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

Our paper "SAM3-I: Segment Anything with Instructions" is accepted by the main track of ACL 2026

Welcome Emanuel de la Cruz Espinosa, who recently joined in our lab as a visiting PhD student.

Welcome Kiarash, who recently joined in our lab as a MSc student.

Congrats to Hang Zhou for his paper, titled 'PICS: Pairwise Image Compositing with Spatial Interactions', being accepted by ICLR 2026.

Welcome Dr. Bohan Wei, who recently joined in our lab as a Postdoc Fellow.

Recent Publications

Hang Zhou, Xinxin Zuo, Sen Wang, Li Cheng (2026). PICS: Pairwise Image Compositing with Spatial Interactions. International Conference on Learning Representations (ICLR).

PDF Code Project Video

Jun Zhou, Chi Xu, Kaifeng Tang, Yuting Ge, Tingrui Guo, Li Cheng (2025). VPHO: Joint Visual-Physical Cue Learning and Aggregation for Hand-Object Pose Estimation. AAAI 2026.

Jing Wang, Weiting Peng, Jing Tang, Zeyu Gong, Xihua Wang, Bo Tao, Li Cheng (2025). Act to See, See to Act: Diffusion-Driven Perception-Action Interplay for Adaptive Policies. Neural Information Processing Systems (NeurIPS).

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).

See all publications

Journal Club

Coming Talks:

June 2026:

AniGen: Unified S3 Fields for Animatable 3D Asset Generation
- By Ji, Jun 2, 2026 - [Talk Slides] [Original Paper]
Image Generators are Generalist Vision Learners
- By Jingjing, Jun 2, 2026 - [Original Paper]

Finished Talks:

DreamControl: Human-Inspired Whole-Body Humanoid Control for Scene Interaction via Guided Diffusion
- By Kiarash, May 15, 2026 - [Talk Slides] [Original Paper]
VACE: All-in-One Video Creation and Editing
- By Siyuan, May 15, 2026 - [Talk Slides] [Original Paper]

Check Full List.