{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T09:13:35Z","timestamp":1785143615340,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":37,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62306091, U21B2038, and 62306092"],"award-info":[{"award-number":["62306091, U21B2038, and 62306092"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,12,3]]},"DOI":"10.1145\/3696409.3700276","type":"proceedings-article","created":{"date-parts":[[2024,12,28]],"date-time":"2024-12-28T09:55:23Z","timestamp":1735379723000},"page":"1-1","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Improving Sequential DeepFake Detection with Local information enhancement"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-6869-8743","authenticated-orcid":false,"given":"Longyun","family":"Dong","sequence":"first","affiliation":[{"name":"HARBIN INSTITUTE OF TECHNOLOGY, WEIHAI, Weihai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9457-7956","authenticated-orcid":false,"given":"Yuanrong","family":"Xu","sequence":"additional","affiliation":[{"name":"HARBIN INSTITUTE OF TECHNOLOGY, WEIHAI, Weihai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1906-734X","authenticated-orcid":false,"given":"Jianping","family":"Zhong","sequence":"additional","affiliation":[{"name":"HARBIN INSTITUTE OF TECHNOLOGY, WEIHAI, Weihai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9196-9818","authenticated-orcid":false,"given":"Zhaobo","family":"Qi","sequence":"additional","affiliation":[{"name":"HARBIN INSTITUTE OF TECHNOLOGY, WEIHAI, Weihai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0042-7074","authenticated-orcid":false,"given":"Weigang","family":"Zhang","sequence":"additional","affiliation":[{"name":"HARBIN INSTITUTE OF TECHNOLOGY, WEIHAI, Weihai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,12,28]]},"reference":[{"key":"e_1_3_3_1_2_2","unstructured":"Jimmy\u00a0Lei Ba. 2016. Layer normalization. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1607.06450 (2016)."},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00408"},{"key":"e_1_3_3_1_4_2","unstructured":"Zhe Chen Yuchen Duan Wenhai Wang Junjun He Tong Lu Jifeng Dai and Yu Qiao. 2022. Vision transformer adapter for dense predictions. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2205.08534 (2022)."},{"key":"e_1_3_3_1_5_2","unstructured":"Alexey Dosovitskiy. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2010.11929 (2020)."},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00213"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/3469877.3490586"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_3_1_9_2","unstructured":"Zhenliang He Wangmeng Zuo Meina Kan Shiguang Shan and Xilin Chen. 2017. AttGAN: Facial attribute editing by only changing what you want. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1711.10678 (2017)."},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00072"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3595916.3626426"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01354"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00091"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00505"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/WIFS.2018.8630787"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00083"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00379"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"crossref","unstructured":"Xiaoxiao Liu Qingyang Xu and Ning Wang. 2019. A survey on deep neural network-based image captioning. The Visual Computer 35 3 (2019) 445\u2013470.","DOI":"10.1007\/s00371-018-1566-y"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3437880.3460400"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"crossref","unstructured":"Priyanka Meel and Dinesh\u00a0Kumar Vishwakarma. 2021. HAN image captioning and forensics ensemble multimodal fake news detection. Information Sciences 567 (2021) 23\u201341.","DOI":"10.1016\/j.ins.2021.03.037"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"crossref","unstructured":"Changtao Miao Zichang Tan Qi Chu Nenghai Yu and Guodong Guo. 2022. Hierarchical frequency-assisted interactive networks for face manipulation detection. IEEE Transactions on Information Forensics and Security 17 (2022) 3008\u20133021.","DOI":"10.1109\/TIFS.2022.3198275"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"crossref","unstructured":"Yisroel Mirsky and Wenke Lee. 2021. The creation and detection of deepfakes: A survey. ACM computing surveys (CSUR) 54 1 (2021) 1\u201341.","DOI":"10.1145\/3425780"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9413141"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_50"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_6"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19778-9_41"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01816"},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"crossref","unstructured":"Matteo Stefanini Marcella Cornia Lorenzo Baraldi Silvia Cascianelli Giuseppe Fiameni and Rita Cucchiara. 2022. From show to tell: A survey on deep learning-based image captioning. IEEE transactions on pattern analysis and machine intelligence 45 1 (2022) 539\u2013559.","DOI":"10.1109\/TPAMI.2022.3148210"},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"crossref","unstructured":"Justus Thies Michael Zollh\u00f6fer Christian Theobalt Marc Stamminger and Matthias Nie\u00dfner. 2018. Headon: Real-time reenactment of human portrait videos. ACM Transactions on Graphics (TOG) 37 4 (2018) 1\u201313.","DOI":"10.1145\/3197517.3201350"},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475518"},{"key":"e_1_3_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3469877.3490566"},{"key":"e_1_3_3_1_35_2","doi-asserted-by":"crossref","unstructured":"Jiachen Yang Aiyun Li Shuai Xiao Wen Lu and Xinbo Gao. 2021. MTD-Net: Learning to detect deepfakes images by multi-scale texture difference. IEEE Transactions on Information Forensics and Security 16 (2021) 4234\u20134245.","DOI":"10.1109\/TIFS.2021.3102487"},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"crossref","unstructured":"Ziming Yang Jian Liang Yuting Xu Xiao-Yu Zhang and Ran He. 2023. Masked relation learning for deepfake detection. IEEE Transactions on Information Forensics and Security 18 (2023) 1696\u20131708.","DOI":"10.1109\/TIFS.2023.3249566"},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01475"},{"key":"e_1_3_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7000"}],"event":{"name":"MMAsia '24: ACM Multimedia Asia","location":"Auckland New Zealand","acronym":"MMAsia '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 6th ACM International Conference on Multimedia in Asia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3696409.3700276","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3696409.3700276","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:10:16Z","timestamp":1750295416000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3696409.3700276"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,3]]},"references-count":37,"alternative-id":["10.1145\/3696409.3700276","10.1145\/3696409"],"URL":"https:\/\/doi.org\/10.1145\/3696409.3700276","relation":{},"subject":[],"published":{"date-parts":[[2024,12,3]]},"assertion":[{"value":"2024-12-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}