306 citations · 1.5k across the 54 of their papers we have counts for
3 papers · 1 filter
Learning Visual Predictive Models of Physics for Playing Billiards
Katerina Fragkiadaki, Pulkit Agrawal, Sergey Levine +1
The ability to plan and execute goal specific actions in varied, unexpected settings is a central requirement of intelligent agents. In this paper, we explore how an agent can be e…
Human Pose Estimation with Iterative Error Feedback
Joao Carreira, Pulkit Agrawal, Katerina Fragkiadaki +1
Hierarchical feature extractors such as Convolutional Networks (ConvNets) have achieved impressive performance on a variety of classification tasks using purely feedforward process…
Learning to See by Moving
Pulkit Agrawal, Joao Carreira, Jitendra Malik
The dominant paradigm for feature learning in computer vision relies on training neural networks for the task of object recognition using millions of hand labelled images. Is it po…