{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T17:28:06Z","timestamp":1770917286728,"version":"3.50.1"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10094781","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":9,"title":["A Dataset for Audio-Visual Sound Event Detection in Movies"],"prefix":"10.1109","author":[{"given":"Rajat","family":"Hebbar","sequence":"first","affiliation":[{"name":"University of Southern California,Signal Analysis and Interpretation Laboratory"}]},{"given":"Digbalay","family":"Bose","sequence":"additional","affiliation":[{"name":"University of Southern California,Signal Analysis and Interpretation Laboratory"}]},{"given":"Krishna","family":"Somandepalli","sequence":"additional","affiliation":[{"name":"University of Southern California,Signal Analysis and Interpretation Laboratory"}]},{"given":"Veena","family":"Vijai","sequence":"additional","affiliation":[{"name":"University of Southern California,Signal Analysis and Interpretation Laboratory"}]},{"given":"Shrikanth","family":"Narayanan","sequence":"additional","affiliation":[{"name":"University of Southern California,Signal Analysis and Interpretation Laboratory"}]}],"member":"263","reference":[{"key":"ref13","article-title":"An introduction to audio post-production for film","author":"nozaic","year":"2006","journal-title":"Thesis Stellenbosch Stellenbosch University"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref12","first-page":"1","article-title":"Machine learning for music genre: multifaceted review and experimentation with audioset","author":"ram\u00edrez","year":"2019","journal-title":"Journal of Intelligent Information Systems"},{"key":"ref34","article-title":"Learning from between-class examples for deep sound recognition","author":"tokozume","year":"2017"},{"key":"ref37","article-title":"Supervised multimodal bitransformers for classifying images and text","author":"kiela","year":"2019"},{"key":"ref15","article-title":"Captioning sound effects in tv and movies – 3play media","year":"0"},{"key":"ref36","article-title":"Learning transferable visual models from natural language supervision","author":"radford","year":"2021","journal-title":"ICML"},{"key":"ref14","article-title":"Real, foley or syntheticƒ an evaluation of everyday walking sounds","author":"gotzen","year":"2013","journal-title":"Proceedings of SMC"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CBMI.2013.6576546"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5361"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1462"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.4304\/jmm.8.2.113-120"},{"key":"ref2","year":"2018","journal-title":"Identifying sounds in audio streams"},{"key":"ref1","year":"2021","journal-title":"Discover built-in sound classification in soundanalysis"},{"key":"ref39","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018"},{"key":"ref17","first-page":"486","article-title":"Freesound datasets: a platform for the creation of open audio datasets","author":"fonseca","year":"2017","journal-title":"Proceedings of the 18th ISMIR Conference"},{"key":"ref38","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3133208"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.33682\/006b-jx26"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2015.06.026"},{"key":"ref24","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","author":"touvron","year":"2021","journal-title":"International Conference on Machine Learning"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-698"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01271"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/78"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2655045"},{"key":"ref22","article-title":"Vatt: Transformers for multimodal self-supervised learning from raw video, audio and text","volume":"34","author":"akbari","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3422852.3423486"},{"key":"ref27","article-title":"Attention bottlenecks for multimodal fusion","volume":"34","author":"nagrani","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00639"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0249957"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"key":"ref4","article-title":"Dcase 2017 challenge setup: Tasks, datasets and baseline system","author":"mesaros","year":"2017","journal-title":"DCASE 2017-Workshop on Detection and Classification of Acoustic Scenes and Events"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1366"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.5626\/JCSE.2012.6.1.40"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3050265"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10094781.pdf?arnumber=10094781","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:04:27Z","timestamp":1700507067000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10094781\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10094781","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}