{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T00:58:52Z","timestamp":1730249932499,"version":"3.28.0"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,7,15]]},"DOI":"10.1109\/icme57554.2024.10687655","type":"proceedings-article","created":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T17:24:16Z","timestamp":1727717056000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["ForecasterFlexOBM: A Multi-View Audio-Visual Dataset for Flexible Object-Based Media Production"],"prefix":"10.1109","author":[{"given":"Davide","family":"Berghi","sequence":"first","affiliation":[{"name":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),Guildford,U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Craig","family":"Cieciura","sequence":"additional","affiliation":[{"name":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),Guildford,U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Farshad","family":"Einabadi","sequence":"additional","affiliation":[{"name":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),Guildford,U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maxine","family":"Glancy","sequence":"additional","affiliation":[{"name":"BBC R&D,London,U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Oliver C.","family":"Camilleri","sequence":"additional","affiliation":[{"name":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),Guildford,U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Philip","family":"Foster","sequence":"additional","affiliation":[{"name":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),Guildford,U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Asmar","family":"Nadeem","sequence":"additional","affiliation":[{"name":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),Guildford,U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Faegheh","family":"Sardari","sequence":"additional","affiliation":[{"name":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),Guildford,U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinzheng","family":"Zhao","sequence":"additional","affiliation":[{"name":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),Guildford,U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marco","family":"Volino","sequence":"additional","affiliation":[{"name":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),Guildford,U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Armin","family":"Mustafa","sequence":"additional","affiliation":[{"name":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),Guildford,U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Philip J. B.","family":"Jackson","sequence":"additional","affiliation":[{"name":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),Guildford,U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Adrian","family":"Hilton","sequence":"additional","affiliation":[{"name":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),Guildford,U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Global: video-on-demand users 2018-2027 by segment"},{"key":"ref2","first-page":"63","article-title":"Learning projective shadow textures for neural rendering of human cast shadows from silhouettes","volume-title":"EGSR","author":"Einabadi"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_31"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-017-1013-y"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3604321.3604374"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3565516.3565522"},{"article-title":"Presenting the S3A Object-Based Audio Drama Dataset","year":"2016","author":"Woodcock","key":"ref7"},{"journal-title":"Tech. Rep., International Telecommunications Union","article-title":"ITU-R BS.2076-2: Audio definition model","year":"2019","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.5594\/JMI.2018.2806499"},{"article-title":"Casualty Accessible and Enhanced (A&E) Audio: Trialling Object-Based Accessible TV Audio","volume-title":"AES","author":"Ward","key":"ref10"},{"article-title":"The editing and tech behind Netflix\u2019s Black Mirror: Bandersnatch","year":"2019","author":"Altman","key":"ref11"},{"article-title":"Object-based media report","volume-title":"Tech. Rep.","year":"2021","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3573381.3596156"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.5594\/JMI.2020.2990255"},{"article-title":"Exploring audio device orchestration in workshops with audio professionals","volume-title":"AES","author":"Hentschel","key":"ref15"},{"article-title":"The Impact of New Forms of Media on Production Tools and Practices","volume-title":"IBC","author":"Ward","key":"ref16"},{"key":"ref17","article-title":"Object-Based Media: An Overview Of The User Experience","volume":"390","author":"Glancy","year":"2020","journal-title":"BBC White Paper"},{"article-title":"Forecaster: our experimental object-based weather forecast","year":"2015","author":"Leonard","key":"ref18"},{"article-title":"Tools for 6-DoF immersive audio-visual content capture and production","volume-title":"IBC","author":"Schweiger","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053900"},{"article-title":"Is someone speaking? Exploring long-term temporal features for audio-visual active speaker detection","volume-title":"MM","author":"Tao","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP53017.2021.9733678"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TAP.1986.1143830"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2902489"},{"key":"ref25","first-page":"2051","article-title":"Tracking sound sources for object-based spatial audio in 3D audio-visual production","author":"Mohd Izhar","year":"2020","journal-title":"Forum Acusticum"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.5594\/JMI.2020.2967204"},{"key":"ref27","first-page":"2988","article-title":"PAT: Positiona-ware transformer for dense multi-label action detection","volume-title":"ICCV Workshops","author":"Sardari"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00909"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01921"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01941"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00259"},{"key":"ref32","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","volume-title":"ACL","author":"Chen"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00709"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14283"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/965139.807402"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/MCG.2007.68"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14507"}],"event":{"name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2024,7,15]]},"location":"Niagara Falls, ON, Canada","end":{"date-parts":[[2024,7,19]]}},"container-title":["2024 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10685847\/10687354\/10687655.pdf?arnumber=10687655","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T06:03:42Z","timestamp":1727762622000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10687655\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,15]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/icme57554.2024.10687655","relation":{},"subject":[],"published":{"date-parts":[[2024,7,15]]}}}