News

1 paper (Whole-Scene Image Holistic Semantic Segmentation) was accepted to IEEE TPAMI.

1 paper (Generalizble Training-Free 3D Pose Estimation) was accepted to IEEE TPAMI.

1 ACL (Efficient Optimization-based LLM Pruning) and 1 ICCV (Heterogeneous Knowledge Distillation) papers were accepted.

2 papers were accepted to ICML (Multi-Task Grouping, Efficient Diffusion Models).

1 ICLR (Auxiliary Learning), 2 CVPR (V-L Model Robust Finetuning, Image Matching), and 1 AAAI (Shape Analysis) papers were accepted.

For incoming PhD/master students, and undergraduate students from WHU who are interested in doing Machine Learning and Computer Vision researches with me, welcome to drop me an email with your CV attached.

I joined Wuhan University as an Associate Professor. I am currently working on Multi-Task/Modal Learning, Efficient Deep Learning (Training & Inference), and 3D Computer Vision.

Our paper: “MTL-NAS: Task-Agnostic Neural Architecture Search towards General-Purpose Multi-Task Learning” has been accepted to CVPR2020.

Our paper: “Estimation of 3D Category-Specific Object Structure: Symmetry, Manhattan and or Multiple Images” has been accepted to IJCV.

Two papers: “NDDR-CNN: Layerwise Feature Fusing in Multi-Task CNNs by Neural Discriminative Dimensionality Reduction” and “Face Anti-Spoofing: Model Matters, So Does Data” have been accepted to CVPR2019.