About me
I am a post-doctoral researcher in Department of Computer Science and Technology in the Tsinghua University. I work with Prof. Jun Zhu. Before that, I received the Ph.D degree from the Institute of Information Science of Beijing Jiaotong University (BJTU) in 2020 (advised by Prof. Yao Zhao). I was a Visiting Student with the Department of Computer Science, University of Rochester (UR) from 2018 to 2019, working with Prof. Ji Liu.
Research Interests
Machine learning, particularly data selection, zero-shot learning, and adversarial learning.
Computer vision, particularly image clustering, classification, and retrieval, motion segmentation, activity recognition, and video summarization.
News
- 2022/08 -- Our paper "Auto-Weighted Layer Representation Based View Synthesis Distortion Estimation for 3-D Video Coding" is accepted by IEEE Trans. on MM.
- 2022/07 -- Our paper "CoSCL: Cooperation of Small Continual Learners is Stronger than a Big One" is accepted by ECCV 2022.
- 2022/06 -- Our paper "The More, The Better? Active Silencing of Non-Positive Transfer for Efficient Multi-Domain Few-Shot Classification" and "One-step Low-Rank Representation for Clustering" are accepted by ACM MM 2022.
- 2022/06 -- Our paper "Diagnosing Ensemble Few-Shot Classifiers" is accepted by IEEE Transactions on Visualization and Computer Graphics.
- 2022/01 -- Our paper "Memory Replay with Data Compression for Continual Learning" is accepted by ICLR 2022.
- 2021/12 -- Our paper "Taking Modality-free Human Identification as Zero-shot Learning" is accepted by IEEE Trans. on CSVT.
- 2021/11 -- I obtained the China Postdoctoral Science Foundation (General Program).
- 2021/09 -- Our paper "Does deep machine vision have just noticeable difference (JND)?" is accepted by IEEE Trans. on CSVT.
- 2021/08 -- I obtained the Youth Foundation of National Natural Science Foundation of China.
- 2021/06 -- I obtained the China Postdoctoral Science Foundation (Special Funding).
- 2021/05 -- A chinese survey about propotype learning has been accepted by the Journal of Software.
- 2021/03 -- Our paper "Double Low-rank Representation with Projection Distance Penalty for Clustering" has been accepted by CVPR2021.
- 2021/02 -- Our paper "Does deep machine vision have just noticeable difference (JND)?" is available here.
- 2020/12 -- A review for recent works in Few-shot Learning is available here.
- 2020/04 -- Our paper has been accepted by Image and Vision Computing.
- 2020/03 -- Our paper has been accepted by IEEE Trans. on CSVT.
- 2020/02 -- Our paper has been accepted by CVPR 2020.
- 2019/12 -- I accepted the invitation to serve as Program Committee (PC) member of IJCAI 2020.
- 2019/12 -- Our paper has been accepted by CVM 2020.
- 2019/12 -- Our paper has been accepted by ACM TIST.
- 2019/11 -- One paper has been accepted by TMM.
- 2019/11 -- One paper has been accepted by NeuCom.
- 2019/10 -- I won the National Scholarship again.
Publications
Memory Replay with Data Compression for Continual Learning
The Tenth International Conference on Learning Representations (ICLR), 2022
[PDF]
[PDF]
机器学习中原型学习研究进展
Taking Modality-free Human Identification as Zero-shot Learning
IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2022
[PDF]
[PDF]
Double Low-Rank Representation With Projection Distance Penalty for Clustering
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021
[PDF]
[PDF]
Auto-weighted low-rank representation for clustering
ATZSL: Defensive Zero-Shot Recognition in the Presence of Adversaries
Defensive Few-shot Adversarial Learning
Does deep machine vision have just noticeable difference (JND)?
IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2021
[PDF]
[PDF]
Hierarchical Prototype Learning for Zero-Shot Recognition
IEEE Transactions on Multimedia (TMM), 2019
[PDF]
[PDF]
ProLFA: Representative Prototype Selection for Local Feature Aggregation
Neurocomputing (NeuCom), 2019
[PDF]
[PDF]
Seeing All From a Few: L1-Norm-Induced Discriminative Prototype Selection
IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2018
[PDF]
[PDF]
Sparsity induced prototype learning via Lp,1-norm grouping
Journal of Visual Communication and Image Representation (JVCI), 2018
[PDF]
[PDF]
Self-Supervised Deep Low-Rank Assignment Model for Prototype Selection
International Joint Conference on Artificial Intelligence (IJCAI), 2018
[PDF]
[PDF]
Learning a General Assignment Model for Video Analytics
IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2017
[PDF]
[PDF]
Distribution-induced Bidirectional Generative Adversarial Network for Graph Representation Learning
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020
[PDF]
[PDF]
To See in the Dark: N2DGAN for Background Modeling in Nighttime Scene
IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2020
[PDF]
[PDF]
Convolutional Prototype Learning for Zero-Shot Recognition
Image and Vision Computing (IVC), 2019
[PDF]
[PDF]
Canonical Correlation Analysis With L2,1-Norm for Multiview Data Representation
IEEE Transactions on Cybernetics (TCYB), 2019
[PDF]
[PDF]
A Theoretical Revisit to Linear Convergence for Saddle Point Problems
ACM Transactions on Intelligent Systems and Technology (ACM TIST), 2020
[PDF]
[PDF]
Understand Dynamic Regret with Switching Cost for Online Decision Making
ACM Transactions on Intelligent Systems and Technology (ACM TIST), 2019
[PDF]
[PDF]
Diffusion Induced Graph Representation Learning
Neurocomputing (NeuCom), 2019
[PDF]
[PDF]
A Novel Generalized Arnold Transform-based Zero-Watermarking Scheme
Applied Mathematics & Information Sciences (Appl Math Inf Sci), 2015
[PDF]
[PDF]
An Image Watermarking Scheme Using Arnold Transform and Fuzzy Smooth Support Vector Machine
Mathematical Problems in Engineering (MPE), 2015
[PDF]
[PDF]
多视角数据失补全
Honors and Awards
Service
Reviewer: AI, T-CSVT, T-NNLS, NeuCom, MTA, IJCAI-2019, IJCAI-2020.
Skills
Python & Matlab
Pytorch & Tensorflow
OpenCV & Scikit-learn
Linux & MacOS
