OWCV2021

(Virtual)

April 21-22, 2021

More info ↓

About the event

Ontario Workshop on Computer Vision (OWCV) is a computer vision workshop, organized by and for the major computer vision labs in Ontario. It is an opportunity for students to present their prospective submissions to a friendly, constructively critical audience, interact with fellow researchers, and to get valuable feedback.

Schedule



Follow us on Twitter!

Important Dates

Submission deadline : April 5, 2021 11:59pm Toronto time

Registration deadline : April 10, 2021 11:59pm Toronto time

Formal registration is closed. But if you're still interested in attending, please email owcv2021@gmail.com!

Call for Papers

Keynote Speakers

Graham Taylor

Associate Professor and Canada Research Chair in Machine Learning
Canada CIFAR AI Chair
School of Engineering, University of Guelph and Vector Institute
Academic Director, NextAI


Title: Advances in Conditional Generative Models

Abstract: In this talk, I will provide an overview of my group's recent work in the domain of conditional generative models. Conditional generative models take some context (the condition) and perform controlled synthesis: text, images, or some other kind of structured output. They are computationally intensive, unwieldy to train and we struggle to evaluate them, given the subjective nature of their creations.

With Facebook AI Research (FAIR) we investigated ways to quantitatively evaluate generative models' outputs in a way that captures quality, diversity and consistency with the instructions we provide them. With FAIR we also showed that more data is not always better when it comes to generative models: a novel automatic data selection process can make training easier and resulting models more robust, with little reduction of diversity. Moreover, this technique massively reduces the computational requirements, making large-scale models more accessible to a wider range of users. In a recent collaboration with Microsoft Research and Mila we advocated for a departure from characteristic "single-shot" type generation. We proposed a method for iterative image generation, inspired by the way a sketch artist composes a scene. Departing from pixel-based outputs, I will also discuss graph-based generative models for constructing physical assemblies, starting with the children's toy LEGO.

Alexander Wong

Canada Research Chair in Artificial Intelligence and Medical Imaging
Member, College of the Royal Society of Canada
Associate Professor, P.Eng.
Co-Director, Vision and Image Processing (VIP) Research Group
Department of Systems Design Engineering, University of Waterloo


Title: Road to Operational AI: Challenges and Opportunities

Abstract: Tremendous advances in artificial intelligence over the past two decades have led to a significant interest in leveraging artificial intelligence across enterprises and industries. However, despite these tremendous opportunities and the significant successes experienced by large, technology enterprises in reaping the benefits of artificial intelligence in delivering better solutions with great value, the widespread adoption of operational artificial intelligence has seen very limited success in many industries and scenarios. In fact, even early successes in adoption have started to surface additional issues that hinder further deployment and adoption. In this talk, I will discuss some of the key challenges in the operationalization of artificial intelligence, ranging from scalability to trust and dependability, and some potential solutions for addressing these challenges.

Sanja Fidler

Associate Professor, University of Toronto
Director of AI, NVIDIA
Vector Institute (co-founder)



Title: Towards AI for 3D Content Creation

Abstract: 3D content is key in several domains such as architecture, film, gaming, and robotics. However, creating 3D content can be very time consuming -- the artists need to sculpt high quality 3d assets, compose them into large worlds, and bring these worlds to life by writing behaviour models that "drives" the characters around in the world. In this talk, I'll discuss some of our recent efforts on introducing automation in the 3D content creation process using A.I.

Michael Brown

Canada Research Chair in Computer Vision
Dept. of Electrical Engineering and Computer Science, York University



Title: In-Camera Color Processing

Abstract: This is a two-part presentation. The first part will provide an overview of how your digital camera processes the sensor image (RAW) to the final output image (sRGB-JPEG). The second part of the presentation will discuss research targeting various aspects of the in-camera processing pipeline, including demosaicing, denoising, white-balance, and general color processing.

Schedule

Accepted Papers

Day 1 Day 2
  • 1. CLAR: Contrastive Learning of Auditory Representations - Haider Al-Tahan, Yalda Mohsenzadeh
  • 3. Automatic Abbreviation of Hockey Videos - Hemanth Pidaparthy, Michael Dowling, James Elder
  • 5. Understanding Gene Model Maps - Michael Lombardo, Faisal Qureshi
  • 7. Identifying and interpreting tuning dimensions in deep networks - Nolan S. Dey, J. Eric Taylor, Bryan P. Tripp, Alexander Wong, Graham W. Taylor
  • 9. Zero-shot Learning with Class Description Regularization - Shayan Kousha, Marcus A. Brubaker
  • 11. Active Correspondences Projector-Camera (Procam) Sensors - Jonathon Malcolm, Ian J. Maquignaz
  • 13. Normalizing Flow for semi-supervised learning - Vincent Sham
  • 15. Wavelet Flow: Fast Training of High Resolution Normalizing Flows - Jason J. Yu, Konstantinos G. Derpanis, Marcus A. Brubaker
  • 17. Hyperspectral pixel unmixing with Deep Variational Inference - Kiran Mantripragada, Faisal Z. Qureshi
  • 19. Training neural networks for feature alignment - Siavash Rezaei
  • 21. SSTVOS: Sparse Spatiotemporal Transformers for Video Object Segmentation - Brendan Duke, Abdalla Ahmed, Christian Wolf, Parham Aarabi, Graham W. Taylor
  • 23. Unsupervised Image Demoireing using Implicit Neural Representation - Seonghyeon Nam, Marcus A. Brubaker, Michael S. Brown
  • 25. Precisely calibrated and spatially informed illumination for conventional fluorescence and improved PALM imaging applications - Angel Mancebo, Luke DeMars, Christopher T Ertsgaard, Elias M Puchner
  • 27. Topo Sampler: A Topology Constrained Noise Sampling for GANs - Adrish Dey, Sayantan Das
  • 2. Transformer-Based Network For Image Operator Approximation - Ian MacPherson
  • 4. Contrastive Learning for Sports Video: Unsupervised Player Classification - Maria Koshkina, Hemanth Pidaparthy, James Elder
  • 6. Renal Boundary and Tumour Detection in MRI using U-Net with Transfer Learning - Anush Agarwal, Nicola Schieda, Mohamed Elfaal, Eranga Ukwatta
  • 8. OLED: One-Class Learned Encoder-Decoder Network with Adversarial Context Masking for Novelty Detection - John Taylor Jewell, Vahid Reza Khazaie, Yalda Mohsenzadeh
  • 10. Object completion with stochastic completion fields - Morteza Rezanejad, Sidharth Gupta, Chandra Gummaluru, Ryan Marten, John Wilder, Michael Gruninger, Dirk Walther
  • 12. Deep Learning-Based Segmentation of Neonatal Cerebral Lateral Ventricles from 3D Ultrasound Images - Zachary Szentimrey, Sandrine de Ribaupierre, Aaron Fenster, Eranga Ukwatta
  • 14. Scale and translation invariance preserving operators on distributions of images - Xavier Snelgrove, Sven Dickinson, Marcus Brubaker
  • 16. Noise2NoiseFlow: Learning Camera Noise Models without Corresponding Clean Images - Ali Maleky, Michael S. Brown, Marcus A. Brubaker
  • 18. Procam Calibration from a Single Pose of a Planar Target - Ghani O. Lawal, Michael Greenspan
  • 20. Structured Visual Search via Composition-aware Learning - Mert Kilickaya, Arnold Smeulders
  • 22. Learning by Aligning Videos in Time - Sanjay Haresh, Sateesh Kumar, Huseyin Coskun, Shahram N. Syed, Andrey Konin, M. Zeeshan Zia, Quoc-Huy Tran
  • 24. A study on the effects of compression on hyperspectral image classification - Kiran Mantripragada, Faisal Z. Qureshi, Phuong D. Dao, Yuhong He
  • 26. Improved 6 DOF Pose Estimation Using Post-Processing Validation - Joy Mazumder, Mohsen Zand, Michael Greenspan

Organizers

Organizing Co-Chair

Matt Kowal

PhD student, Ryerson University
Postgraduate Affiliate, Vector Institute

Organizing Co-Chair

Vikram Voleti

PhD candidate, Mila
Visiting Researcher, University of Guelph

Program Chair

Calden Wloka

Post-doctoral Visitor,
York University

General Chair

Marcus Brubaker

Assistant Professor, York University
Faculty Affiliate, Vector Institute
Adjunct Professor, University of Toronto

Program Committee

Abdullah Abuolaim

PhD candidate,
York University

Iuliia Kotseruba

PhD student,
York University

Contact

Any questions at all? Send us an email!

Contact

Thanks to graphquon.github.io for the website theme!