{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T11:04:30Z","timestamp":1730199870658,"version":"3.28.0"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,11,16]],"date-time":"2021-11-16T00:00:00Z","timestamp":1637020800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,11,16]],"date-time":"2021-11-16T00:00:00Z","timestamp":1637020800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,11,16]],"date-time":"2021-11-16T00:00:00Z","timestamp":1637020800000},"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":[[2021,11,16]]},"DOI":"10.1109\/avss52988.2021.9663793","type":"proceedings-article","created":{"date-parts":[[2022,1,5]],"date-time":"2022-01-05T15:43:05Z","timestamp":1641397385000},"page":"1-8","source":"Crossref","is-referenced-by-count":5,"title":["From Multimodal to Unimodal Attention in Transformers using Knowledge Distillation"],"prefix":"10.1109","author":[{"given":"Dhruv","family":"Agarwal","sequence":"first","affiliation":[]},{"given":"Tanay","family":"Agrawal","sequence":"additional","affiliation":[]},{"given":"Laura M.","family":"Ferrari","sequence":"additional","affiliation":[]},{"given":"Francois","family":"Bremond","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"journal-title":"Reformer The Efficient Transformer","year":"2020","author":"kitaev","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2070481.2070509"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/2993148.2993176"},{"key":"ref13","article-title":"Representation learning with contrastive predictive coding","author":"oord","year":"2018","journal-title":"arXiv preprint arXiv 1807 03748"},{"key":"ref14","article-title":"The handbook of multimodal-multisensor interfaces","volume":"2","author":"oviatt","year":"2018","journal-title":"Signal processing architectures and detection of emotion and cognition"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref16","first-page":"973","article-title":"Utterance-level multimodal sentiment analysis","volume":"1","author":"p\u00e9rez-rosas","year":"2013","journal-title":"Proceedings annual meeting of the Association for Computational Linguistics"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2020.3038167"},{"key":"ref18","article-title":"Learning an augmented rgb representation with cross-modal knowledge distillation for action detection","volume":"2","author":"rui dai","year":"0","journal-title":"IEEE\/CVF International Conference on Computer Vision (ICCV)"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1208"},{"journal-title":"A simple framework for contrastive learning of visual representations","year":"2020","author":"chen","key":"ref4"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1115"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.417"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00807"},{"journal-title":"Distilling the knowledge in a neural network","year":"2015","author":"hinton","key":"ref8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853739"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/1150402.1150464"},{"key":"ref9","article-title":"Transformers in vision: A survey","author":"khan","year":"2021","journal-title":"arXiv preprint arXiv 2101 06286"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1023\/B:MTAP.0000046380.27575.a5"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"journal-title":"Contrastive representation distillation","year":"2020","author":"tian","key":"ref21"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2017.8019301"},{"journal-title":"Attention is all you need","year":"2017","author":"vaswani","key":"ref23"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/35.41402"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33017216"}],"event":{"name":"2021 17th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)","start":{"date-parts":[[2021,11,16]]},"location":"Washington, DC, USA","end":{"date-parts":[[2021,11,19]]}},"container-title":["2021 17th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9663572\/9663735\/09663793.pdf?arnumber=9663793","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T12:56:50Z","timestamp":1652187410000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9663793\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11,16]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/avss52988.2021.9663793","relation":{},"subject":[],"published":{"date-parts":[[2021,11,16]]}}}