{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T04:59:47Z","timestamp":1781585987353,"version":"3.54.5"},"reference-count":60,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,20]],"date-time":"2024-12-20T00:00:00Z","timestamp":1734652800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,20]],"date-time":"2024-12-20T00:00:00Z","timestamp":1734652800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004317","name":"Shihezi University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004317","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004317","name":"Shihezi University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004317","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,12,20]]},"DOI":"10.1109\/dsit61374.2024.10881540","type":"proceedings-article","created":{"date-parts":[[2025,2,18]],"date-time":"2025-02-18T18:18:17Z","timestamp":1739902697000},"page":"1-11","source":"Crossref","is-referenced-by-count":3,"title":["MMSFD: Multi-grained and Multi-modal Fusion for Short Video Fake News Detection"],"prefix":"10.1109","author":[{"given":"Shuai","family":"Ren","sequence":"first","affiliation":[{"name":"Shihezi University,School of Information Science and Technology,Shihezi,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yahui","family":"Liu","sequence":"additional","affiliation":[{"name":"Shihezi University,School of Information Science and Technology,Shihezi,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yaping","family":"Zhu","sequence":"additional","affiliation":[{"name":"Shihezi University,School of Information Science and Technology,Shihezi,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wanlong","family":"Bing","sequence":"additional","affiliation":[{"name":"Shihezi University,School of Information Science and Technology,Shihezi,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongliang","family":"Ma","sequence":"additional","affiliation":[{"name":"Shihezi University,School of Information Science and Technology,Shihezi,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing Jiaotong University,School of Computer Science and Information Technology,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Tiktok vs. youtube: Which one is right for you?","author":"Smith","year":"2024"},{"key":"ref2","volume-title":"Tiktok statistics you need to know","author":"Dean","year":"2024"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612426"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-5316"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-42699-6_8"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.115412"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3591106.3592271"},{"key":"ref8","article-title":"NLP-based feature extraction for the detection of COVID-19 misinformation videos on YouTube","volume-title":"Proceedings of the 1st Workshop on NLP for COVID-19 at ACL 2020","author":"Medina Serrano"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1108\/OIR-03-2018-0101"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i12.26689"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/BigData52589.2021.9671928"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3511968"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19\u20131423"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref15","article-title":"Internvid: A large-scale video-text dataset for multimodal understanding and generation","author":"Wang","year":"2024"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3450004"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1022"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/1963405.1963500"},{"key":"ref19","first-page":"3818","article-title":"Detecting rumors from microblogs with recurrent neural networks","volume-title":"Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence","author":"Ma"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/545"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i1.16080"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2015.7113322"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2019.00062"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref26","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219903"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313552"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3481548"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2021.102610"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-47436-2_27"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i4.25670"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3042055"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330935"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2114388118"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1093\/jcmc\/zmab010"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3340555.3353763"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-10117-y"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482212"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02214"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00638"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.544"},{"key":"ref43","article-title":"Violet : End-to-end video-language transformers with masked visualtoken modeling","author":"Fu","year":"2022"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01589"},{"key":"ref45","first-page":"38728","article-title":"mPLUG2: A modularized multi-modal foundation model across text, image and video","volume-title":"Proceedings of the 40th International Conference on Machine Learning","author":"Xu"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2024.3521729"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.cose.2023.103139"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00115"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00480"},{"key":"ref50","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of the 38th International Conference on Machine Learning","volume":"139","author":"Radford"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3487553.3524650"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref53","first-page":"165","article-title":"Google translate","volume-title":"Technical Services Quarterly","volume":"29","author":"Johnson","year":"2012"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.756"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/d14-1181"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2028"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.40"},{"key":"ref58","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2015"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"}],"event":{"name":"2024 7th International Conference on Data Science and Information Technology (DSIT)","location":"Nanjing, China","start":{"date-parts":[[2024,12,20]]},"end":{"date-parts":[[2024,12,22]]}},"container-title":["2024 7th International Conference on Data Science and Information Technology (DSIT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10880698\/10880863\/10881540.pdf?arnumber=10881540","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,20]],"date-time":"2025-02-20T20:01:49Z","timestamp":1740081709000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10881540\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,20]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/dsit61374.2024.10881540","relation":{},"subject":[],"published":{"date-parts":[[2024,12,20]]}}}