Peyman Bateni

I am currently working on Beam AI with the wonderfully knowledgable Dr. Leonid Sigal. At Beam AI, we enable mobile apps to monitor user stress through the selfie camera in real-time. Learn more at beamhealth.ai.

I completed my graduate studies in Machine Learning at the University of British Columbia under the supervision of Dr. Frank Wood where I divided my time between UBC PLAI Group as a graduate researcher and Inverted AI as a research engineer. Previously, I completed my undergraduate studies in Computer Science at the University of British Columbia. During my time at UBC, I also had the pleasure of collaborating with Dr. Leonid Sigal and Dr. Guiseppe Carenini on a range of Computer Vision / NLP problems.

Email  /  GitHub  /  PapersWithCode  /  Twitter  /  LinkedIn

Google Scholar  /  DBLP  /  ResearchGate  /  YouTube

profile photo
Research / Publications

I'm broadly interested in developing methods that allow for intelligent reasoning within the visual space. My past research has primarily focused on few-shot and semi-supervised learning of object classifiers and detectors. More recently, I've begun work on developing methods for continuous monitoring of mental health on mobile devices.

Real-Time Monitoring of User Stress, Heart Rate and Heart Rate Variability on Mobile Devices
Peyman Bateni, Leonid Sigal
ArXiv  /  Code  /  Bibtex  /  PapersWithCode  /  Video

On Label-Efficient Computer Vision: Building Fast and Effective Few-Shot Image Classifiers
Peyman Bateni - Supervisor: Frank Wood, Second Reader: Leonid Sigal
Master's Thesis
UBC cIRcle Archives  /  Code  /  Bibtex  /  PapersWithCode  /  Video

Beyond Simple Meta-Learning: Multi-Purpose Models for Multi-Domain, Active and Continual Few-Shot Learning
Peyman Bateni, Jarred Barber, Raghav Goyal, Vaden Masrani, Jan-Willem van de Meent, Leonid Sigal, Frank Wood
Neural Networks by Elsevier (Official Journal of the International Neural Network Society, European Neural Network Society & Japanese Neural Network Society), 2022 (in submission)
ArXiv  /  Code  /  Bibtex  /  PapersWithCode

Enhancing Few-Shot Image Classification with Unlabelled Examples
Peyman Bateni*, Jarred Barber*, Jan-Willem van de Meent, Frank Wood
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2022 - Algorithm Track
Paper  /  ArXiv  /  Code  /  Bibtex  /  PapersWithCode  /  Video

Imagining The Road Ahead: Multi-Agent Trajectory Prediction via Differentiable Simulation
Adam Scibior, Vasileios Lioutas, Daniele Reda, Peyman Bateni, Frank Wood
IEEE International Conference on Intelligent Transportation (ITSC), 2021
(A short-form version of this paper was also presented at the Autonomous Driving: Perception, Prediction and Planning Workshop at CVPR 2021 where it was awarded Best Paper)

Paper  /  ArXiv  /  Bibtex  /  PapersWithCode  /  Video

Neural RST-based Evaluation of Discourse Coherence
Grigorii Guz*, Peyman Bateni*, Darius Muglich, Giuseppe Carenini
Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (AACL) and the International Joint Conference on Natural Language Processing (IJCNLP), 2020
Paper  /  ArXiv  /  Code  /  Bibtex  /  PapersWithCode  /  Video

Improved Few-Shot Visual Classification
Peyman Bateni, Raghav Goyal, Vaden Masrani, Frank Wood, Leonid Sigal
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020
(A short-form version of this paper was also presented at the Visual Learning with Limited Labels Workshop at CVPR 2020)
Paper  /  ArXiv  /  Code  /  Bibtex  /  PapersWithCode  /  Video


Website adapted from Jon Barron