![]() |
LI, Wen |
I am a professor with the School of Computer Science and Engineering, University of Electronic Science and Technology of China(SCSE, UESTC), leading the Data Intelligence Group(DIG).
I was working with Prof. Luc Van Gool as a postdoctoral researcher at the Computer Vision Laboratory, ETH Zurich, Switzerland. I obtained my PhD degree under the supervision of Prof. Dong Xu from the Nanyang Technological University(NTU) on 2015. I also worked closely with Prof. Ivor Wai-Hung Tsang during my PhD.
- |
Revisiting Deep Semi-supervised Learning: An Empirical Distribution Alignment Framework and Its Generalization Bound |
- |
WebVision Database: Visual Learning and Understanding from Web Data. |
![]() |
Denoised Maximum Classifier Discrepancy for Source-Free Unsupervised Domain Adaptation. |
![]() |
Counterfactual Debiasing Inference for Compositional Action Recognition |
![]() |
STST: Spatial-Temporal Specialized Transformer for Skeleton-based Action Recognition |
![]() |
DLOW: Domain Flow and Applications. |
![]() |
Scale-Aware Domain Adaptive Faster RCNN. |
![]() |
Unbiased Mean Teacher for Cross Domain Object Detection. |
![]() |
The Heterogeneity Hypothesis: Finding Layer-wise Dissimilated Network Architecture. |
![]() |
SRDAN: Scale-aware and Range-aware Domain Adaptation Network for Cross-dataset 3D Object Detection. |
![]() |
Cluster, Split, Fuse, and Update: Meta-Learning for Open Compound Domain Adaptive Semantic Segmentation. |
![]() |
Off-policy Reinforcement Learning for Efficient and Effective GAN Architecture Search. |
![]() |
Semi-Supervised Learning by Augmented Distribution Alignment. |
![]() |
Fast Image Restoration Networks with Multi-bin Trainable Linear Unit. |
![]() |
DLOW: Domain Flow for Adaptation and Generalization |
![]() |
Learning Semantic Segmentation from Synthetic Data: A Geometrically Guided Input-Output Adaptation Approach. |
![]() |
Sliced Wasserstein Generative Models. |
![]() |
Dividing and Aggregating Network for Multi-view Action Recognition |
![]() |
Semi-Supervised Optimal Transport for Heterogeneous Domain Adaptation |
![]() |
Domain Adaptive Faster R-CNN for Object Detection in the Wild |
![]() |
ROAD: Reality Oriented Adaptation for Semantic Segmentation of Urban Scenes |
![]() |
Appearance-and-Relation Networks for Video Classification |
![]() |
Collaborative and Adversarial Network for Unsupervised Domain Adaptation |
![]() |
Unsupervised Domain Adaptation for Face Anti-Spoofing |
![]() |
Domain Generalization and Adaptation using Low Rank Exemplar SVMs |
![]() |
Visual Recognition in RGB Images and Videos by Learning from RGB-D Data |
![]() |
An Exemplar-Based Multi-View Domain Generalization Framework for Visual Recognition |
![]() |
Learning Discriminative Correlation Subspace for Heterogeneous Domain Adaptation |
![]() |
Deep Domain Adaptation by Geodesic Distance Minimization |
![]() |
Visual Recognition by Learning from Web Data via Weakly Supervised Domain Generalization |
![]() |
Fast Algorithms for Linear and Kernel SVM+ |
![]() |
Exploiting Privileged Information from Web Data for Action and Event Recognition |
![]() |
Co-Labeling for Multi-view Weakly Labeled Learning |
![]() |
Multi-view Domain Generalization for Visual Recognition |
![]() |
Visual Recognition by Learning From Web Data: A Weakly Supervised Domain Generalization Approach |
![]() |
FaLRR: A Fast Low Rank Representation Solver |
![]() |
Distance Metric Learning using Privileged Information for Face Verification and Person Re-identification |
![]() |
Flowing on Riemannian Manifold: Domain Adaptation by Shifting Covariance |
![]() |
Learning with Augmented Features for Supervised and Semi-supervised Heterogeneous Domain Adaptation |
![]() |
Exploiting Low-rank Structure from Latent Domains for Domain Generalization |
![]() |
Exploiting Privileged Information from Web Data for Image Categorization |
![]() |
Recognizing RGB Images by Learning from RGB-D Data |
![]() |
Fusing Robust Face Region Descriptors via Multiple Metric Learning for Face Recognition in the Wild |
![]() |
Co-Labeling: A New Multi-View Learning Approach for Ambiguous Problems |
![]() |
Batch Mode Adaptive Multiple Instance Learning for Computer Vision Tasks |
![]() |
Text-based Image Retrieval Using Progressive Multi-Instance Learning |
![]() |
Improving Web Image Search by Bag-based Re-ranking |
Workshop Organizers:
Co-organizer of CVPR 2020 Workshop on Visual Understanding by Learning from Web Data.
Co-organizer of ICCV 2019 Workshop on Transferring and Adapting Source Knowledge (TASK) in Computer Vision (CV).
Co-organizer of CVPR 2019 Workshop on Visual Understanding by Learning from Web Data.
Co-organizer of ECCV 2018 Workshop on Transferring and Adapting Source Knowledge (TASK) in Computer Vision (CV).
Co-organizer of CVPR 2018 Workshop on Visual Understanding by Learning from Web Data.
Co-organizer of ICCV 2017 Workshop on Transferring and Adapting Source Knowledge (TASK) in Computer Vision (CV).
Co-organizer of CVPR 2017 Workshop on Visual Understanding by Learning from Web Data.
Co-organizer of ECCV 2016 Workshop on Transferring and Adapting Source Knowledge (TASK) in Computer Vision (CV).
Co-organizer of ICDM 2015 Workshop on Practical Transfer Learning.
Conference Reviewer:
Journal Reviewer: