FacebookFacebook group TwitterTwitter
ICVSS From Representation to Action and Interaction


SpeakersSyllabusTitles & Abstracts
Trevor Darrell
University of California, Berkeley, US
Adversarial Learning, Representation Learning, Learning in sparse/weakly labeled settings, Cross-Modal Learning Adversarial Perceptual Representation Learning Across Diverse Modalities and Domains
Vittorio Ferrari
University of Edinburgh, UK
Recognition and Localization of Visual Concepts, Interaction Between Visual Concepts, Minimal Human Supervision, Weakly Supervised Learning Training object localization models in weakly supervised settings
Sanja Fidler
University of Toronto, CA
Vision and Language, Learning Embedding Representations, Captioning, Retrieval, Question-Answering Learning Joint Embeddings of Vision and Language
Andrew Fitzgibbon
Microsoft, Cambridge, UK
Model Fitting, Vector and Matrix Calculus, Nonlinear Optimization Algorithms, Quasi-Newton and Gauss-Newton Derivates, Deal With Missing Data and Outliers, Robust Kernels Fitting models to data: Accuracy, Speed, Robustness
Emilio Frazzoli
ETH Z├╝rich - nuTonomy, US
Autonomous Cars, Perception for Action, Software and Hardware Architecture, Formal Methods vs. Learning, Design for Safety Perception for Action: on nuTonomy's Vision for Autonomous Driving
Ross B. Girshick
Facebook AI Research (FAIR), US
Object Detection, Instance Segmentation, Visual Reasoning, Deep Learning, Module Networks From Visual Perception to Visual Reasoning
Abhinav Gupta
Carnegie Mellon University (CMU), US
Representation Learning, Perception and Action, Unsupervised learning, Self-supervised Learning Self-supervised Learning of Visual Representations for Perception and Action
Vladlen Koltun
Intel Labs, US
Sensorimotor Control, Perception-Action Coupling, Reinforcement Learning and its Discontents, Natural Supervision Learning to Act with Natural Supervision
Hao Li
University of Southern California and Pinscreen Inc., US
Teleportation, Virtual Reality, 3D Digitalization, Photorealistic 3D, Dynamic Shape Reconstruction, Deep Learning Digital Human Teleportation using Deep Learning
Jiri Matas
Center for Machine Perception, CZ
Tracking, Deblurring, Blind Deconvolution Tracking of Fast Moving Objects
Jan Peters
Technische Universit├Ąt Darmstadt, DE
Reinforcement Learning, Policy Search, Robot Learning, Imitation Learning Learning Visuomotor Skills in Robotics
Ruslan Salakhutdinov
Apple & Carnegie Mellon University, US
Unsupervised Deep Learning, Multimodal Representations, Images from Captions, Deep Reinforcement Learning Learning Deep Unsupervised and Multimodal Models
Raquel Urtasun
University of Toronto and UBER, CA
Self-Driving Cars, Deep Learning, Robotics, Perception, Localization, Mapping Towards Affordable Self Driving Cars


SpeakersSyllabusRules of Engagement
Stefano Soatto
University of California, Los Angeles, US
Reading Group Competition Rules of Engagement


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


Industrial Panel