I am a full professor with the Department of Electrical and Computer Engineering, University of Alberta. Prior to joining University of Alberta in year 2018, I worked at A*STAR, Singapore, TTI-Chicago, USA, and NICTA, Australia. I received my BSc degree in Computer Science from Jilin University in 1996, M. Eng. degree from Nankai University in 1999, and PhD in Computing Science from the University of Alberta in 2004. My research expertise is mainly on computer vision and machine learning.
Interests
- Computer Vision
- Machine Learning
Education
-
PhD, 2004
University of Alberta
-
MEng, 1999
Nankai University
-
BSc, 1996
Jilin University
Latest
- Our paper "Unleashing Multispectral Video's Potential in Semantic Segmentation: A Semi-supervised Viewpoint and New UAV-View Benchmark" is accepted by NeurIPS 2024.
- Unleashing Multispectral Video's Potential in Semantic Segmentation: A Semi-supervised Viewpoint and New UAV-View Benchmark
- Our paper "RegionGrasp: A Novel Task for Contact Region Controllable Hand Grasp Generation" is accepted by European Conference on Computer Vision (ECCV) Workshop HANDS@ECCV2024!
- RegionGrasp: A Novel Task for Contact Region Controllable Hand Grasp Generation
- GSD: View-Guided Gaussian Splatting Diffusion for 3D Reconstruction
- Our paper "GSD: View-Guided Gaussian Splatting Diffusion for 3D Reconstruction" is accepted by European Conference on Computer Vision (ECCV) 2024!
- Our paper "RACon: Retrieval-Augmented Simulated Character Locomotion Control " is accepted by IEEE International Conference on Multimedia & Expo (ICME) 2024 for oral presentation!
- RACon: Retrieval-Augmented Simulated Character Locomotion Control
- MoMask: Generative Masked Modeling of 3D Human Motions
- Our paper "MoMask: Generative Masked Modeling of 3D Human Motions " is accepted by IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2024!
- Generative Human Motion Stylization in Latent Space
- Our paper "Generative Human Motion Stylization in Latent Space " is accepted by International Conference on Learning Representations (ICLR) 2024!
- DVSOD: RGB-D Video Salient Object Detection
- SemanticRT: A Large-Scale Dataset and Method for Robust Semantic Segmentation in Multispectral Images
- Our CVPR 2023 workshop paper "Segment Anything Is Not Always Perfect: An Investigation of SAM on Different Real-world Applications" has won the most insightful paper award presented by the 1st Workshop on Vision-based InduStrial InspectiON!
- Segment Anything Is Not Always Perfect: An Investigation of SAM on Different Real-world Applications
- BigNeuron: A resource to benchmark and predict best-performing algorithms for automated reconstruction of neuronal morphology
- Multispectral Video Semantic Segmentation: A Benchmark Dataset and Baseline
- Our paper "Multispectral Video Semantic Segmentation: A Benchmark Dataset and Baseline" is accepted by IEEE Conference on Computer Vision and Pattern Recognition 2023!
- Delving into Calibrated Depth for Accurate RGB-D Salient Object Detection
- Snipper: A Spatiotemporal Transformer for Simultaneous Multi-Person 3D Pose Estimation Tracking and Forecasting on a Video Snippet
- Our paper "Delving into Calibrated Depth for Accurate RGB-D Salient Object Detection" is accepted by Interactional Journal of Computer Vision (IJCV) 2023!
- Resource-Efficient Medical Image Analysis
- Object Wake-up: 3D Object Rigging from a Single Image.
- Our paper "Object Wake-up: 3D Object Rigging from a Single Image" is accepted by European Conference on Computer Vision (ECCV) 2022!
- Our paper "TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts." is accepted by European Conference on Computer Vision (ECCV) 2022!
- TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts.
- Human Pose and Shape Estimation from Single Polarization Images
- Our paper "Contrastive Learning for Unsupervised Video Highlight Detection" is accepted by IEEE Conference on Computer Vision and Pattern Recognition(CVPR) 2022!
- Our paper "Exploring Denoised Cross-video Contrast for Weakly-supervised Temporal Action Localization" is accepted by IEEE Conference on Computer Vision and Pattern Recognition(CVPR) 2022!
- Our paper "Generating Diverse and Natural 3D Human Motions from Text" is accepted by IEEE Conference on Computer Vision and Pattern Recognition(CVPR) 2022!
- Action2video: Generating Videos of Human 3D Actions
- DMRA: Depth-induced Multi-scale Recurrent Attention Network for RGB-D Saliency Detection
- Promoting Saliency From Depth: Deep Unsupervised RGB-D Saliency Detection
- Investigating Pose Representations and Motion Contexts Modeling for 3D Motion Prediction
- Our paper "Action2video: Generating Videos of Human 3D Actions" is accepted by International Journal of Computer Vision(IJCV) 2022!
- Our paper "Investigating Pose Representations and Motion Contexts Modeling for 3D Motion Prediction" is accepted by IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)!
- Joint Semantic Mining for Weakly Supervised RGB-D Salient Object Detection
- Our paper "Joint Semantic Mining for Weakly Supervised RGB-D Salient Object Detection" is accepted by NeurIPS 2021
- 3D Pose Estimation and Future Motion Prediction from 2D Images
- Our paper "3D pose estimation and future motion prediction from 2D images" is accepted by Pattern Recogntion
- CHASE: Robust Visual Tracking via Cell-Level Differentiable Neural Architecture Search
- Enhancing Human Motion Assessment by Self-supervised Representation Learning
- Our paper "CHASE: Robust Visual Tracking via Cell-Level Differentiable Neural Architecture Search" is accepted by BMVC 2021
- Our paper "Enhancing Human Motion Assessment by Self-supervised Representation Learning" is accepted by BMVC 2021
- Automated Generation of Accurate and Fluent Medical X-ray Reports
- EventHPE: Event-based 3D Human Pose and Shape Estimation
- Joint Visual and Audio Learning for Video Highlight Detection
- Our paper "Automated Generation of Accurate & Fluent Medical X-ray Reports" is accepted by EMNLP 2021
- Dual Learning Music Composition and Dance Choreography
- Our paper "Dual Learning Music Composition and Dance Choreography" is accepted by ACM Multimedia 2021
- Our paper "EventHPE: Event-based 3-D Human Pose Estimation" is accepted by ICCV 2021
- Our paper "Joint Visual and Audio Learning for Video Highlight Detection" is accepted by ICCV 2021
- Our paper "Calibrated RGB-D Salient Object Detection" is accepted by IEEE Conference on Computer Vision and Pattern Recognition 2021
- Our paper "Learning Calibrated Medical Image Segmentation via Multi-rater Agreement Modeling" is accepted by IEEE Conference on Computer Vision and Pattern Recognition 2021 (Best Paper Candidate)
- Calibrated RGB-D Salient Object Detection
- Learning Calibrated Medical Image Segmentation via Multi-rater Agreement Modeling
- Stabilizing Training of Generative Adversarial Nets via Langevin Stein Variational Gradient Descent
- Our paper "Deep Learning for Visual Tracking: A Comprehensive Survey" is accepted by IEEE Transactions on Intelligent Transportation Systems (T-ITS)
- Action2Motion: Conditioned Generation of 3D Human Motions
- Our paper "Action2Motion: Conditioned Generation of 3-D Human Motions" is accepted by ACM Multimedia 2020
- Our paper "3D Human Shape Reconstruction from a Polarization Image" is accepted by ECCV 2020
- 3D Human Shape Reconstruction from a Polarization Image
- FALCONS: FAst Learner-grader for CONtorted poses in Sports
- SparseFusion: Dynamic Human Avatar Modeling from Sparse RGBD Images
- 3D Pose Estimation and Future Motion Prediction from 2D Images
- Towards Natural and Accurate Future Motion Prediction of Humans and Animals
- Hierarchical Motion Recurrent Network for Future Motion Prediction of Humans and Animals