LECTURES
Speakers | Syllabus | Titles & Abstracts |
Alexei Efros UC Berkeley, US |
Deep Learning for Vision | Deep Learning for Vision: the Hype, the Magic, and Open Challenges |
Irfan Essa Georgia Institute of Technology and Google Research, US |
Video Analysis, Video Compression, Registration and Alignment, Video Segmentation and Tracking, Action/Activity Recognition | Computational Video: Can we just extend all image-based approaches to video by applying image analysis to all the frames? |
Andreas Geiger University of Tübingen and MPI-IS Tübingen, DE |
3D Reconstruction, Graphical Models, 3D Representations, Deep Learning | Probabilistic and Deep Models for 3D Reconstruction |
Kristen Grauman University of Texas at Austin and Facebook AI Research, US |
First Person Vision, Anticipation | First-Person Perception by Anticipating the Unseen and Unheard |
Abhinav Gupta Carnegie Mellon University, US |
Self-supervised Learning, Visual Representations, Perception and Action | Self-supervised Learning of Visual Representations for Perception and Action |
Phillip Isola Massachusetts Institute of Technology, US |
Generative Models, Image Syntesis | Image synthesis with deep generative models |
Alex Kendall Wayve and University of Cambridge, UK |
Autonomous Driving, domain adaptation, imitation learning, reinforcement learning | Training Deep Learning to Drive in the Real World with Computer Vision |
Ira Kemelmacher-Shlizerman Allen School of Computer Science, UW, US |
AR/VR applications | People modeling and AR/VR applications |
Jitendra Malik University of California at Berkeley, US |
3D vision, recognition, reconstruction, Perception and control, Hilbert problems of computer vision | What problems does computer vision need to solve? |
Richard Newcombe Facebook Reality Labs, US |
Spatial AI | Spatial AI at the Frontier of XR, Robotics & AI Assistants |
Torsten Sattler Chalmers University of Technology, SE |
Visual Localization | Visual Localization |
Davide Scaramuzza ETH Zürich, CH |
Robot Vision | Robot Vision: from Frame-based to Event-based Cameras |
Bernt Schiele Max Planck Institute, DE |
Privacy and Security, Computer Vision, Machine Learning | The Bright and Dark Sides of Computer Vision and Machine Learning — Challenges and Opportunities for Privacy and Security |
Stefano Soatto Amazon and University of California Los Angeles, USA |
Learning Representations | Learning Representations: From Shannon to Fisher to Bayes to Kolmogorov via Deep Networks and the Implications to Visual Information Processing in Biology and in the Cloud |
Federico Tombari Technical University of Munich, DE |
3D descriptors, 3D object detection, 6DoF pose estimation, 3D reconstruction, SLAM | Features for 6D pose and 3D reconstruction: towards lightweight, monocular and unsupervised |
READING GROUP (WITH PRIZE!)
Speakers | Syllabus | Rules of Engagement |
Stefano Soatto Amazon and University of California Los Angeles, USA |
Reading Group Competition |
Rules of Engagement |
ESSAY COMPETITION (WITH PRIZE!)
Speakers | Syllabus | Rules of Engagement |
Fabio Galasso OSRAM Corporate Technology, DE |
Essay Competition |
Rules of Engagement |
INDUSTRY MEETS STUDENTS
Industrial Panel
- AWS, Amazon, US
- Ambarella-VISLAB, US
- Autonomous Intelligent Driving GmbH, DE
- Daqri, US
- Facebook Research, US
- Google, US
- Microsoft, US
- Naver Labs, EU
- PTC - Vuforia, US
- Qualcomm, US
- Rakuten, JP
- SeeQuestor, UK
- Toshiba Research Europe, UK
- Toyota Europe Motor, BE