FacebookFacebook group TwitterTwitter
ICVSS Computer Vision - Where are we?


SpeakersSyllabusTitles & 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


SpeakersSyllabusRules of Engagement
Stefano Soatto
Amazon and University of California Los Angeles, USA
Reading Group Competition Rules of Engagement


SpeakersSyllabusRules of Engagement
Fabio Galasso
OSRAM Corporate Technology, DE
Essay Competition Rules of Engagement


Industrial Panel