{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T04:31:10Z","timestamp":1730262670533,"version":"3.28.0"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,10,31]],"date-time":"2022-10-31T00:00:00Z","timestamp":1667174400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,31]],"date-time":"2022-10-31T00:00:00Z","timestamp":1667174400000},"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":[[2022,10,31]]},"DOI":"10.1109\/ieeeconf56349.2022.10052073","type":"proceedings-article","created":{"date-parts":[[2023,3,7]],"date-time":"2023-03-07T13:41:29Z","timestamp":1678196489000},"page":"1321-1325","source":"Crossref","is-referenced-by-count":1,"title":["Cross-utterance context for multimodal video transcription"],"prefix":"10.1109","author":[{"given":"Roshan","family":"Sharma","sequence":"first","affiliation":[{"name":"Carnegie Mellon University,Pittsburgh,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bhiksha","family":"Raj","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University and Mohamed bin Zayed University of Artificial Intelligence Pittsburgh, USA and Masdar,Abu Dhabi,UAE"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-5514"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953251"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1643"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2928"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1106"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP49672.2021.9362109"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953112"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846320"},{"key":"ref17","article-title":"Aggregated residual transformations for deep neural networks","volume":"abs 1611 5431","author":"xie","year":"2016","journal-title":"CoRR"},{"key":"ref16","article-title":"An image is worth 16×16 words: Transformers for image recognition at scale","volume":"abs 2010 11929","author":"dosovitskiy","year":"2020","journal-title":"CoRR"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref23","article-title":"How2: a large-scale dataset for multimodal language understanding","author":"sanabria","year":"0","journal-title":"Proceedings of the Workshop on Visually Grounded Interaction and Language (ViGIL) NeurIPS"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"journal-title":"The kinetics human action video dataset","year":"2017","author":"zisserman","key":"ref20"},{"key":"ref22","article-title":"Speech summarization using restricted self-attention","volume":"abs 2110 6263","author":"sharma","year":"2021","journal-title":"CoRR"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-2031"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003788"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383466"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414928"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682750"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462439"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.216"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00504"}],"event":{"name":"2022 56th Asilomar Conference on Signals, Systems, and Computers","start":{"date-parts":[[2022,10,31]]},"location":"Pacific Grove, CA, USA","end":{"date-parts":[[2022,11,2]]}},"container-title":["2022 56th Asilomar Conference on Signals, Systems, and Computers"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10051833\/10051818\/10052073.pdf?arnumber=10052073","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,10]],"date-time":"2023-04-10T14:48:11Z","timestamp":1681138091000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10052073\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,31]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/ieeeconf56349.2022.10052073","relation":{},"subject":[],"published":{"date-parts":[[2022,10,31]]}}}