人工智能；多模态内容分析理解；生成式大模型安全

2010-09--2016-07   中国科学院计算技术研究所   工学博士
2007-09--2009-07   中国传媒大学   工学硕士
2003-09--2007-07   中国传媒大学   工学学士

   

2024-03~现在, 中国科学院微电子研究所, 副研究员
2016-07~2024-03,中国科学院信息工程研究所, 助理研究员

[1]. Xiaomeng Fu, Xi Wang*, Qiao Li, et al., "OMS: One More Step Noise Searching to Enhance Membership Inference Attacks for Diffusion Models”, in International Joint Conference on Artificial Intelligence (IJCAI-25), 2025. (CCF-A )

[2]. Xiaomeng Fu, Xi Wang*, Qiao Li, et al., "Unlocking Generative Priors: A New Membership Inference Framework for Diffusion Models," in IEEE Transactions on Information Forensics and Security, vol. 20, pp. 4638-4650, 2025 (CCF-A )

[3]. Qiao Li, Xiaomeng Fu, Xi Wang, et.al., “Unveiling Structural Memorization: Structural Membership Inference Attack for Text-to-Image Diffusion Models”, ACM International Conference on MultiMedia (ACM MM), 2024. (CCF-A 长文)

[4]. Jiahe Tian, Cai Yu, Xi Wang, et.al., “Dynamic Mixed-Prototype Model for Incremental Deepfake Detection”, ACM International Conference on MultiMedia (ACM MM), 2024. (CCF-A 长文)

[5].  Jin Liu, Xi Wang*, Xiaomeng Fu, et.al., “OSM-Net: One-to-Many One-Shot Talking Head Generation With Spontaneous Head Motions”, IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), Vol.34(8): 6888-6900, 2024. (中科院 一区，CCF-B，IF: 8.3)

[6]. Jin Liu, Xi Wang*, Xiaomeng Fu, et.al., “MFR-Net: Multi-faceted Responsive Listening Head Generation via Denoising Diffusion Model”, ACM International Conference on MultiMedia (ACM MM), 2023. (CCF-A 长文)

[7]. Xiaomeng Fu, Xi Wang*, Jin Liu, et.al., “CoP: Chain-of-Pose for Image Animation in Large Pose Changes”, ACM International Conference on MultiMedia (ACM MM), 2023. (CCF-A 长文)

[8]. Xingyu Gao, Xi Wang*, Zhenyu Chen*, et.al., “Knowledge Enhanced Vision and Language Model for Multi-modal Fake News Detection”, IEEE Transactions on MultiMedia (TMM), 2024. (中科院 一区，CCF-B，IF: 8.4)

[9]. Jiahe Tian, Peng Chen, Cai Yu, Xiaomeng Fu, Xi Wang, et.al., “Learning to Discover Forgery Cues for Face Forgery Detection”, IEEE Transactions on Information Forensics and Security (TIFS), 2024. (中科院 一区，CCF-A，IF: 6.3)

[10]. Jiahe Tian, Cai Yu, Xi Wang, et.al., “Real Appearance Modeling for More General Deepfake Detection”, European Conference on Computer Vision (ECCV), 2024. (CCF-B会议)

[11]. Zhulin Tao, Runze Zhao, Xin Shi, Xingyu Gao*, Xi Wang*, Xianglin Huang, “Multimodal Consistency Suppression Factor for Fake News Detection”, ACM Trans. Multimedia Comput. Commun. Appl (ACM TOMM), 2024. (IF: 5.2)

[12]. Jin Chen, Jiahe Tian, Cai Yu, Xi Wang, et.al, “ConfR: Conflict Resolving for Generalizable Deepfake Detection”, IEEE International Conference on Multimedia and Expo (ICME), 2024

[13]. Yuchen Guo, Xi Wang, et.al:Generative Transferable Universal Adversarial Perturbation for Combating Deepfakes. CSCWD: 1986-1991

[14]. Yuchen Guo, Xi Wang, Xiaomeng Fu, et.al: Generative Universal Nullifying Perturbation for Countering Deepfakes Through Combined Unsupervised Feature Aggregation.ICANN(2) 2024: 289-303

[15]. Xi Wang, L. Su, H. Qi, Q. Huang and G. Li, “Face Distortion Recovery Based on Online Learning Database for Conversational Video”, IEEE Transactions on MultiMedia (TMM), 16(8):2130-2140, 2014. (中科院 一区，CCF-B，IF: 7.3)

[16]. 王茜, et.al. ”知识融合的多模态虚假新闻检测方法”, 信息安全学报. 2024. (CCF 中文期刊-B)

[17]. Yinuo. Zhang, Zhulin Tao, Xi Wang*, et al., INO at Factify 2: Structure Coherence based Multi- Modal Fact Verification, AAAI workshops, 2023. (CCF-A workshops)

[18]. Jin Liu, Xi Wang*, Xiaomeng Fu, et al., “OPT: One-shot Pose-Controllable Talking Head Generation”, IEEE International Conference on Acoustics, Speech, and Signal processing (ICASSP), 2023. (CCF-B 长文)

[19]. Jin Liu, Xi Wang*, Xiaomeng Fu , et.al., “FONT: Flow-guided One-shot Talking Head Generation with Natural Head Motions”, IEEE Conference on Multimedia & Expro (ICME), 2023. (CCF-B 长文)

[20]. Xiaomeng Fu, Xi Wang*, Jin Liu, et.al., “Large Pose Friendly Face Reenactment using subtle motions”, IEEE Conference on Multimedia & Expro (ICME), 2023. (CCF-B 长文)

[21]. Junwei Zhou, Xi Wang*, et.al., “A Decoupled Language Model Based on Contrastive Attention Mechanism for Scene Text Recognition”, ICCAI, 2023.

[22]. Junwei Zhou, Xi Wang*, et.al, Improved Fusion of Visual and Semantic Representations by Gated Co-Attention for Scene Text Recognition. ICCPR 2022.

[23]. 刘锦，陈鹏，王茜*，等人，“人类面部重演方法综述”，中国图象图形学报, vol.27:2629-2652, 2022. (CCF 中文期刊-B)

[24]. Xiaomeng Fu; Xi Wang*; Jin Liu; et.al., “MakeItSmile: Detail-Enhanced Smiling Face Reenactment”, International Joint Conference on Neural Networks (IJCNN), 2022. (CCF-C)

[25]. Hongchao Gao, Xi Wang*, et.al, “Self-Representation Convolutional neural networks”, IEEE International Conference on Multimedia& Expo (ICME), 2019. (CCF-B)

[26]. Hongchao Gao; Yujia Li; Xi Wang*; et.al.; “Ensemble Attention For Text Recognition In Natural Images”, International Joint Conference on Neural Networks (IJCNN), 2019. (CCF-C)

[27]. Junwei. Zhou, Xi Wang*, et.al, “Spatial-Temporal Attention for Image Captioning”, IEEE Conference on Multimedia Big Data (BigMM), 2018.

[28]. Shaohua. Liu, Yan Shang, Jizhong Han, Xi Wang*, et.al, “Multi-lingual Scene Text Detection Based on Fully Convolutional Networks”. Pacific-Rim Conference on Multimedia (PCM), 2017. (CCF-C)

[29]. 王茜, 苏荔, 黄庆明, “融合视觉感知特性的视频编码率失真优化”, 计算机辅助设计与图形学学报, 27(10) :1851-1858, 2015. (CCF 中文期刊-A)

[30]. Xi Wang, C. Yan, Q. Huang, L. Su, S. Jiang, X. Huang, “The Face Object based HEVC System for Video Call”, EAI Conference on MobiMedia, 2015.

[31]. Xi Wang, L. Su, Q. Huang, G. Li and H. Qi, “Online Learning Based Face Distortion Recovery for Conversational Video Coding”, Data Compression Conference (DCC), 2013. (CCF-B)

[32]. Xi Wang, Li Su, Q. Huang, C. Liu and L. Duan, “Motion Based Perceptual Distortion and Rate Optimization for Video Coding”, IEEE Conference on Multimedia & Expro, 2012. (CCF-B)

[33]. Xi Wang, L. Su, Q. Huang, C. Liu, “Visual Perception based Lagrangian Rate Distortion Optimization for Video Coding”, IEEE Conference on Image Processing (ICIP), 2011. (CCF-C)

[34]. Y. Li; H. Gao; Xi Wang; J. Han; R. Li; Text Recognition Using Local Correlation, British Machine Vision Conference (BMVC), 2019.

[35]. H. Gao; Y. Li; J. Dai; Xi Wang; J. Han; R. Li; Multi-Granularity Deep Local Representations for Irregular Scene Text Recognition, Transactions on Data Science, 2022.

[36]. Chenggang Yan, Yongdong Zhang, Feng Dai, Xi Wang, Liang Li, Qionghai Dai, “Parallel deblocking filter for HEVC on many core processor”, Electronics Letters, pp: 367-368, 2014.