FacebookFacebook group TwitterTwitter
ICVSS Computer Vision after Deep Learning

LECTURES

SpeakersSyllabusTitles & Abstracts
Daniel Cremers
Technische Universität München, DE
Dense 3D Reconstruction, Direct 3D Reconstruction, SLAM Dense & Direct Methods for 3D Reconstruction & Visual SLAM
Larry Davis
University of Maryland, USA
Face and object detection, attribute learning, visual recommendation systems, image to image regression, modeling face illumination Faces, Fashion, Forensics – Applications driving basic research in computer vision
Andrew Davison
Imperial College London, UK
SLAM, Spatial AI, Event Cameras From SLAM to Spatial AI
James J. DiCarlo
Massachusetts Institute of Technology, USA
Object Categorization, Face Detection and Discrimination, Human Vision, Neural Networks Reverse engineering human visual intelligence
Tom Drummond
Monash University, AU
Geometry, Lie groups, Deep learning, Multi-task learning, Uncertainty estimation Geometry and Deep Learning
Paolo Favaro
University of Bern, CH
Unsupervised Learning, Self-Supervised Learning, Transfer Learning, Representation Learning, Disentangling of Factors of Variation Beyond Supervised Learning
Chelsea Finn
UC Berkeley, USA
Deep Reinforcement Learning, Model-Based Reinforcement Learning, Self-Supervised Learning, Video Prediction and Generation, Robotic Perception and Control Deep Visuomotor Learning
Georgia Gkioxari
Facebook, USA
Object Recognition, Instance Segmentation, Pose Estimation, Detectron, Object Interactions, Pose Tracking Instance-level Visual Recognition
Georg Klein
Microsoft, USA
Mixed and Augmented Reality; SLAM; Embedded Computer Vision Head Tracking on HoloLens
Hugo Larochelle
Google Brain and Université de Sherbrooke, CA
Deep Learning, Transfer Learning, Representation Learning Generalizing from Few Examples with Meta-Learning
Victor Lempitsky
Skolkovo Institute of Science and Technology, RU
Convolutional Networks, Image Generation, Image Processing, Perceptual Losses, Adversarial Learning, Deep Image Prior Generative Convolutional Networks
Andrew Rabinovich
Magic Leap, USA
Multitask Learning, Transfer Learning, Gradient Normalization Multi Task Learning for Computer Vision
Josh Tenenbaum
Massachusetts Institute of Technology, USA
Vision Meets Common Sense Vision meets common sense: Seeing the physical and social worlds
Antonio Torralba
Massachusetts Institute of Technology and IBM, USA
Vision and Audition, Multimodal Learning, Self-Supervised Learning Multimodal self-supervised learning: learning to see and hear
Carl Vondrick
Columbia University and Google Research, USA
Predictive Vision, Anticipating Human Actions, Tracking Visual Objects, Recognizing Ambient Sound Predictive Vision

READING GROUP (WITH PRIZE!)

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

ESSAY COMPETITION (WITH PRIZE!)

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

INDUSTRY MEETS STUDENTS

Industrial Panel


POSTER SESSION (WITH PRIZE!)