Leonid Sigal

Professor, University of British Columbia
 
 
 

Menu

Home | About | Biography | CV Students and Collaborators | Research | Teaching | Publications | Code and Data |

Contact

Dep. of Computer Science
University of British Columbia
ICCS 119
2366 Main Mall
Vancouver, B.C. V6T 1Z4
CANADA

Phone: 1-604-822-4368
Email: lsigal at cs.ubc.ca

About Me ...

Leonid Sigal's Photo

I am a Professor in the Department of Computer Science at the University of British Columbia. I am also an NSERC Canada Research Chair (CRC II) in Computer Vision and Machine Learning and a CIFAR AI Chair at the Vector Institute for AI in Toronto. In addition, I serve as an Academic Advisor to RBC/Borealis AI.

Prior to this I was a Senior Research Scientist at Disney Research Pittsburgh and an Adjunct Faculty member at Carnegie Mellon University.

My research focuses on problems of visual understanding and reasoning. This includes object recognition, scene understanding, articulated motion capture, motion modeling, action recognition, motion perception, manifold learning, transfer learning, character and cloth animation and a number of other directions on the intersection of computer vision, machine learning, and computer graphics.

My full bio and CV can be found here.

News and recent activity

  • I am a recipient of Killam Accelerator Fellowship.
  • I am a recipient of NSERC Canada Research Chair (CRC II) in Computer Vision and Machine Learning and the NSERC DAS award.
  • I am a recipient of CIFAR AI Chair.

Press coverage

Our work on semantic video event representation in CVPR 2016.

Our work on modeling action progression using LSTMs in CVPR 2016.

Our work on zero-shot pose estimation in AAAI 2016.

Our work on graph-based activity recognition in CVPR 2015.

Our work on story-driven photo album curation in WACV 2015.

Our work on body mounted camera motion capture in ACM SIGGRAPH 2011.

Some semi-recent research highlights:

(for full least see publications)

CVPR'25
Black Swan: Abductive and Defeasible Video Reasoning in Unexpected Events, A. Chinchure, S. Ravi, R. Ng, V. Shwartz, B. Li and L. Sigal, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025.
Project Page Paper Code

NeurIPS'25
Extending video masked autoencoders to 128 frames, N. B. Gundavarapu, L. Friedman, R. Goyal, C. Hegde, E. Agustsson, S. Waghmare, M. Sirotenko, M.-H. Yang, T. Weyand, B. Gong and L. Sigal, Neural Information Processing Systems (NeurIPS), 2025.
Project Page Paper

ECCV'24
TIBET: Identifying and Evaluating Biases in Text-to-Image Generative Models, A. Chinchure, P. Shukla, G. Bhatt, K. Salij, K. Hosanagar, L. Sigal and M. Turk, European Conference on Computer Vision (ECCV), 2024.
Project Page Paper Code

ECCV'24
Preventing Catastrophic Forgetting through Memory Networks in Continuous Detection, G. Bhatt, J. Ross and L. Sigal, European Conference on Computer Vision (ECCV), 2024.
Paper

CVPR'24
Prompting Hard or Hardly Prompting: Prompt Inversion for Text-to-Image Diffusion Models, S. Mahajan, T. Rahman, K.M. Yi and L. Sigal, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
Paper Code

CVPR'24
Plug-and-Play, Dense-Label-Free Extraction of Open-Vocabulary Semantic Segmentation from Vision-Language Models, L. Jiayun, S. Khandelwal, L. Sigal and B. Li, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
Paper

CVPR'24
Visual Prompting for Generalized Few-shot Segmentation: A Multi-scale Approach, M.R.I. Hossain, M. Siam, L. Sigal and J. Little, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
Paper Code

CVPR'23
Make-A-Story: Visual Memory Conditioned Consistent Story Generation, T. Rahman, H.-Y. Lee, J. Ren, S. Tulyakov, S. Mahajan and L. Sigal, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023.