{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T05:28:52Z","timestamp":1774330132888,"version":"3.50.1"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,15]],"date-time":"2023-12-15T00:00:00Z","timestamp":1702598400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,15]],"date-time":"2023-12-15T00:00:00Z","timestamp":1702598400000},"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":[[2023,12,15]]},"DOI":"10.1109\/bigdata59044.2023.10386376","type":"proceedings-article","created":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T18:28:47Z","timestamp":1705948127000},"page":"1450-1459","source":"Crossref","is-referenced-by-count":2,"title":["Multimodal Co-attention Transformer for Video-Based Personality Understanding"],"prefix":"10.1109","author":[{"given":"Mingwei","family":"Sun","sequence":"first","affiliation":[{"name":"University of Maryland,College Park"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kunpeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Maryland,College Park"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Personality: A psychological interpretation","author":"Allport","year":"1937"},{"issue":"2","key":"ref2","article-title":"Personality types as predictors of decision making styles","volume":"22","author":"Riaz","year":"2012","journal-title":"Journal of Behavioural Sciences"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1037\/0021-9010.86.2.326"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1287\/isre.2017.0768"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.ps.41.020190.002221"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1037\/0022-3514.59.6.1216"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/icwsm.v10i1.14738"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1002\/ejsp.2420080405"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1177\/0146167209346309"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2762299"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107715"},{"key":"ref12","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"ref13","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2018.8422105"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICAwST.2017.8256484"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-018-1212-4"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.472"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-49409-8_27"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-49409-8_28"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00681"},{"key":"ref24","first-page":"4","article-title":"Is space-time attention all you need for video understanding?","volume":"2","author":"Bertasius","year":"2021","journal-title":"ICML"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.73"},{"key":"ref27","first-page":"9758","article-title":"Self-supervised learning by cross-modal audio-video clustering","volume":"33","author":"Alwassel","year":"2020","journal-title":"NeurPS"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413869"},{"key":"ref29","first-page":"25","article-title":"Self-supervised multimodal versatile networks","volume":"33","author":"Alayrac","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1980.1163420"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-49220-9"},{"key":"ref32","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint arXiv:1810.04805"},{"key":"ref33","article-title":"Vatt: Transformers for multimodal self-supervised learning from raw video, audio and text","author":"Akbari","year":"2021"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-49409-8_32"},{"key":"ref35","article-title":"Axiomatic attribution for deep networks","author":"Sundararajan","year":"2017"}],"event":{"name":"2023 IEEE International Conference on Big Data (BigData)","location":"Sorrento, Italy","start":{"date-parts":[[2023,12,15]]},"end":{"date-parts":[[2023,12,18]]}},"container-title":["2023 IEEE International Conference on Big Data (BigData)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10385234\/10386078\/10386376.pdf?arnumber=10386376","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T01:56:24Z","timestamp":1706752584000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10386376\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,15]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/bigdata59044.2023.10386376","relation":{},"subject":[],"published":{"date-parts":[[2023,12,15]]}}}