Leonid Sigal

Faculty Member

Associate Professor, Department of Computer Science, University of British Columbia

Canada CIFAR Artificial Intelligence Chair

Leonid Sigal is an Associate Professor in the Department of Computer Science at the University of British Columbia. Prior to that, he was a Senior Research Scientist at Disney Research Pittsburgh and an Adjunct Faculty member at Carnegie Mellon University. He received his PhD in Computer Science from Brown University and completed a postdoctoral fellowship at the University of Toronto. Leonid also serves as scientific advisor for Borealis AI.

Leonid’s research interests are primarily in computer vision, machine learning, and computer graphics. His research focuses on problems of visual and multi-modal (visual, textural, auditory) understanding, reasoning and generation. This includes object recognition, scene understanding, articulated motion capture, action recognition, representation learning, manifold learning, transfer learning, character and cloth animation.

Research Interests

  • Computer Vision
  • Machine Learning
  • Computer Graphics
  • Neural Networks


  • NSERC Canada Research Chair (Tier 2) in Computer Vision and Machine Learning (2018-2023)
  • Recipient of NSERC Discovery Accelerator Supplement (2018-2021)
  • Recipient of Killam Accelerator Research Fellowship (2021-2023)
  • Associate Editor for IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI) and Computer Vision and Image Understanding (CVIU)
  • Area chair for ECCV (2014, 2018), IEEE ICCV (2015), IEEE CVPR (2019)
  • Advisor, Borealis AI


Human pose estimation

Leonid Sigal


Discriminative feature alignment: Improving transferability of unsupervised domain adaptation by Gaussian-guided latent alignment

Jing Wang and Jiahong Chen and Jianzhe Lin and Leonid Sigal and Clarence W de Silva


Referring transformer: A one-step approach to multi-task visual grounding

Muchen Li and Leonid Sigal


Weakly-supervised audio-visual sound source detection and separation

Tanzila Rahman and Leonid Sigal


PROVIDE: a probabilistic framework for unsupervised video decomposition

Polina Zablotskaia and Edoardo A Dominici and Leonid Sigal and Andreas M Lehrmann


Guest editorial introduction to the special issue on large-scale visual sensor networks: architectures and applications

Paolo Spagnolo and Hamid Aghajan and George Bebis and Shaogang Gong and Amy Loutfi and Leonid Sigal and Wei-Shi Zheng


TriBERT: Human-centric Audio-visual Representation Learning

Tanzila Rahman and Mengyu Yang and Leonid Sigal


Probabilistic Label-Efficient Deep Generative Structures (PLEDGES)

Avi Pfeffer and Catherine Call and Frank Wood and Brad Rosenberg and Kirstin Bibbiani and Leonid Sigal and Ishaan Shah and Deniz Erdogmus and Sameer Singh and Jan W van de Meent