{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T01:40:52Z","timestamp":1755826852080,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":44,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"SNSF Sinergia","award":["198632"],"award-info":[{"award-number":["198632"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3613434","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:26:54Z","timestamp":1698391614000},"page":"9355-9359","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Encoding and Decoding Narratives: Datafication and Alternative Access Models for Audiovisual Archives"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6866-1409","authenticated-orcid":false,"given":"Yuchen","family":"Yang","sequence":"first","affiliation":[{"name":"EPFL, Lausanne, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"e_1_3_2_1_2_1","volume-title":"Comm: A core ontology for multimediaannotation. Handbook on Ontologies","author":"Arndt Richard","year":"2009","unstructured":"Richard Arndt, Rapha\u00ebl Troncy, Steffen Staab, and Lynda Hardman. 2009. Comm: A core ontology for multimediaannotation. Handbook on Ontologies (2009), 403--421."},{"key":"e_1_3_2_1_3_1","volume-title":"Introduction: Special Issue on AudioVisual Data in DH. DHQ: Digital Humanities Quarterly 15, 1","author":"Arnold Taylor","year":"2021","unstructured":"Taylor Arnold, Stefania Scagliola, Lauren Tilton, and Jasmijn Van Gorp. 2021. Introduction: Special Issue on AudioVisual Data in DH. DHQ: Digital Humanities Quarterly 15, 1 (2021)."},{"volume-title":"Narrative environments and experience design: Space as a medium of communication","author":"Austin Tricia","key":"e_1_3_2_1_4_1","unstructured":"Tricia Austin. 2020. Narrative environments and experience design: Space as a medium of communication. Routledge."},{"key":"e_1_3_2_1_5_1","volume-title":"7th Workshop on Computational Models of Narrative (CMN","author":"Bartalesi Valentina","year":"2016","unstructured":"Valentina Bartalesi, Carlo Meghini, and Daniele Metilli. 2016. Steps towards a formal ontology of narratives based on narratology. In 7th Workshop on Computational Models of Narrative (CMN 2016). Schloss Dagstuhl-Leibniz-Zentrum fuer Informatik."},{"key":"e_1_3_2_1_6_1","volume-title":"Comparative K-Pop Choreography Analysis through Deep-Learning Pose Estimation across a Large Video Corpus. DHQ: Digital Humanities Quarterly 15, 1","author":"Broadwell Peter","year":"2021","unstructured":"Peter Broadwell and Timothy R Tangherlini. 2021. Comparative K-Pop Choreography Analysis through Deep-Learning Pose Estimation across a Large Video Corpus. DHQ: Digital Humanities Quarterly 15, 1 (2021)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1080\/00393541.2018.1442548"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2022.103581"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISIC.2012.6398257"},{"key":"e_1_3_2_1_10_1","first-page":"1","article-title":"Exploring Film Language with a Digital Analysis Tool","volume":"15","author":"Cooper Allison","year":"2021","unstructured":"Allison Cooper, Fernando Nascimento, and David Francis. 2021. Exploring Film Language with a Digital Analysis Tool: The Case of Kinolab. DHQ: Digital Humanities Quarterly 15, 1 (2021), 1--29.","journal-title":"The Case of Kinolab. DHQ: Digital Humanities Quarterly"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.datak.2021.101977"},{"volume-title":"Multimedia Storage and Archiving Systems III","author":"de Vries Arjen P","key":"e_1_3_2_1_12_1","unstructured":"Arjen P de Vries and HM Blanken. 1998. Database technology and the management of multimedia data in the Mirror project. In Multimedia Storage and Archiving Systems III, Vol. 3527. SPIE, 443--453."},{"key":"e_1_3_2_1_13_1","volume-title":"Bringing heritage sites to life for visitors: towards a conceptual framework for immersive experience. Advances in Hospitality and Tourism Research (AHTR)","author":"Dogan V\u0130N\u00c7","year":"2020","unstructured":"EV\u0130N\u00c7 Dogan and M Hamdi KAN. 2020. Bringing heritage sites to life for visitors: towards a conceptual framework for immersive experience. Advances in Hospitality and Tourism Research (AHTR) (2020), 1--24."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00374"},{"key":"e_1_3_2_1_15_1","volume-title":"Clip2video: Mastering video-text retrieval via image clip. arXiv preprint arXiv:2106.11097","author":"Fang Han","year":"2021","unstructured":"Han Fang, Pengfei Xiong, Luhui Xu, and Yu Chen. 2021. Clip2video: Mastering video-text retrieval via image clip. arXiv preprint arXiv:2106.11097 (2021)."},{"key":"e_1_3_2_1_16_1","volume-title":"Methods and Advanced Tools for the Analysis of Film Colors in Digital Humanities. DHQ: Digital Humanities Quarterly 14, 4","author":"Flueckiger Barbara","year":"2020","unstructured":"Barbara Flueckiger and Gaudenz Halter. 2020. Methods and Advanced Tools for the Analysis of Film Colors in Digital Humanities. DHQ: Digital Humanities Quarterly 14, 4 (2020)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00524"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-09589-9"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_13"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.5749\/movingimage.15.2.0082"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531960"},{"key":"e_1_3_2_1_22_1","volume-title":"Deep fragment embeddings for bidirectional image sentence mapping. Advances in neural information processing systems 27","author":"Karpathy Andrej","year":"2014","unstructured":"Andrej Karpathy, Armand Joulin, and Li F Fei-Fei. 2014. Deep fragment embeddings for bidirectional image sentence mapping. Advances in neural information processing systems 27 (2014)."},{"key":"e_1_3_2_1_23_1","volume-title":"Computational Archives for Experimental Museology. In International Conference on Emerging Technologies and the Digital Transformation of Museums and Heritage Sites. Springer, 3--18","author":"Kenderdine Sarah","year":"2021","unstructured":"Sarah Kenderdine, Ingrid Mason, and Lily Hibberd. 2021. Computational Archives for Experimental Museology. In International Conference on Emerging Technologies and the Digital Transformation of Museums and Heritage Sites. Springer, 3--18."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3035918.3054775"},{"key":"e_1_3_2_1_25_1","volume-title":"Mdmmt-2: Multidomain multimodal transformer for video retrieval, one more step towards generalization. arXiv preprint arXiv:2203.07086","author":"Kunitsyn Alexander","year":"2022","unstructured":"Alexander Kunitsyn, Maksim Kalashnikov, Maksim Dzabraev, and Andrei Ivaniuta. 2022. Mdmmt-2: Multidomain multimodal transformer for video retrieval, one more step towards generalization. arXiv preprint arXiv:2203.07086 (2022)."},{"volume-title":"Introduction to MPEG-7: multimedia content description interface","author":"Manjunath Bangalore S","key":"e_1_3_2_1_26_1","unstructured":"Bangalore S Manjunath, Philippe Salembier, and Thomas Sikora. 2002. Introduction to MPEG-7: multimedia content description interface. John Wiley & Sons."},{"key":"e_1_3_2_1_27_1","volume-title":"Nanne van Noord, and Giovanna Fossati.","author":"Masson Eef","year":"2020","unstructured":"Eef Masson, Christian Gosvig Olesen, Nanne van Noord, and Giovanna Fossati. 2020. Exploring Digitised Moving Image Collections: The SEMIA Project, Visual Analysis and the Turn to Abstraction. DHQ: Digital Humanities Quarterly 4 (2020)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00990"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-77004-4_1"},{"key":"e_1_3_2_1_31_1","volume-title":"Robust speech recognition via large-scale weak supervision. arXiv preprint arXiv:2212.04356","author":"Radford Alec","year":"2022","unstructured":"Alec Radford, JongWook Kim, Tao Xu, Greg Brockman, Christine McLeavey, and Ilya Sutskever. 2022. Robust speech recognition via large-scale weak supervision. arXiv preprint arXiv:2212.04356 (2022)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3281375.3281386"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0987-1"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-67835-7_38"},{"key":"e_1_3_2_1_35_1","volume-title":"Multimedia metadata standards. Multimedia semantics: Metadata, analysis and interaction","author":"Schallauer Peter","year":"2011","unstructured":"Peter Schallauer, Werner Bailer, Rapha\u00ebl Troncy, and Florian Kaiser. 2011. Multimedia metadata standards. Multimedia semantics: Metadata, analysis and interaction (2011), 129--144."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01939"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3391614.3393654"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654948"},{"key":"e_1_3_2_1_40_1","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision. 322--330","author":"Ma Xingjun","year":"2019","unstructured":"YisenWang, Xingjun Ma, Zaiyi Chen, Yuan Luo, Jinfeng Yi, and James Bailey. 2019. Symmetric cross entropy for robust learning with noisy labels. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 322--330."},{"key":"e_1_3_2_1_41_1","volume-title":"The Media Ecology Project: Collaborative DH Synergies to Produce New Research in Visual Culture History. DHQ: Digital Humanities Quarterly 15, 1","author":"Williams Mark","year":"2021","unstructured":"Mark Williams and John Bell. 2021. The Media Ecology Project: Collaborative DH Synergies to Produce New Research in Visual Culture History. DHQ: Digital Humanities Quarterly 15, 1 (2021)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"e_1_3_2_1_43_1","volume-title":"CLIP-ViP: Adapting Pre-trained Image-Text Model to Video-Language Representation Alignment. arXiv preprint arXiv:2209.06430","author":"Xue Hongwei","year":"2022","unstructured":"Hongwei Xue, Yuchong Sun, Bei Liu, Jianlong Fu, Ruihua Song, Houqiang Li, and Jiebo Luo. 2022. CLIP-ViP: Adapting Pre-trained Image-Text Model to Video-Language Representation Alignment. arXiv preprint arXiv:2209.06430 (2022)."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_29"}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Ottawa ON Canada","acronym":"MM '23"},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3613434","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3613434","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:01:06Z","timestamp":1755820866000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3613434"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":44,"alternative-id":["10.1145\/3581783.3613434","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3613434","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}