Researcher Trevor Darrell

Researcher Biography
http://www.eecs.berkeley.edu/Faculty/Homepages/darrell.html

Current Projects

Simultaneous On-Target Domain Adaptation and Performance Prediction
Self-supervised Visual Pre-training for Motor Control
Similarity Learning for Multiple Object Tracking
BDD 100K and Beyond Data Labeling Efforts
Autonomous Driving in Unstructured Stochastic Intersections
Combining Deep Learning and Model Predictive Control for Safe, Effective Autonomous Driving

Past Projects

Predicting Pedestrian Behavior from 3D Cues
Domain Adaptation with Scene Structure
Object-centric Spatial-Temporal Interaction Networks for Rare Event Recognition
CyCADA: Cycle Consistent Adversarial Domain Adaptation
Public-Road Demonstration of the BDD/HCE Autonomous Driving Car
Robust Visual Understanding in Adversarial Environments
Adversarial Deep Learning for Autonomous Driving
Fast Simultaneous Object Detection and Segmentation
Clockwork FCNs for Fast Video Processing
Cross-modal Transfer Learning