Vision and Learning Lab is led by Dr. Li Cheng at the Department of Electrical and Computer Engineering, University of Alberta. Our research centers around computer vision, machine learning, visual behavior analysis, biomedical image anlysis, and multimedia signal processing.

News

Welcome Dr. Pengyu Zhang, who recently joined in our lab as a Postdoc Fellow.

Congrats to Hang Zhou for having two papers being accepted into CVPR 2025!

Congrats to Jun for his paper, Hand Gesture Recognition from an Open-Set Perspective, being accepted recently by IEEE TMM!

Two papers in our lab are accepted into ICLR 2025. They are 1st authored by Yilin and Gohar, respectively. Congratulations!

Welcome Dr. Jing Wang, who recently joined in our lab as a Postdoc Fellow.

Recent Publications

Shihao Zou, Yuanlu Xu, Nikolaos Sarafianos, Federica Bogo, Tony Tung, Weixin Si, Li Cheng (2025). Generating High-Fidelity Clothed Human Dynamics with Temporal Diffusion. ACM Transactions on Multimedia Computing, Communications and Applications.

Guorui Liao, Chunyuan Zheng, Li Cheng, Haoyu Xie, Shanshan Huang, Jun Liao, Haoxuan Li, Li Liu (2025). HiPoser: 3D Human Pose Estimation with Hierarchical Shared Learning at Parts-Level Using Inertial Measurement Units. Association for the Advancement of Artificial Intelligence (AAAI).

Hang Zhou, Xinxin Zuo, Rui Ma, Li Cheng (2025). BOOTPLACE: Bootstrapped Object Placement with Detection Transformers. Computer Vision and Pattern Recognition (CVPR).

PDF Code Project

Weitao Feng, Hang Zhou, Jing Liao, Li Cheng, Wenbo Zhou (2025). CASAGPT: Cuboid Arrangement and Scene Assembly for Interior Design. Computer Vision and Pattern Recognition (CVPR).

Yilin Wang, Chuan Guo, Yuxuan Mu, Muhammad Gohar Javed, Xinxin Zuo, Juwei Lu, Hai Jiang, Li Cheng (2025). MotionDreamer: One-to-Many Motion Synthesis with Localized Generative Masked Transformer. International Conference on Learning Representations (ICLR).

See all publications

Journal Club

Coming Talks:

VGGT: Visual Geometry Grounded Transformer
- By Hang, Aug 19, 2025 - [Talk Slides] [Original Paper]
CVPR 2025 Paper Sharing
- By Jingjing, Aug 19, 2025 - [Talk Slides]
High-Authenticity and High-Fidelity Multimodal Generation
- By Prof. Shijian Lu, Aug 21, 2025

Finished Talks:

Model Unification for Object Tracking and Segmentation
- By Pengyu, July 7, 2025 - [Talk Slides] [Original Paper1] [Original Paper2]
Evaluating the Potential of Hardware-Accelerated Neural Rendering to Supplant Ray Tracing
- By Siyuan, July 7, 2025

Check Full List.