{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T04:57:40Z","timestamp":1781585860694,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":47,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100006374","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62471090"],"award-info":[{"award-number":["62471090"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006374","name":"Natural Science Foundation of Sichuan Province","doi-asserted-by":"publisher","award":["23NSFSC0422"],"award-info":[{"award-number":["23NSFSC0422"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1145\/3731715.3733403","type":"proceedings-article","created":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T18:31:39Z","timestamp":1750876299000},"page":"1598-1606","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Multiscale Adaptive Conflict-Balancing Model For Multimedia Deepfake Detection"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-5618-663X","authenticated-orcid":false,"given":"Zihan","family":"Xiong","sequence":"first","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1220-7219","authenticated-orcid":false,"given":"Xiaohua","family":"Wu","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1493-7064","authenticated-orcid":false,"given":"Lei","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8925-315X","authenticated-orcid":false,"given":"Fangqi","family":"Lou","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,6,30]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018"},{"key":"e_1_3_2_1_2_1","volume-title":"Rubi: Reducing unimodal biases for visual question answering. Advances in neural information processing systems 32","author":"Cadene Remi","year":"2019","unstructured":"Remi Cadene, Corentin Dancette, Matthieu Cord, Devi Parikh, et al. 2019. Rubi: Reducing unimodal biases for visual question answering. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/DICTA56598.2022.10034605"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00603"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01815"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3635717"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413700"},{"key":"e_1_3_2_1_8_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Dang Hao","unstructured":"Hao Dang, Feng Liu, Joel Stehouwer, Xiaoming Liu, and Anil K. Jain. 2020. On the Detection of Digital Face Manipulation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_2_1_9_1","volume-title":"Ecapatdnn: Emphasized channel attention, propagation and aggregation in tdnn based speaker verification. arXiv preprint arXiv:2005.07143.","author":"Desplanques Brecht","year":"2020","unstructured":"Brecht Desplanques, Jenthe Thienpondt, and Kris Demuynck. 2020. Ecapatdnn: Emphasized channel attention, propagation and aggregation in tdnn based speaker verification. arXiv preprint arXiv:2005.07143."},{"key":"e_1_3_2_1_10_1","volume-title":"The deepfake detection challenge (dfdc) dataset. arXiv preprint arXiv:2006.07397","author":"Dolhansky Brian","year":"2020","unstructured":"Brian Dolhansky, Joanna Bitton, Ben Pflaum, Jikuo Lu, Russ Howes, Menglin Wang, and Cristian Canton Ferrer. 2020. The deepfake detection challenge (dfdc) dataset. arXiv preprint arXiv:2006.07397 (2020)."},{"key":"e_1_3_2_1_11_1","volume-title":"Exploiting human social cognition for the detection of fake and fraudulent faces via memory networks. arXiv preprint arXiv:1911.07844","author":"Fernando Tharindu","year":"2019","unstructured":"Tharindu Fernando, Clinton Fookes, Simon Denman, and Sridha Sridharan. 2019. Exploiting human social cognition for the detection of fake and fraudulent faces via memory networks. arXiv preprint arXiv:1911.07844 (2019)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19954"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2023.3269152"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803740"},{"key":"e_1_3_2_1_15_1","volume-title":"IJCAI International Joint Conference on Artificial Intelligence. IJCAI: International Joint Conferences on","author":"Huang R","unstructured":"R Huang, MWY Lam, J Wang, D Su, D Yu, Y Ren, and Z Zhao. 2022. FastDiff: A Fast Conditional Diffusion Model for High-Quality Speech Synthesis. In IJCAI International Joint Conference on Artificial Intelligence. IJCAI: International Joint Conferences on Artificial Intelligence Organization, 4157--4163."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2023.110124"},{"key":"e_1_3_2_1_17_1","volume-title":"ICASSP 2022-2022 IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE, 6367--6371","author":"Heo Hee-Soo","year":"2022","unstructured":"Jee-weon Jung, Hee-Soo Heo, Hemlata Tak, Hye-jin Shim, Joon Son Chung, Bong- Jin Lee, Ha-Jin Yu, and Nicholas Evans. 2022. Aasist: Audio anti-spoofing using integrated spectro-temporal graph attention networks. In ICASSP 2022-2022 IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE, 6367--6371."},{"key":"e_1_3_2_1_18_1","volume-title":"FakeAVCeleb: A novel audio-video multimodal deepfake dataset. arXiv preprint arXiv:2108.05080","author":"Khalid Hasam","year":"2021","unstructured":"Hasam Khalid, Shahroz Tariq, Minha Kim, and Simon SWoo. 2021. FakeAVCeleb: A novel audio-video multimodal deepfake dataset. arXiv preprint arXiv:2108.05080 (2021)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00512"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2018.2876837"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3656580"},{"key":"e_1_3_2_1_22_1","volume-title":"Focal Loss for Dense Object Detection. arXiv preprint arXiv:1708.02002","author":"Lin T","year":"2017","unstructured":"T Lin. 2017. Focal Loss for Dense Object Detection. arXiv preprint arXiv:1708.02002 (2017)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023"},{"key":"e_1_3_2_1_24_1","first-page":"1","article-title":"Derivative-free methods for policy optimization: Guarantees for linear quadratic systems","volume":"21","author":"Malik Dhruv","year":"2020","unstructured":"Dhruv Malik, Ashwin Pananjady, Kush Bhatia, Koulik Khamaru, Peter L Bartlett, and Martin J Wainwright. 2020. Derivative-free methods for policy optimization: Guarantees for linear quadratic systems. Journal of Machine Learning Research 21, 21 (2020), 1--51.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_25_1","volume-title":"Mohsen Sardari Zarchi, and Razieh Sheikhpour.","author":"Mehrjardi Fatemeh Zare","year":"2023","unstructured":"Fatemeh Zare Mehrjardi, Ali Mohammad Latif, Mohsen Sardari Zarchi, and Razieh Sheikhpour. 2023. A survey on deep learning-based image forgery detection. Pattern Recognition (2023), 109778."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413570"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682602"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681672"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00806"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3297768"},{"key":"e_1_3_2_1_31_1","unstructured":"Jinghan Ru Yuxin Xie Xianwei Zhuang Yuguo Yin and Yuexian Zou. 2025. Do we really have to filter out random noise in pre-training data for language models? arXiv:2502.06604 [cs.CL] https:\/\/arxiv.org\/abs\/2502.06604"},{"key":"e_1_3_2_1_32_1","first-page":"80","article-title":"Recurrent convolutional strategies for face manipulation detection in videos","volume":"3","author":"Sabir Ekraam","year":"2019","unstructured":"Ekraam Sabir, Jiaxin Cheng, Ayush Jaiswal, Wael Abd Almageed, Iacopo Masi, and Prem Natarajan. 2019. Recurrent convolutional strategies for face manipulation detection in videos. Interfaces (GUI) 3, 1 (2019), 80--87.","journal-title":"Interfaces (GUI)"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3319535.3363269"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3267357.3267367"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3297280.3297410"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01271"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093492"},{"key":"e_1_3_2_1_38_1","volume-title":"International Conference on Machine Learning. PMLR, 24043--24055","author":"Wu Nan","year":"2022","unstructured":"Nan Wu, Stanislaw Jastrzebski, Kyunghyun Cho, and Krzysztof J Geras. 2022. Characterizing and overcoming the greedy nature of learning in multi-modal deep neural networks. In International Conference on Machine Learning. PMLR, 24043--24055."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024--1642"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2023.3262148"},{"key":"e_1_3_2_1_41_1","volume-title":"ATRI: Mitigating Multilingual Audio Text Retrieval Inconsistencies by Reducing Data Distribution Errors. arXiv:2502.14627 [cs.SD] https:\/\/arxiv.org\/abs\/2502.14627","author":"Yin Yuguo","year":"2025","unstructured":"Yuguo Yin, Yuxin Xie, Wenyuan Yang, Dongchao Yang, Jinghan Ru, Xianwei Zhuang, Liming Liang, and Yuexian Zou. 2025. ATRI: Mitigating Multilingual Audio Text Retrieval Inconsistencies by Reducing Data Distribution Errors. arXiv:2502.14627 [cs.SD] https:\/\/arxiv.org\/abs\/2502.14627"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3309899"},{"key":"e_1_3_2_1_43_1","unstructured":"Hanqing Zhao Wenbo Zhou Dongdong Chen Tianyi Wei Weiming Zhang and Nenghai Yu. 2021. Multi-attentional Deepfake Detection. arXiv:2103.02406 [cs.CV] https:\/\/arxiv.org\/abs\/2103.02406"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00572"},{"key":"e_1_3_2_1_45_1","volume-title":"Computer Vision - ECCV","author":"Zhuang Xianwei","year":"2024","unstructured":"Xianwei Zhuang, Hongxiang Li, Xuxin Cheng, Zhihong Zhu, Yuxin Xie, and Yuexian Zou. 2025. KDProR: A Knowledge-Decoupling Probabilistic Framework for Video-Text Retrieval. In Computer Vision - ECCV 2024, Ale\u0161 Leonardis, Elisa Ricci, Stefan Roth, Olga Russakovsky, Torsten Sattler, and G\u00fcl Varol (Eds.). Springer Nature Switzerland, Cham, 313--331."},{"key":"e_1_3_2_1_46_1","unstructured":"Xianwei Zhuang Yuxin Xie Yufan Deng Dongchao Yang Liming Liang Jinghan Ru Yuguo Yin and Yuexian Zou. 2025. VARGPT-v1.1: Improve Visual Autoregressive Large Unified Model via Iterative Instruction Tuning and Reinforcement Learning. arXiv:2504.02949 [cs.CV] https:\/\/arxiv.org\/abs\/2504.02949"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"crossref","unstructured":"Xianwei Zhuang Zhihong Zhu Yuxin Xie Liming Liang and Yuexian Zou. 2025. VASparse: Towards Efficient Visual Hallucination Mitigation via Visual-Aware Token Sparsification. arXiv:2501.06553 [cs.CV] https:\/\/arxiv.org\/abs\/2501.06553","DOI":"10.1109\/CVPR52734.2025.00396"}],"event":{"name":"ICMR '25: International Conference on Multimedia Retrieval","location":"Chicago IL USA","acronym":"ICMR '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 2025 International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3731715.3733403","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T04:12:18Z","timestamp":1755749538000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3731715.3733403"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":47,"alternative-id":["10.1145\/3731715.3733403","10.1145\/3731715"],"URL":"https:\/\/doi.org\/10.1145\/3731715.3733403","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]},"assertion":[{"value":"2025-06-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}