LECTURES
Speakers | Syllabus | Titles & Abstracts |
Michael Bronstein Twitter Inc. & University of Oxford, UK |
Geometric Deep Learning | Geometric Deep Learning - The Erlangen Programme of ML |
Dima Damen University of Bristol, UK |
Video Understanding, Fine-Grained, Multi-Modal, Egocentric | Video Understanding - an Egocentric Perspective |
David Forsyth University of Illinois, USA |
Fake Data, Mathematical Structure, Intrinsic Images, Scene Relightning | Learning shading and lighting without ground truth |
Abhishek Gupta Massachusetts Institute of Technology, USA |
Deep Reinforcement Learning, Robotics | How to Train Your Robot: Techniques for Enabling Robotic Learning in the Real World |
Matthew Johnson Microsoft Research, Cambridge, UK |
Fourier Feature Networks, Neural Rendering, Volumetric Ray Casting, Azure Machine Learning | Fourier Feature Networks and Neural Volume Rendering |
Laura Leal-Taixé Technische Universität München, DE |
Multi-Object Tracking (MOT), Tracking-by-Regression, Tracking-by-Attention | Shifting paradigms in multi-object tracking |
Hao Li Pinscreen, Inc. & MBZUAI, UAE |
Neural Rendering, Dialogue Replacement | Don't get lost in Translation: The Neural Rendering of the Champion |
Matthias Niessner Technische Universität München, DE |
Neural Rendering, 3D Reconstruction, Differentiable Optimization | Neural Rendering meets 3D Reconstruction |
Gerhard Reitmayr Qualcomm, US |
Augmented Reality, Virtual Reality | Trends and Challenges in Building XR devices |
Elisa Ricci University of Trento, IT |
Learning to adapt: paradigms and challenges in adapting deep models to domain and semantic shift | Learning to adapt: paradigms and challenges in adapting deep models to domain and semantic shift |
Davide Scaramuzza ETH Zürich, CH |
Autonomous Robots, Perception and Control | Learning Robot Navigation: from Perception to Action |
Jamie Shotton Wayve, UK |
Autonomous Vehicles, Embodied AI | The Next Frontier in Embodied AI: Autonomous Vehicles |
Vincent Sitzmann Massachusetts Institute of Technology, USA |
3D vision, Neural Rendering, Visual Representations, Self-Supervised Learning | Learning to Perceive the 3D World from 2D Images |
Andrea Vedaldi University of Oxford, UK |
Unsupervised Learning, Contrastive Learning, 3D Geometry | Meaningful unsupervised learning: from labelling to 3D geometry |
READING GROUP (WITH PRIZE!)
Speakers | Syllabus | Rules of Engagement |
Stefano Soatto Amazon and University of California Los Angeles, USA |
Reading Group Competition | Sent by email |
ESSAY COMPETITION (WITH PRIZE!)
Speakers | Syllabus | Rules of Engagement |
Fabio Galasso Sapienza University of Rome, Italy |
Essay Competition | Sent by email |
INDUSTRY MEETS STUDENTS
Industrial Panel
- Ambarella-VISLAB, US
- AWS, Amazon, US
- Google, US
- ImageS, IT
- Intel, US
- Leonardo, IT
- Microsoft, US
- Naver Labs, EU
- PTC - Vuforia, AT
- Qualcomm, US
- Rakuten, JP
- Reality Labs Research, US
- STMicroelectronics, IT
- Toshiba Research Europe, UK
- Toyota Europe Motor, BE
- Wayve, UK