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. Hang Zhou, who recently joined in our lab as a Postdoc Fellow.

Welcome Jun Zhou, who recently joined in our lab as a visiting PhD student.

Our paper "Unleashing Multispectral Video's Potential in Semantic Segmentation: A Semi-supervised Viewpoint and New UAV-View Benchmark" is accepted by NeurIPS 2024.

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

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!

Recent Publications

Wei Ji, Jingjing Li, Wenbo Li, Yilin Shen, Li Cheng, Hongxia Jin (2024). Unleashing Multispectral Video's Potential in Semantic Segmentation: A Semi-supervised Viewpoint and New UAV-View Benchmark. Neural Information Processing Systems (NeurIPS).

Yilin Wang, Chuan Guo, Li Cheng, Hai Jiang (2024). RegionGrasp: A Novel Task for Contact Region Controllable Hand Grasp Generation. European Conference on Computer Vision (ECCV) Workshops.

Yuxuan Mu, Xinxin Zuo, Chuan Guo, Yilin Wang, Juwei Lu, Xiaofeng Wu, Songcen Xu, Peng Dai, Youliang Yan, Li Cheng (2024). GSD: View-Guided Gaussian Splatting Diffusion for 3D Reconstruction. European Conference on Computer Vision (ECCV).

Yuxuan Mu, Shihao Zou, Kangning Yin, Zheng tian, Li Cheng, Weinan Zhang, Jun Wang (2024). RACon: Retrieval-Augmented Simulated Character Locomotion Control. IEEE International Conference on Multimedia & Expo (ICME), Oral.

Chuan Guo, Yuxuan Mu, Muhammad Gohar Javed, Sen Wang, Li Cheng (2024). MoMask: Generative Masked Modeling of 3D Human Motions. Computer Vision and Pattern Recognition (CVPR).

See all publications

Journal Club

Coming Talks:

MultiPly: Reconstruction of Multiple People from Monocular Video in the Wild
- By Yande, Sept 20, 2024 - [Talk Slides] [Original Paper]
IMAGEBIND: One Embedding Space To Bind Them All
- By Jingjing, Sept 20, 2024 - [Talk Slides] [Original Paper]

Finished Talks:

Telling Left from Right: Identifying Geometry-AwareSemantic Correspondence
- By Siyuan, August 19, 2024 - [Talk Slides] [Original Paper]
Achieving Human Level Competitive Robot Table Tennis
- By Gohar, August 19, 2024 - [Talk Slides] [Original Paper]

Check Full List.