Wei Wang
Associate Professor @ CASIA • AI Safety
I completed my PhD in Pattern Recognition from the Institute of Automation, Chinese Academy of Sciences (CASIA), where I was advised by Tieniu Tan during 2012-2017. I am currently an Associate Professor of the New Laboratory of Pattern Recognition (NLPR), CASIA. I am a member of IEEE, CCF, CAAI, etc. I am also a member of technical executive committee on Digital Forensics and Security of CSIG, technical committee (TC) on Computer Vision of CCF, TC on Pattern Recognition of CAAI, etc. My current research interests include artificial intelligence and its security problem, image and video forensics and privacy, and information content security.
news
Jul 01, 2024 | One paper is accepted in ECCV 2024 |
---|---|
Jul 01, 2024 | One paper is accepted by ACM TOMM |
Jun 04, 2024 | One paper is accepted by IEEE T-MM |
Apr 25, 2024 | One paper is accepted by IEEE T-IFS |
Dec 09, 2023 | Two papers are accepted in AAAI 2024 |
selected publications
2024
- Improving Generalization of Deepfake Detectors by Imposing Gradient RegularizationIEEE Transactions on Information Forensics and Security, 2024
- AAAIAE-NeRF: Audio Enhanced Neural Radiance Field for Few Shot Talking Head SynthesisIn Proceedings of the AAAI Conference on Artificial Intelligence, Mar 2024
- AAAILearning Dense Correspondence for NeRF-Based Face ReenactmentIn Proceedings of the AAAI Conference on Artificial Intelligence, Mar 2024
- Adversarial Attacks on Scene Graph GenerationIEEE Transactions on Information Forensics and Security, Mar 2024
2023
- PRTemporal Sparse Adversarial Attack on Sequence-Based Gait RecognitionPattern Recognition, Sep 2023
- 中国科学
- ACM MMContext-Aware Talking-Head Video EditingIn Proceedings of the 31st ACM International Conference on Multimedia, Oct 2023
- ICASSPDesigning a 3D-Aware StyleNeRF Encoder for Face EditingIn ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Jun 2023
2022
- ACM MMDefeating DeepFakes via Adversarial Visual ReconstructionIn Proceedings of the 30th ACM International Conference on Multimedia, Oct 2022
- Guided Erasable Adversarial Attack (GEAA) Toward Shared Data ProtectionIEEE Transactions on Information Forensics and Security, Oct 2022
2021
- CVPRExploring Adversarial Fake Images on Face ManifoldIn Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Jun 2021
- ACM MMSOGAN: 3D-Aware Shadow and Occlusion Robust GAN for Makeup TransferIn MM 2021 - Proceedings of the 29th ACM International Conference on Multimedia, Oct 2021
- CVPRMUST-GAN: Multi-level Statistics Transfer for Self-driven Person Image GenerationIn Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Jun 2021
- Adversarial Analysis for Source Camera IdentificationIEEE Transactions on Circuits and Systems for Video Technology, Jun 2021
- Are You Confident That You Have Successfully Generated Adversarial Examples?IEEE Transactions on Circuits and Systems for Video Technology, Jun 2021
2018
- Image Forensics Based on Planar Contact Constraints of 3D ObjectsIEEE Transactions on Information Forensics and Security, Feb 2018
2017
- Optimized 3D Lighting Environment Estimation for Image Forgery DetectionIEEE Transactions on Information Forensics and Security, Feb 2017
2014
- Exploring DCT Coefficient Quantization Effects for Local Tampering DetectionIEEE Transactions on Information Forensics and Security, Oct 2014