{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T15:59:50Z","timestamp":1772553590636,"version":"3.50.1"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,1,5]],"date-time":"2023-01-05T00:00:00Z","timestamp":1672876800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,5]],"date-time":"2023-01-05T00:00:00Z","timestamp":1672876800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1722822,1750439"],"award-info":[{"award-number":["1722822,1750439"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01MH125740,R01MH096951,U01MH116925"],"award-info":[{"award-number":["R01MH125740,R01MH096951,U01MH116925"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,1,5]]},"DOI":"10.1109\/fg57933.2023.10042612","type":"proceedings-article","created":{"date-parts":[[2023,2,16]],"date-time":"2023-02-16T23:02:10Z","timestamp":1676588530000},"page":"1-7","source":"Crossref","is-referenced-by-count":6,"title":["Face-to-Face Contrastive Learning for Social Intelligence Question-Answering"],"prefix":"10.1109","author":[{"given":"Alex","family":"Wilf","sequence":"first","affiliation":[{"name":"Language Technologies Institute, Carnegie Mellon University"}]},{"given":"Martin Q.","family":"Ma","sequence":"additional","affiliation":[{"name":"Language Technologies Institute, Carnegie Mellon University"}]},{"given":"Paul Pu","family":"Liang","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Machine Learning Department"}]},{"given":"Amir","family":"Zadeh","sequence":"additional","affiliation":[{"name":"Amazon Alexa AI"}]},{"given":"Louis-Philippe","family":"Morency","sequence":"additional","affiliation":[{"name":"Language Technologies Institute, Carnegie Mellon University"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Beit: Bert pre-training of image transformers","author":"Bao","year":"2021","journal-title":"arXiv preprint"},{"key":"ref2","author":"Brody","year":"2022","journal-title":"How Attentive are Graph Attention Networks?"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01567"},{"key":"ref4","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"International conference on machine learning","author":"Chen"},{"key":"ref5","article-title":"Big self-supervised models are strong semi-supervised learners","author":"Chen","year":"2020","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2019.02063"},{"key":"ref8","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00949"},{"key":"ref10","article-title":"Fast graph representation learning with pytorch geometric","author":"Fey","year":"2019","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2005.1555942"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01007"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380027"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3390\/technologies9010002"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00358"},{"key":"ref18","article-title":"Nemo: a toolkit for building ai applications using neural modules","author":"Kuchaiev","year":"2019","journal-title":"arXiv preprint"},{"key":"ref19","article-title":"Mcqa: Multimodal co-attention based network for question answering","author":"Kumar","year":"2020","journal-title":"arXiv preprint"},{"key":"ref20","article-title":"Albert: A lite bert for self-supervised learning of language representations","author":"Lan","year":"2019","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d18-1167"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.208"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.29007\/1mjd"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2005605"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.457"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.501"},{"key":"ref27","first-page":"2207","article-title":"Cross-lingual retrieval for iterative self-supervised training","volume":"33","author":"Tran","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.29007\/9qvn"},{"key":"ref29","article-title":"Deep graph infomax","author":"Veli\u010dkovi\u0107","year":"2018","journal-title":"arXiv preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00999"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403043"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00992"},{"key":"ref33","article-title":"Mtag: Modal-temporal attention graph for unaligned human multimodal language sequences","author":"Yang","year":"2020","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.79"},{"key":"ref35","first-page":"5812","article-title":"Graph contrastive learning with augmentations","volume":"33","author":"You","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01359"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00901"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1115"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12021"},{"key":"ref40","article-title":"Factorized multimodal transformer for multimodal sequential learning","author":"Zadeh","year":"2019","journal-title":"arXiv preprint"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01589"},{"key":"ref42","first-page":"7025","article-title":"Contrastive learning of global and local video representations","volume":"34","author":"Zeng","year":"2021","journal-title":"Advances in Neural Information Processing Systems"}],"event":{"name":"2023 IEEE 17th International Conference on Automatic Face and Gesture Recognition (FG)","location":"Waikoloa Beach, HI, USA","start":{"date-parts":[[2023,1,5]]},"end":{"date-parts":[[2023,1,8]]}},"container-title":["2023 IEEE 17th International Conference on Automatic Face and Gesture Recognition (FG)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10042469\/10042499\/10042612.pdf?arnumber=10042612","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T14:46:32Z","timestamp":1707835592000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10042612\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,5]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/fg57933.2023.10042612","relation":{},"subject":[],"published":{"date-parts":[[2023,1,5]]}}}