (2022)","DOI":"10.1109\/CVPR52688.2022.01519"},{"key":"38_CR22","doi-asserted-by":"crossref","unstructured":"Sun, Y., et al.: Monocular, one-stage, regression of multiple 3d people. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11179\u201311188 (2021)","DOI":"10.1109\/ICCV48922.2021.01099"},{"key":"38_CR23","unstructured":"Tan, M., Le, Q.: Efficientnet: Rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning, pp. 6105\u20136114. PMLR (2019)"},{"issue":"11","key":"38_CR24","doi-asserted-by":"publisher","first-page":"1276","DOI":"10.1175\/1520-0477(1983)064<1276:WATS>2.0.CO;2","volume":"64","author":"KE Trenberth","year":"1983","unstructured":"Trenberth, K.E.: What are the seasons? Bull. Am. Meteor. Soc. 64(11), 1276\u20131282 (1983)","journal-title":"Bull. Am. Meteor. Soc."},{"key":"38_CR25","doi-asserted-by":"crossref","unstructured":"Wang, C.Y., Bochkovskiy, A., Liao, H.Y.M.: Scaled-yolov4: Scaling cross stage partial network. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13029\u201313038 (2021)","DOI":"10.1109\/CVPR46437.2021.01283"},{"key":"38_CR26","doi-asserted-by":"crossref","unstructured":"Wang, Q., Xie, J., Zuo, W., Zhang, L., Li, P.: Deep cnns meet global covariance pooling: Better representation and generalization. IEEE Trans. Pattern Anal. Mach. Intell. 43(8), 2582\u20132597 (2020)","DOI":"10.1109\/TPAMI.2020.2974833"},{"key":"38_CR27","doi-asserted-by":"publisher","unstructured":"Wightman, R.: Pytorch image models. https:\/\/github.com\/rwightman\/pytorch-image-models (2019). https:\/\/doi.org\/10.5281\/zenodo.4414861","DOI":"10.5281\/zenodo.4414861"},{"key":"38_CR28","unstructured":"Xiao, T., Dollar, P., Singh, M., Mintun, E., Darrell, T., Girshick, R.: Early convolutions help transformers see better. In: Advances in Neural Information Processing Systems, vol. 34 (2021)"},{"key":"38_CR29","doi-asserted-by":"crossref","unstructured":"Yang, S., Luo, P., Loy, C.C., Tang, X.: Wider face: A face detection benchmark. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5525\u20135533 (2016)","DOI":"10.1109\/CVPR.2016.596"},{"key":"38_CR30","unstructured":"Yuan, L., et al.: Florence: A new foundation model for computer vision. arXiv preprint arXiv:2111.11432 (2021)"},{"issue":"6","key":"38_CR31","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\/978-3-031-27077-2_38","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,9]],"date-time":"2023-12-09T19:18:34Z","timestamp":1702149514000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-27077-2_38"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031270765","9783031270772"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-27077-2_38","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)"}}]}}