Roozbeh Mottaghi

Joint model-based and model-free RL for Visual Reaction

PyTorch implementation of our CVPR 2020 paper Visual Reaction: Learning To Play Catch With Your Drone.

Github page

Imitation learning for language instruction following

PyTorch implementation of our CVPR 2020 paper ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks.

Github page

Meta-learning for self-adapative navigation

PyTorch implementation of our CVPR 2019 paper Learning to Learn how to Learn: Self-Adaptive Visual Navigation using Meta-Learning and our ICLR 2019 paper Visual Semantic Navigation using Scene Priors.

Github page

Dog behavior modeling

Torch implementation of our CVPR 2018 paper Who Let The Dogs Out? Modeling Dog Behavior From Visual Data.

Github page

Occlusion reasoning

Torch implementation of our CVPR 2018 paper SeGAN: Segmenting and Generating the Invisible.

Github page

Physics-based prediction

Torch implementation of our ECCV 2016 paper "What happens if..." Learning to Predict the Effect of Forces in Images and our CVPR 2016 paper Newtonian Image Understanding: Unfolding the Dynamics of Objects in Static Images.

Github page for Newtonian Image Understanding
Github page for What Happens if