Yuezun Li's Homepage

Yuezun Li (李岳尊)

I am an assistant professor/lecturer in the institute of Artificial Intelligence, at Ocean University of China. My research interest lies at computer vision, machine learning and multimedia forensics.

I was a Senior Research Scientist at the Department of Computer Science and Engineering of University at Buffalo, SUNY, working with Prof. Siwei Lyu. I was a summer intern at GE glocal research center during 2016 - 2018. I received Ph.D. degree in computer science at University at Albany, SUNY in 2020, advised by Prof. Siwei Lyu. I received M.S. degree in Computer Science in 2015 and B.S. degree in Software Engineering in 2012 at Shandong University.

Research group: Currently I am leading Vision Analysis and Security (VAS) group, which interests in computer vision, DNN security and multimedia forensics. Our group has multiple openings. Please drop me an email if you are interested in internship / M.S. program.

[News] [Publications] [Fundings] [Service] [中文版]

News

[2024.04]: One paper on deepfake detection is accepted by IEEE TIFS. New!
[2024.04]: One paper on deepfake defense is accepted by IEEE TETC. New!
[2024.04]: One paper on image-text retrieval is accepted by ICMR. New!
[2024.02]: One paper on image-text retrieval is accepted by KBS. New!
[2024.01]: One paper on deepfake defense is accepted by CVIU. New!
[2023.12]: One paper on adversarial robustness is accepted by ICASSP.
[2023.11]: I gave a talk at a forum in CSIG ChinaFMS conference 2023.
[2023.10]: One paper on adversarial robustness is accepted by CVIU.
[2023.07]: I gave a talk at a forum in CCF CFTC 2023 on Recent Advances on CV Security.
[2023.06]: One ICME paper entitled Forensics Forest is selected as Oral.
[2023.05]: A dataset on phytoplankton observation is accepted by JMSE.
[2023.05]: One paper on Semantic Segmentation is accepted by IEEE TNNLS.
[2023.04]: One paper on Universal Domain Adaptation is accepted by IEEE TCSVT.
[2023.03]: Two papers on DeepFake defense are accepted by ICME.

>> More

Publications(* Equal contribution, # Corresponding author, + Advised student)

Representative works:

Preprints
	Multilateral Temporal-view Pyramid Transformer for Video Inpainting Detection Ying Zhang⁺, Bo Peng, Jiaran Zhou, Huiyu Zhou, Junyu Dong, Yuezun Li^#. arXiv:2404.11054, 2024.
	DomainForensics: Exposing Face Forgery across Domains via Bi-directional Adaptation Qingxuan Lv⁺, Yuezun Li^#, Junyu Dong^#, Sheng Chen, Hui Yu, Huiyu Zhou, Shu Zhang. arXiv:2312.10680, 2023.
	Contrastive Multi-FaceForensics: An End-to-end Bi-grained Contrastive Learning Approach for Multi-face Forgery Detection Cong Zhang⁺, Honggang Qi, Yuezun Li^#, Siwei Lyu. arXiv:2308.01520, 2023.
2024
	ForensicsForest Family: A Series of Multi-scale Hierarchical Cascade Forests for Detecting GAN-generated Faces Jiucui Lu⁺, Jiaran Zhou, Bin Li, Junyu Dong, Siwei Lyu, Yuezun Li^#. IEEE Transactions on Information Forensics and Security (TIFS), 2024. (Extended from ICME 2023) [Code]
	FakeTracer: Catching Face-swap DeepFakes via Implanting Traces in Training Pu Sun⁺, Honggang Qi, Yuezun Li^#, Siwei Lyu. IEEE Transactions on Emerging Topics in Computing (TETC), 2024. (Extended from ICIP2022) [Code]
	Dynamic Soft Labeling for Visual Semantic Embedding Jiaao Yu⁺, Yunlai Ding, Junyu Dong, Yuezun Li. ACM International Conference on Multimedia Retrieval (ICMR), 2024. [Code]
	Multiview Adaptive Attention Pooling for Image-Text Retrieval Yunlai Ding⁺, Jiaao Yu⁺, Qingxuan Lv, Haoran Zhao, Junyu Dong, Yuezun Li. Knowledge-Based Systems (KBS), 2024. [Code]
	LandmarkBreaker: A Proactive Method to Obstruct DeepFakes via Disrupting Facial Landmark Extraction Yuezun Li, Pu Sun, Honggang Qi, Siwei Lyu. Computer Vision and Image Understanding (CVIU), 2024. (Extended from WIFS2020) [Code]
	Enhancing Adversarial Robustness of DNNs via Weight Decorrelation in Training Cong Zhang, Yuezun Li, Honggang Qi, Siwei Lyu. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024. [Code]
	AdaNI: Adaptive Noise Injection to Improve Adversarial Robustness Yuezun Li, Cong Zhang, Honggang Qi, Siwei Lyu. Computer Vision and Image Understanding (CVIU), 2024. [Code]
2023
	PMOT2023: A large-scale multi-object tracking (MOT) dataset with application to phytoplankton observation Jiaao Yu⁺, Qingxuan Lv, Yuezun Li^#, Junyu Dong^#, Haoran Zhao, Qiong Li. Journal of Marine Science and Engineering (JMSE), 2023. (interdiscipline) [Code]
	Robust Scene Parsing by Mining Supportive Knowledge from Dataset Ao Luo, Fan Yang, Xin Li, Yuezun Li, Zhicheng Jiao, Hong Cheng, Siwei Lyu. IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2023. [Code]
	LaFea: Learning Latent Representation beyond Feature for Universal Domain Adaptation Qingxuan Lv⁺, Yuezun Li^#, Junyu Dong^#, Ziqian Guo. IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2023. [Code]
	Forensics Forest: Multi-scale Hierarchical Cascade Forest for Detecting GAN-generated Faces Jiucui Lu⁺, Yuezun Li^#, Jiaran Zhou, Bin Li, Siwei Lyu. IEEE International Conference on Multimedia and Expo (ICME), 2023. (Oral) [Code]
	Face Poison: Obstructing DeepFakes by Disrupting Face Detection Yuezun Li, Jiaran Zhou, Siwei Lyu. IEEE International Conference on Multimedia and Expo (ICME), 2023. [Code]
	Improving Transferable Adversarial Attack via Feature-Momentum Xianglong He⁺, Yuezun Li^#, Haipeng Qu, Junyu Dong. Computers & Security (COSE), 2023. [Code]
	Watching the BiG Artifacts: Exposing DeepFake Videos via Bi-Granularity Artifacts Han Chen^, Yuezun Li^, Dongdong Lin, Bin Li, Junqiang Wu. Pattern Recognition (PR), 2023. [Code]
2022
	Faketracer: Exposing DeepFakes with Training Data Contamination Pu Sun, Yuezun Li^#, Honggang Qi, Siwei Lyu. IEEE Conference on Image Processing (ICIP), 2022. [Code]
	LandmarkGAN: Synthesizing Faces from Landmarks Pu Sun^, Yuezun Li^, Honggang Qi, Siwei Lyu. Pattern Recognition Letters, 2022. [Code]
	Learning a Deep Dual-level Network for Robust DeepFake Detection Wenbo Pu, Jing Hu, Xin Wang, Yuezun Li, Shu Hu, Bin Zhu, Qi Song, Xi Wu, Siwei Lyu. Pattern Recognition (PR), 2022. [Code]
	Detection-by-Simulation: Exposing DeepFake via Simulating Forgery using Face Reconstruction Jiaran Zhou and Yuezun Li^#. IEEE International Conference on Multimedia Information Processing, Retrieval (MIPR), 2022. [Code]
2021
	Invisible Backdoor Attack with Sample-Specific Triggers Yuezun Li, Yiming Li, Baoyuan Wu, Longkang Li, Ran He, Siwei Lyu. IEEE International Conference on Computer Vision (ICCV), 2021. [Code]
	TransRPN: Towards the Transferable Adversarial Perturbations Using Region Proposal Networks and Beyond Yuezun Li, Ming-Ching Chang, Pu Sun, Honggang Qi, Junyu Dong, Siwei Lyu. International Journal on Computer Vision and Image Understanding (CVIU), 2021. [Code]
	DFGC 2021: A DeepFake Game Competition Bo Peng, Hongxing Fan, Wei Wang, Jing Dong, Yuezun Li, Siwei Lyu, etc. International Joint Conference on Biometrics (IJCB), 2021. [Code]
	DeepFake-o-meter: An Open Platform for DeepFake Detection Yuezun Li,Cong Zhang, Pu Sun, Lipeng Ke, Yan Ju, Honggang Qi, Siwei Lyu. Systematic Approaches to Digital Forensic Engineering, in conjunction with the IEEE Security and Privacy Smposium (S&P), 2021. [Code]

>> More

Fundings

[2022-2023]: PI, Fundamental Research Funds for the Central Universities, ￥100k.
[2022-2023]: PI, Qingdao Postdoctoral Applied Research Project, ￥50k.
[2021-2022]: PI, CPSF 70-th Support, ￥80k.
[2021-2022]: PI, CPSF Special Support, ￥180k.

Service

Journal Reviewer: IEEE Transactions on Information Forensics and Security; IEEE Transactions on Pattern Analysis and Machine Intelligence; IEEE Transactions on Neural Networks and Learning Systems; IEEE Journal of Selected Topics in Signal Processing; Signal Processing; IEEE Transactions on Multimedia; IEEE Transactions on Emerging Topics in Computational Intelligence; International Journal of Computer Vision; IEEE Transactions on Multimedia; IEEE Transactions on Circuits and Systems for Video Technology

Conference Reviewer: ECCV; AAAI; ICCV; CVPR; IJCB