{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T15:55:09Z","timestamp":1781538909544,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":71,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T00:00:00Z","timestamp":1781481600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"the Scientific Research Fund of Hu- nan Provincial Education Department","award":["24B0308"],"award-info":[{"award-number":["24B0308"]}]},{"name":"the National Innovation Training Program for College Students, China","award":["02510536030"],"award-info":[{"award-number":["02510536030"]}]},{"name":"the Key Research and Development Project in the Field of Life and Health by Dalian Municipal Science and Technology Bureau","award":["2025ZDJH01PT112"],"award-info":[{"award-number":["2025ZDJH01PT112"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,16]]},"DOI":"10.1145\/3805622.3810582","type":"proceedings-article","created":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T14:42:57Z","timestamp":1781534577000},"page":"2077-2086","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["TSAD:Trace-Semantic Adaptive Disentanglement for Detecting and Grounding Multi-Modal Media Manipulation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2115-1540","authenticated-orcid":false,"given":"Wenzheng","family":"Liu","sequence":"first","affiliation":[{"name":"Changsha University of Science and Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9375-3628","authenticated-orcid":false,"given":"Cheng","family":"Fu","sequence":"additional","affiliation":[{"name":"Changsha University of Science and Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0370-4109","authenticated-orcid":false,"given":"Hujin","family":"Peng","sequence":"additional","affiliation":[{"name":"Changsha University of Science and Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8048-4138","authenticated-orcid":false,"given":"Junlong","family":"Wu","sequence":"additional","affiliation":[{"name":"Changsha University of Science and Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3332-9485","authenticated-orcid":false,"given":"Xianhong","family":"Chen","sequence":"additional","affiliation":[{"name":"Changsha University of Science and Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5966-5215","authenticated-orcid":false,"given":"Lan","family":"Huang","sequence":"additional","affiliation":[{"name":"Changsha University of Science and Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-0700-7603","authenticated-orcid":false,"given":"Jing","family":"Xu","sequence":"additional","affiliation":[{"name":"Changsha University of Science and Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6002-5142","authenticated-orcid":false,"given":"Yixi","family":"Tian","sequence":"additional","affiliation":[{"name":"Changsha University of Science and Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2813-7286","authenticated-orcid":false,"given":"Menghan","family":"Liang","sequence":"additional","affiliation":[{"name":"Changsha University of Science and Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3583-369X","authenticated-orcid":false,"given":"Xiaofeng","family":"Wang","sequence":"additional","affiliation":[{"name":"National University of Defence Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4307-6290","authenticated-orcid":false,"given":"Tan","family":"Deng","sequence":"additional","affiliation":[{"name":"Changsha University of Science and Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6332-8800","authenticated-orcid":false,"given":"Wanwei","family":"Jiang","sequence":"additional","affiliation":[{"name":"Zhongshan Hospital of Dalian University, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5715-8260","authenticated-orcid":false,"given":"Xiang","family":"Li","sequence":"additional","affiliation":[{"name":"Zhongshan Hospital of Dalian University, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,15]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755707"},{"key":"e_1_3_3_1_3_2","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Cao Biwei","year":"2025","unstructured":"Biwei Cao, Qihang Wu, Jiuxin Cao, Bo Liu, and Jie Gui. 2025. ERIC-FND: External Reliable Information-enhanced Multimodal Contrastive Learning for Fake News Detection. In Proceedings of the AAAI Conference on Artificial Intelligence."},{"key":"e_1_3_3_1_4_2","unstructured":"Nuria\u00a0Alina Chandra Ryan Murtfeldt Lin Qiu and Arnab Karmakar. 2025. Deepfake-Eval-2024: A Multi-Modal In-the-Wild Benchmark of Deepfakes Circulated in 2024. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.02857 (2025)."},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"crossref","unstructured":"Yupeng Chang Xu Wang Jindong Wang Yuan Wu Linyi Yang Kaijie Zhu Hao Chen Xiaoyuan Yi Cunxiang Wang Yidong Wang et\u00a0al. 2024. A survey on evaluation of large language models. ACM transactions on intelligent systems and technology 15 3 (2024) 1\u201345.","DOI":"10.1145\/3641289"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i2.32218"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01789"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00195"},{"key":"e_1_3_3_1_9_2","first-page":"4171","volume-title":"Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies, volume 1 (long and short papers)","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies, volume 1 (long and short papers). 4171\u20134186."},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00389"},{"key":"e_1_3_3_1_11_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_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01763"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"crossref","unstructured":"Nanyi Fei Zhiwu Lu Yizhao Gao Guoxing Yang Yuqi Huo Jingyuan Wen Haoyu Lu Ruihua Song Xin Gao Tao Xiang et\u00a0al. 2022. Towards artificial general intelligence via a multimodal foundation model. Nature Communications 13 1 (2022) 3094.","DOI":"10.1038\/s41467-022-30761-2"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01011"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00019"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02141"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"crossref","unstructured":"Ping He et\u00a0al. 2025. Cross-Modal Fake News Detection Method Based on Multi-Level Fusion Without Evidence. Algorithms 18 (2025).","DOI":"10.3390\/a18070426"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.eacl-main.15"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01347"},{"key":"e_1_3_3_1_20_2","first-page":"474","volume-title":"European Conference on Computer Vision","author":"Hua Hang","year":"2024","unstructured":"Hang Hua, Jing Shi, Kushal Kafle, Simon Jenni, Daoan Zhang, John Collomosse, Scott Cohen, and Jiebo Luo. 2024. Finematch: Aspect-based fine-grained image and text mismatch detection and correction. In European Conference on Computer Vision. Springer, 474\u2013491."},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.959"},{"key":"e_1_3_3_1_22_2","unstructured":"Chengze Jiang Zhuangzhuang Wang Minjing Dong and Jie Gui. 2025. Survey of adversarial robustness in multimodal large language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.13962 (2025)."},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"crossref","unstructured":"Yizhang Jin Jian Li Tianjun Gu Yexin Liu Bo Zhao Jinxiang Lai Zhenye Gan Yabiao Wang Chengjie Wang Xin Tan et\u00a0al. 2025. Efficient multimodal large language models: A survey. Visual Intelligence 3 1 (2025) 27.","DOI":"10.1007\/s44267-025-00099-6"},{"key":"e_1_3_3_1_24_2","unstructured":"Douwe Kiela Hamed Firooz Aravind Mohan Vedanuj Goswami Amanpreet Singh Pratik Ringshia and Davide Testuggine. 2020. The hateful memes challenge: Detecting hate speech in multimodal memes. Advances in neural information processing systems 33 (2020) 2611\u20132624."},{"key":"e_1_3_3_1_25_2","first-page":"5583","volume-title":"International conference on machine learning","author":"Kim Wonjae","year":"2021","unstructured":"Wonjae Kim, Bokyung Son, and Ildoo Kim. 2021. Vilt: Vision-and-language transformer without convolution or region supervision. In International conference on machine learning. PMLR, 5583\u20135594."},{"key":"e_1_3_3_1_26_2","unstructured":"Jian Li Weiheng Lu Hao Fei Meng Luo Ming Dai Min Xia Yizhang Jin Zhenye Gan Ding Qi Chaoyou Fu et\u00a0al. 2024. A survey on benchmarks of multimodal large language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2408.08632 (2024)."},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i1.32022"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"crossref","unstructured":"Qilei Li Mingliang Gao Guisheng Zhang Wenzhe Zhai Jinyong Chen and Gwanggil Jeon. 2024. Towards multimodal disinformation detection by vision-language knowledge interaction. Information Fusion 102 (2024) 102037.","DOI":"10.1016\/j.inffus.2023.102037"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"crossref","unstructured":"Xin Li Rongrong Ni Pengpeng Yang Zhiqiang Fu and Yao Zhao. 2022. Artifacts-disentangled adversarial learning for deepfake detection. IEEE Transactions on Circuits and Systems for Video Technology 33 4 (2022) 1658\u20131670.","DOI":"10.1109\/TCSVT.2022.3217950"},{"key":"e_1_3_3_1_30_2","unstructured":"Yuqi Li Junhao Dong Chuanguang Yang Shiping Wen Piotr Koniusz Tingwen Huang Yingli Tian and Yew-Soon Ong. 2025. MMT-ARD: Multimodal Multi-Teacher Adversarial Distillation for Robust Vision-Language Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2511.17448 (2025)."},{"key":"e_1_3_3_1_31_2","unstructured":"Yuqi Li Chuanguang Yang Junhao Dong Zhengtao Yao Haoyan Xu Zeyu Dong Hansheng Zeng Zhulin An and Yingli Tian. 2025. Ammkd: Adaptive multimodal multi-teacher distillation for lightweight vision-language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2509.00039 (2025)."},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00863"},{"key":"e_1_3_3_1_33_2","unstructured":"Daizong Liu Mingyu Yang Xiaoye Qu Pan Zhou Yu Cheng and Wei Hu. 2025. A survey of attacks on large vision\u2013language models: Resources advances and future trends. IEEE Transactions on Neural Networks and Learning Systems (2025)."},{"key":"e_1_3_3_1_34_2","doi-asserted-by":"crossref","unstructured":"Huan Liu Zichang Tan Qiang Chen Yunchao Wei Yao Zhao and Jingdong Wang. 2025. Unified frequency-assisted transformer framework for detecting and grounding multi-modal manipulation. International Journal of Computer Vision 133 3 (2025) 1392\u20131409.","DOI":"10.1007\/s11263-024-02245-x"},{"key":"e_1_3_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i1.32029"},{"key":"e_1_3_3_1_36_2","unstructured":"Ilya Loshchilov Frank Hutter et\u00a0al. 2017. Fixing weight decay regularization in adam. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1711.05101 5 5 (2017) 5."},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01605"},{"key":"e_1_3_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.316"},{"key":"e_1_3_3_1_39_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_40_2","unstructured":"Alhassan Mumuni and Fuseini Mumuni. 2025. Large language models for artificial general intelligence (AGI): A survey of foundational principles and approaches. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2501.03151 (2025)."},{"key":"e_1_3_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01647"},{"key":"e_1_3_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02559"},{"key":"e_1_3_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01361"},{"key":"e_1_3_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01240"},{"key":"e_1_3_3_1_45_2","first-page":"8748","volume-title":"International conference on machine learning","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong\u00a0Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et\u00a0al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PmLR, 8748\u20138763."},{"key":"e_1_3_3_1_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00667"},{"key":"e_1_3_3_1_47_2","doi-asserted-by":"crossref","unstructured":"Rui Shao Tianxing Wu Jianlong Wu Liqiang Nie and Ziwei Liu. 2024. Detecting and grounding multi-modal media manipulation and beyond. IEEE Transactions on Pattern Analysis and Machine Intelligence 46 8 (2024) 5556\u20135574.","DOI":"10.1109\/TPAMI.2024.3367749"},{"key":"e_1_3_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3754951"},{"key":"e_1_3_3_1_49_2","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Song Xiufeng","year":"2024","unstructured":"Xiufeng Song, Xiao Guo, Jiache Zhang, Qirui Li, Lei Bai, Xiaoming Liu, Guangtao Zhai, and Xiaohong Liu. 2024. On Learning Multi-Modal Forgery Representation for Diffusion Generated Video Detection. In Advances in Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01823"},{"key":"e_1_3_3_1_51_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i7.32772"},{"key":"e_1_3_3_1_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02657"},{"key":"e_1_3_3_1_53_2","doi-asserted-by":"crossref","unstructured":"Renshuai Tao Chuangchuang Tan Huan Liu Jiakai Wang Haotong Qin Yakun Chang Wei Wang Rongrong Ni and Yao Zhao. 2025. SAGNet: Decoupling Semantic-Agnostic Artifacts From Limited Training Data for Robust Generalization in Deepfake Detection. IEEE Transactions on Information Forensics and Security 20 (2025) 6429\u20136442.","DOI":"10.1109\/TIFS.2025.3581726"},{"key":"e_1_3_3_1_54_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00499"},{"key":"e_1_3_3_1_55_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448385"},{"key":"e_1_3_3_1_56_2","unstructured":"Jian Wang Baoyuan Wu Li Liu and Qingshan Liu. 2025. FauForensics: Boosting Audio-Visual Deepfake Detection with Facial Action Units. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2505.08294 (2025)."},{"key":"e_1_3_3_1_57_2","doi-asserted-by":"crossref","unstructured":"Jingwei Wang Ziyue Zhu Chunxiao Liu Rong Li and Xin Wu. 2024. LLM-Enhanced multimodal detection of fake news. PloS one 19 10 (2024) e0312240.","DOI":"10.1371\/journal.pone.0312240"},{"key":"e_1_3_3_1_58_2","doi-asserted-by":"publisher","DOI":"10.1109\/BigData59044.2023.10386743"},{"key":"e_1_3_3_1_59_2","doi-asserted-by":"crossref","unstructured":"Ikuya Yamada Akari Asai Hiroyuki Shindo Hideaki Takeda and Yuji Matsumoto. 2020. LUKE: Deep contextualized entity representations with entity-aware self-attention. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2010.01057 (2020).","DOI":"10.18653\/v1\/2020.emnlp-main.523"},{"key":"e_1_3_3_1_60_2","doi-asserted-by":"crossref","unstructured":"Bo Yan Pan Liu Yumin Yang and Yanming Guo. 2025. Self-Supervised Feature Disentanglement for Deepfake Detection. Mathematics 13 12 (2025) 2024.","DOI":"10.3390\/math13122024"},{"key":"e_1_3_3_1_61_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02048"},{"key":"e_1_3_3_1_62_2","unstructured":"Lili Yu Bowen Shi Ramakanth Pasunuru Benjamin Muller Olga Golovneva Tianlu Wang Arun Babu Binh Tang Brian Karrer Shelly Sheynin et\u00a0al. 2023. Scaling autoregressive multi-modal models: Pretraining and instruction tuning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2309.02591 (2023)."},{"key":"e_1_3_3_1_63_2","unstructured":"Youngjoon Yu Hong\u00a0Joo Lee Byeong\u00a0Cheon Kim Jung\u00a0Uk Kim and Yong\u00a0Man Ro. 2020. Investigating vulnerability to adversarial examples on multimodal data fusion in deep learning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2005.10987 (2020)."},{"key":"e_1_3_3_1_64_2","unstructured":"Junrong Yue Yifan Zhang Chuan Qin Bo Li Xiaomin Lie Xinlei Yu Wenxin Zhang and Zhendong Zhao. 2025. Think Hierarchically Act Dynamically: Hierarchical Multi-modal Fusion and Reasoning for Vision-and-Language Navigation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2504.16516 (2025)."},{"key":"e_1_3_3_1_65_2","unstructured":"Sayeem\u00a0Been Zaman Wasimul Karim Arefin\u00a0Ittesafun Abian Reem\u00a0E Mohamed Md\u00a0Rafiqul Islam Asif Karim and Sami Azam. 2025. DeepAgent: A Dual Stream Multi Agent Fusion for Robust Multimodal Deepfake Detection. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2512.07351 (2025)."},{"key":"e_1_3_3_1_66_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.613"},{"key":"e_1_3_3_1_67_2","doi-asserted-by":"crossref","unstructured":"Duzhen Zhang Yahan Yu Jiahua Dong Chenxing Li Dan Su Chenhui Chu and Dong Yu. 2024. Mm-llms: Recent advances in multimodal large language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2401.13601 (2024).","DOI":"10.18653\/v1\/2024.findings-acl.738"},{"key":"e_1_3_3_1_68_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00379"},{"key":"e_1_3_3_1_69_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00222"},{"key":"e_1_3_3_1_70_2","doi-asserted-by":"crossref","unstructured":"Jiaran Zhou Yuezun Li Baoyuan Wu Bin Li Junyu Dong et\u00a0al. 2024. Freqblender: Enhancing deepfake detection by blending frequency knowledge. Advances in Neural Information Processing Systems 37 (2024) 44965\u201344988.","DOI":"10.52202\/079017-1429"},{"key":"e_1_3_3_1_71_2","doi-asserted-by":"publisher","DOI":"10.63317\/5ajv9ahb5wpn"},{"key":"e_1_3_3_1_72_2","first-page":"1218","volume-title":"Proceedings of the 20th chinese national conference on computational linguistics","author":"Zhuang Liu","year":"2021","unstructured":"Liu Zhuang, Lin Wayne, Shi Ya, and Zhao Jun. 2021. A robustly optimized BERT pre-training approach with post-training. In Proceedings of the 20th chinese national conference on computational linguistics. 1218\u20131227."}],"event":{"name":"ICMR '26: International Conference on Multimedia Retrieval","location":"Amsterdam The Netherlands","acronym":"ICMR '26","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 2026 International Conference on Multimedia Retrieval"],"original-title":[],"deposited":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T15:05:23Z","timestamp":1781535923000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805622.3810582"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,15]]},"references-count":71,"alternative-id":["10.1145\/3805622.3810582","10.1145\/3805622"],"URL":"https:\/\/doi.org\/10.1145\/3805622.3810582","relation":{},"subject":[],"published":{"date-parts":[[2026,6,15]]},"assertion":[{"value":"2026-06-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}