Welcome for contacting me on career prospects & techs & research. Drop me emails or WeChat me (please leave a detailed note when sending a friend request). 😉
04 / 2018: 📝 One paper on 3D face & face recognition has been accepted by CCBR 2018, with a dataset MeGlass released.
04 / 2018: 📝 One paper on micro-emotion recognition has been accepted by IEEE Access.
03 / 2017: 📝 One paper on micro-emotion recognition has been accepted by FG 2017.
03 / 2017: 🥇 The winner of FG2017 facial micro-expression recognition competition, acknowledgement to my collaborator Shuai Zhou. Code released at EmotionChallenge.
03 / 2017: 🥈 The silver medal (rank5) of HUAWEI Code Craft 2017 in Beijing site, acknowledgement to my partners Yudong Wu and Xingyuan Gao.
We propose a video-driven portrait animation framework named LivePortrait with a focus on better generalization, controllability, and efficiency for practical usage. The generation speed remarkably reaches 12.8ms on an RTX 4090 GPU with PyTorch. The inference code and models are available at https://github.com/KwaiVGI/LivePortrait.
This paper proposes a novel training remedy by decomposing the model into the weight parameters and the BN statistics in the training phase. Based on decomposing, we design a novel framework via meta-learning, called Decomposed Meta Batch Normalization (DMBN) for fast domain adaptation in face recognition.
This paper proposes an efficient method Face Alignment Policy Search (FAPS) to search the optimal alignment template in face recognition. A well-designed benchmark is also proposed to evaluate the searched policy.
We propose a novel regression framework, named 3DDFA_V2, to make a balance among speed, accuracy and stability.
Our model runs at over 50fps on a single CPU core (>200fps with ONNX acceleration) and outperforms other state-of-the-art heavy models simultaneously. Code and models are available at https://github.com/cleardusk/3DDFA_V2.
This paper constructs a new dataset Fine-Grained 3D face (FG3D) with 200k samples for training, and proposes a Fine-Grained reconstruction Network (FGNet) concentrating on shape modication by warping the network input and output to the UV space. FG3D is available at https://github.com/XiangyuZhu-open/Beyond3DMM.
We propose a novel face recognition method via meta-learning named Meta Face Recognition (MFR) to learn a generalized model performing well on unseen domains. Besides, we propose two benchmarks for generalized face recognition evaluation. The proposed benchmarks will be available at https://github.com/cleardusk/MFR.
This paper proposes a Domain Frequency Instructor (DFI), a light weighted Residual Balancing Mapping (RBM) block and a Domain Balancing Margin (DBM) to improve generalization on tailed domains.
We present a method to synthesize virtual spoof data in 3D space to improve face anti-spoofing. The synthetic virtual samples can significantly boost the anti-spoofing performance when combined with a proposed data balancing strategy.
In the application of face recognition, eyeglasses could significantly degrade the recognition accuracy. In this paper, we propose to address this problem in a virtual synthesis manner.
We release a multi-modality 3D mask face anti-spoofing database named 3DMA, which contains 920 videos of 67 genuine subjects wearing 48 kinds of 3D masks, captured in visual (VIS) and near-infrared (NIR) modalities.
Zicheng Liu, Siyuan Li, Di Wu, Zhiyuan Chen, Lirong Wu, Jianzhu Guo, Stan Z. Li Under Review (ICCV 2021), 2021
arxiv /
paper /
OT-Cleaner: Refurbishing Unclean Labels with Optimal Transport
Jun Xia, Cheng Tan, Jianzhu Guo, Lirong Wu, Yongjie Xu, Stan Z. Li Under Review (ICML 2021), 2021
Deep Manifold Attributed Graph Embedding with Graph Geodesic Similarity
Zelin Zang, Siyuan Li, Di Wu, Jianzhu Guo, Yongjie Xu, Stan Z. Li Under Review (KDD 2021), 2021
Competitions
1-st Winner of Joint Challenge on Dominant and Complementary Emotion Recognition Using Micro Emotion Features and Head, in conjunction with FG 2017, First author. [Code]
HUAWEI Code Craft 2017: Awarded Silver Medal (rank 5th) in Beijing Site. Team with three members, equal contribution.
Reviewer for CVPR, ICCV, ECCV, AAAI, MM, IJCAI, IJCB, BMVC, FG, Transactions on Pattern Analysis and Machine Intelligence (TPAMI), Transactions on Image Processing (TIP), Transactions on Cybernetics (T-C), IEEE Transactions on Neural Networks and Learning Systems (TNNLS), TBIOM, Knowledge-Based Systems, IEEE Access, Neurocomputing, IET Computer Vision, etc.